Compare commits

..

232 Commits

Author SHA1 Message Date
panni cd9028354b incremental tmp 2021-03-09 03:09:52 +01:00
panni c77489a5be the heat 2020-08-12 17:02:54 +02:00
panni 25f204b330 whoops, missed dev flag 2020-08-12 17:01:06 +02:00
panni 89dded387d core: properly handle ReadTimeout 2020-08-12 16:09:53 +02:00
panni a9b677f0ce core: catch more exceptions 2020-08-08 03:46:57 +02:00
panni 6b918be799 release 2.6.5.3247 2020-07-26 03:12:35 +02:00
panni f259682391 core: findBetterSubtitles: increase minimum score for better subtitles for movies with extracted embedded subs from 82 to 112 2020-07-26 03:08:46 +02:00
panni 8a059c988e core: findBetterSubtitles: increase minimum score for better subtitles for movies with extracted embedded subs from 82 to 112 2020-07-26 03:07:04 +02:00
panni 8512940ccf core: fix for tv.plex.agents.movie not populating its media types 2020-07-26 02:54:28 +02:00
panni de2b11f69a back to dev 2020-07-25 05:56:40 +02:00
panni df1fba83a8 release 2.6.5.3241 2020-07-25 05:53:12 +02:00
panni d98ae74c8a 2.6.5.3241 2020-07-25 05:51:09 +02:00
panni 6484646122 advanced_settings: refiners: drone: add custom pem_file support; fixes #735 2020-07-25 05:22:57 +02:00
panni 52bac14a2e core: remove old remnants;
core: update certifi to 2020.6.20
2020-07-25 05:08:51 +02:00
panni 0be589bc5f add support for new Plex Movie agent 2020-07-25 05:01:12 +02:00
panni e083e133eb bump dev 2020-04-14 05:06:45 +02:00
panni c787e671c3 providers: addic7ed: enforce limits once they're hit, to avoid unnecessary search queries #723 2020-04-14 05:06:02 +02:00
panni 31ff93c3f1 fix logging; set DownloadLimitPerDayExceeded timeout to 4 hours (was one day); #723 2020-04-13 05:57:41 +02:00
panni 289f174e2b providers: addic7ed: properly implement limits #723 2020-04-13 05:54:04 +02:00
panni ea03f3fc4d providers: addic7ed: properly compare last_dl, add last_reset tracking info to log #723 2020-04-12 22:47:21 +02:00
panni 740fc93c13 bump dev 2020-04-12 06:54:36 +02:00
panni e94bd3fcb9 providers: addic7ed: limit downloads per day; add vip setting 2020-04-12 06:52:45 +02:00
panni dba469750b submod: HI: remove more music tags
core: update pysubs2
providers: opensubtitles: actually use sessions (they're broken) for checking for token state
2020-04-11 05:06:12 +02:00
panni c7fe6076cb bump version 2020-03-08 16:32:40 +01:00
panni 356f578014 remove py3 compat breaking unnecessary change 2020-03-08 16:29:49 +01:00
panni b151ed4c55 core: mods: CM_punctuation_space2: detect AND don't try changing domain/url/host when fixing punctuation
add python-tld; functools_lru_cache
2020-03-08 05:37:32 +01:00
panni 9455e3b52b skip drawing tags for SRT 2020-03-08 05:18:20 +01:00
panni 60e2656541 back to dev 2020-02-16 06:06:23 +01:00
panni fcb1a8a6a7 release 2.6.5.3223 2020-02-16 06:05:04 +01:00
panni 9e5829151d release 2.6.5.3223 2020-02-16 06:03:21 +01:00
panni 1f0a713f9b core: scoring: reorder subtitles based on second non-hash-score if main hash score is the same; morpheus65535/bazarr#821 2020-02-16 05:44:59 +01:00
panni ff49dd4512 providers: bsplayer: verify hash; clean up 2020-02-16 05:08:50 +01:00
panni 3cf83b5bf7 back to dev 2020-02-15 03:17:36 +01:00
panni c51ce55d32 update maintenance state in readme 2020-02-15 03:17:00 +01:00
panni ee9268957d release 2.6.5.3217 2020-02-15 03:16:32 +01:00
panni 5d1858d5da 2.6.5.3217 2020-02-15 03:15:17 +01:00
panni d59abea1f5 changelog 2020-02-15 03:02:05 +01:00
panni e6b79334d8 core: scheduler: add option to specify subtitle storage maintenance 2020-02-15 03:00:06 +01:00
panni 88d2a44f08 core: reuse OS hash
core: refiners: tvdb: don't fail on bad firstAired date
2020-02-15 02:27:11 +01:00
panni 78e47d3cd5 providers: screwzira: move config;
providers: add BSPlayer
2020-02-15 02:10:32 +01:00
panni 6b6af347da providers: screwzira: disable when foreign only is enabled 2020-02-15 02:08:16 +01:00
panni dccee96cf1 Merge branch 'master' into develop-2.6 2020-02-15 02:06:59 +01:00
pannal 92b24de7cd Merge pull request #698 from dornizar/master
ScrewZira Hebrew subtitle support
2020-02-15 02:04:53 +01:00
panni 1225a4887c bump dev 2020-01-19 05:39:41 +01:00
panni 2a82857570 #711 plex security blerp 2020-01-19 05:38:59 +01:00
panni 831bec3630 bump dev 2020-01-19 05:35:10 +01:00
panni 55cbf2478a morpheus65535/bazarr#656 further generalize formats; skip release group match if format match failed 2020-01-19 05:02:34 +01:00
panni 20a850b9e9 #711 use correct Log function 2020-01-18 23:26:43 +01:00
panni 11c649a7af #711 don't fail on inexistant stream IDs when detecting extra stream info (mediainfo) 2020-01-18 23:21:01 +01:00
panni c1e5a2077b Merge branch 'bzr_#703' into develop-2.6 2019-12-25 01:39:13 +01:00
panni dc96f626dd bazarr #703: py3 compat backport 2019-12-25 01:32:32 +01:00
panni 46f48023f4 bazarr #660: lowercase all BOM encodings 2019-12-24 00:44:53 +01:00
panni e3d83f6dc2 bazarr #660: don't double-check encodings when BOM encoding detected 2019-12-24 00:42:50 +01:00
panni fc484e569f bazarr #660: try detecting BOMs before doing any other encoding guessing 2019-12-24 00:38:50 +01:00
panni a92f3e2480 bazarr #703: use proper language code detection instead of a wild guess; should fix bad existing subtitle detection 2019-12-24 00:10:26 +01:00
dor 064c447528 changed imports to subliminal_patch 2019-11-09 21:32:02 +02:00
panni 64c1bcd9e6 bump dev 2019-11-09 04:46:56 +01:00
panni 0cca4a2ebe core: UnRAR: set binary to executable, even if not checked out from git; might fix #693 2019-11-09 04:28:14 +01:00
panni c4c26a76f1 core: clarify Detecting Streams 2019-11-09 03:57:38 +01:00
panni 1a638431d7 core: when extracting embedded subtitles from task, execute threads synchronously 2019-11-09 03:19:01 +01:00
panni 5d5fa21630 refactor all extraction into support.extract; extract also on SearchAllRecentlyAddedMissing 2019-11-09 02:59:36 +01:00
dor e78ace4664 ScrewZira Hebrew subtitle support
www.screwzira.com
2019-11-07 18:54:52 +02:00
panni 37596c412c Merge branch 'master' into develop-2.6 2019-10-26 04:57:34 +02:00
panni d200021243 Merge remote-tracking branch 'origin/master' 2019-10-26 04:44:55 +02:00
panni 1a999e202f release 2.6.5.3183 2019-10-26 04:44:24 +02:00
panni fd748b29e9 fix changelog 2019-10-26 04:41:26 +02:00
panni 775d1e3cf1 back to dev 2019-10-26 04:39:15 +02:00
panni c6a1df9a79 release 2.6.5.3152 2019-10-26 04:38:34 +02:00
panni 77861a4c6d release 2.6.5.3152 2019-10-26 04:38:03 +02:00
panni bf1e1c3139 bump dev 2019-10-26 04:17:25 +02:00
panni a564a1d808 providers: addic7ed: wait a short while between retries and after successfully logging in 2019-10-26 04:14:38 +02:00
panni 22ac935f9b core: scanning: add additional INFO logging for undetected languages 2019-10-23 14:12:37 +02:00
panni 02e2bcb417 bump dev 2019-10-21 17:21:01 +02:00
panni 3445259cde providers: addic7ed: fix detection of completed subtitle (#686) 2019-10-21 17:15:02 +02:00
panni c20c32c17d providers: addic7ed: refresh show IDs if stored ones were empty 2019-10-21 17:10:34 +02:00
panni 3fec766890 core: fix #688 2019-10-21 16:03:40 +02:00
panni f208a24213 providers: addic7ed: fix bungled show_ids reference; #686 2019-10-20 16:53:13 +02:00
panni 9e9dfb3f4d providers: addic7ed: fix Mayans M.C.; add logging; fix AuthenticationError 2019-10-20 05:50:33 +02:00
panni 83eecf09ed bump dev 2019-10-20 05:20:13 +02:00
panni 1aebe8d0dd providers: addic7ed: fix getting show ids (failing on foreign characters)
providers: addic7ed: don't run anything if no credentials given
providers: addic7ed: actually try three times to log in
providers: addic7ed: store last show ids fetch; when show id not found, re-try once per day
2019-10-20 05:19:05 +02:00
panni bb64e482df providers: addic7ed: fix getting show list (failing on foreign characters)
providers: addic7ed: don't run anything if no credentials given
providers: addic7ed: actually try three times to log in
2019-10-20 05:04:02 +02:00
panni 1841a72ca7 bump dev 2019-10-20 04:00:23 +02:00
panni 997d4aa1cf core: don't process any further if stream info is missing 2019-10-20 03:59:39 +02:00
panni d517e86333 core: don't fall back to default providers if none enabled 2019-10-20 03:45:16 +02:00
panni 8bcfc712fb updated dev 2019-10-19 23:21:03 +02:00
panni c0cf2fd78e providers: argenteam: bazarr-backport: use new url; fixes 2019-10-19 23:19:19 +02:00
panni 0a7de0e9b6 core: bazarr-backport: generic 10 minute throttling if uncaught exception occurs; also for downloads 2019-10-19 23:17:09 +02:00
panni 1e2a127dac core: bazarr-backport: generic 10 minute throttling if uncaught exception occurs 2019-10-19 23:13:57 +02:00
panni 5b8cd215e4 core: backport removal of existing subtitle file from bazarr, to support MergerFS 2019-10-19 23:02:57 +02:00
panni 7583edf3fe providers: addic7ed: move re to correct place; fix show match; #686 2019-10-19 15:36:46 +02:00
panni 2f219a1a81 providers: addic7ed: fix show match 2019-10-19 15:35:19 +02:00
panni 9127c38297 bump dev 2019-10-19 07:15:45 +02:00
panni 0c379f8b9f providers: addic7ed: add timeout on authentication error 2019-10-19 07:15:07 +02:00
panni d2b617bdf4 addicted; fix #686 2019-10-19 06:55:32 +02:00
panni 6d6f6d9356 forgot to fix #681 2019-10-19 06:54:38 +02:00
panni 8ffb20ebe3 try fixing #681 2019-10-07 15:13:00 +02:00
panni eed7b9da0c core: support using mediainfo for retrieving MP4 MOV_TEXT subtitle stream titles (PMS bug) 2019-10-05 16:47:45 +02:00
panni 802381b2bc back to dev 2019-10-05 04:25:48 +02:00
panni f265c861d2 back to dev 2019-10-05 04:24:20 +02:00
panni 1dc7b4b5e4 back to dev 2019-10-05 04:15:11 +02:00
panni c48aa2b255 release 2.6.5.3152 2019-10-05 04:14:28 +02:00
panni 66859802f9 update readme 2019-10-05 04:13:50 +02:00
panni 433c8e987b back from dev 2019-10-05 04:07:52 +02:00
panni aa477ca48c Merge branch 'develop-2.6' 2019-10-05 04:07:33 +02:00
pannal 65b502afa4 bump dev 2019-09-21 16:25:33 +02:00
pannal 06c0b44589 fix Dicked.get 2019-09-21 16:24:21 +02:00
pannal d651f2cbb7 bump dev 2019-09-20 18:24:16 +02:00
pannal 8b5be8ea4b #676 improve 2019-09-20 18:14:14 +02:00
pannal f4e82c560d core: fix default values of opensubtitles-skip-wrong-fps, use_https; fix #676 2019-09-20 18:10:16 +02:00
panni c23b3e93a6 bump dev 2019-08-31 14:33:04 +02:00
panni de447d2d0b core: fix for determining whether to search under certain circumstances; fixes #666 2019-08-31 14:32:42 +02:00
panni 95b1272018 explicit language=None check 2019-08-25 06:12:48 +02:00
pannal 11d111da7c Update README.md 2019-08-24 04:51:26 +02:00
pannal 638dec0f04 Update README.md 2019-08-24 04:45:45 +02:00
panni a0ab6e406a providers: titlovi: raise ConfigurationError if credentials aren't given 2019-08-22 15:46:38 +02:00
panni 23242c0f52 bump dev 2019-08-22 15:34:45 +02:00
pannal 48bf70e825 Merge pull request #660 from viking1304/develop-2.6
New implementation of Titlovi using API
2019-08-22 15:32:43 +02:00
panni ada0b96872 #664 fix missing language processing of multiple videos refreshed at once 2019-08-22 14:58:28 +02:00
panni 0e4917bba9 #661 further improvements 2019-08-13 18:06:06 +02:00
panni 8169d31e86 #661 fix bad condition 2019-08-13 13:01:05 +02:00
panni 75b83aa163 #661 fix match strictness when determining preexisting external subtitles 2019-08-13 12:56:08 +02:00
viking1304 d2022de970 Removed titlovi from AntiCaptcha lablel 2019-08-12 21:02:51 +02:00
viking1304 8db1cdacb4 Revert "Disable provider Titlovi if user and password are not set"
This reverts commit 527d171a6a.
2019-08-09 19:01:08 +02:00
viking1304 527d171a6a Disable provider Titlovi if user and password are not set 2019-08-09 18:54:35 +02:00
viking1304 20620cfa7e New implentation of Titlovi using API 2019-08-09 18:22:42 +02:00
panni 4d03ca078d back to dev 2019-08-09 03:38:54 +02:00
panni 775e2cca47 Merge remote-tracking branch 'origin/master' 2019-08-09 03:13:46 +02:00
panni 7cb2486d3e release 2.6.5.3124 2019-08-09 03:13:34 +02:00
panni 02a3ecc9fe prepare for release 2019-08-09 03:11:55 +02:00
panni 54435398af bump dev 2019-08-08 15:09:04 +02:00
panni ffc42883de core: extract embedded/menu: fix detection of unknown streams; don't use unknown streams if a known language was previously found 2019-08-08 14:30:29 +02:00
panni 0cf0371a43 core: language: use replacement map from bazarr 2019-08-06 18:04:34 +02:00
panni f5156bcea7 providers: titlovi: fix matching 2019-07-27 03:10:08 +02:00
panni efdf3b2c9d core: http: fallback to default DNS when normal resolving fails; fixes #657 2019-07-27 02:57:35 +02:00
panni c3d3163392 providers: subscene: fix unknown language code error when "empty" result is returned 2019-07-05 13:56:21 +02:00
panni c91d5ca483 providers: subscene: add support for pt-BR (based on https://github.com/Diaoul/subliminal/pull/740/commits/b22cf08a5d0e7082b0dc6c0de8cc764f01233625) 2019-07-05 13:55:52 +02:00
panni 5f0982970d docker/bazarr compat 2019-07-05 03:22:06 +02:00
panni ee05da70f4 providers: subscene: explicitly set account filters for languages 2019-06-23 15:26:41 +02:00
panni 04c283c48d providers: subscene: limit alternative searches to 3; set throttle to 8 2019-06-23 04:24:18 +02:00
panni 836945c95c providers: subscene: move login/cookies to initialization sequence 2019-06-22 16:45:31 +02:00
panni bd4c180c07 submod: generic: en: fix ";='s 2019-06-22 04:29:03 +02:00
pannal e1f5290365 Update README.md 2019-06-22 04:07:30 +02:00
panni eefffcfb1b back to dev 2019-06-22 04:06:10 +02:00
panni 9e088a5e9d release 2.6.5.3109 2019-06-22 04:05:37 +02:00
panni 317c02bf06 prepare next release 2019-06-22 04:04:22 +02:00
panni 22724c269c core: bazarr compat 2019-06-21 15:04:00 +02:00
panni 2a48782b6b core: bazarr compat 2019-06-21 15:00:35 +02:00
panni e7c3039fde providers: subscene: detect login availability; fallback to non year results if none found with year 2019-06-21 04:49:54 +02:00
panni 2afba02b59 bump dev 2019-06-21 04:17:15 +02:00
panni 94928c2930 providers: add Napisy24 (polish) 2019-06-21 04:16:46 +02:00
panni 2c25191291 providers: subscene: support logging in 2019-06-20 16:11:21 +02:00
panni ba2f3f2172 back to dev 2019-06-06 02:18:34 +02:00
panni aa5cba9347 release 2.6.5.3099 2019-06-06 02:15:23 +02:00
panni 5f40452f57 release 2.6.5.3099 2019-06-06 02:14:50 +02:00
panni 2dd9b1723b core: allow system DNS again by putting "system" as the DNS 2019-06-06 02:13:20 +02:00
panni ee54839f28 back to dev 2019-06-06 01:45:16 +02:00
panni c2f054a25e release 2.6.5.3096 2019-06-06 01:41:57 +02:00
panni f095d5c99c providers: subscene: remove obsolete exception handling 2019-06-06 01:38:28 +02:00
panni ab93f9809a providers: subscene: dumb down endpoint detection; adapt 2019-06-06 01:31:27 +02:00
panni bbb9a62357 back to dev 2019-05-30 04:23:49 +02:00
panni 82ffed699f release 2.6.5.3092 2019-05-30 04:23:07 +02:00
panni 4751ea8396 bump dev 2019-05-30 04:21:50 +02:00
panni c15d8fbe58 bump dev 2019-05-30 04:14:38 +02:00
panni b379468b47 properly re-raise 2019-05-30 04:13:00 +02:00
panni 0deb3eae21 providers: subscene: react to new endpoint; store and use new endpoint 2019-05-30 04:11:12 +02:00
panni 0c1042ec5c bump dev 2019-05-27 12:39:04 +02:00
panni 05d0de5120 core: providers: argenteam: backport fixes from bazarr 2019-05-27 12:34:37 +02:00
panni 2fa217d5d9 core: subtitle: encoding: re-revert 1ed4f11 2019-05-27 12:27:18 +02:00
panni a65b5a5d82 core: missed forced utf-8 instance 2019-05-24 18:10:09 +02:00
panni 7bb42e95d8 core: add env var SZ_KEEP_ENCODING to keep encoding of subtitles 2019-05-24 18:06:00 +02:00
panni db536502a1 bump dev 2019-05-19 06:06:43 +02:00
panni 47c8f1a2e6 Merge branch 'submod_opt' into develop-2.6 2019-05-19 06:04:17 +02:00
panni 30a0f11515 providers: subscene: don't calculate video fn for now 2019-05-19 04:27:20 +02:00
panni 9bf5123a00 providers: subscene: don't search for season packs (broken); fix endpoint error handling 2019-05-18 15:03:53 +02:00
panni f337b53ae3 submod: HI: remove music
submod: common: be less aggressive about music symbols
submod: HI: be less aggressive about brackets
submod: HI: be less aggressive about MAN
2019-05-18 06:23:04 +02:00
panni aea6050d71 subtitle: try decoding with utf-16 by default as well 2019-05-17 23:45:06 +02:00
panni 13d5e0761e providers: subscene: fix endpoint once again 2019-05-13 16:14:26 +02:00
panni ce28d0284c back from dev 2019-05-12 06:17:08 +02:00
panni 1a0bb9c3e4 release 2.6.5.3074 2019-05-12 06:05:16 +02:00
panni d0c71b4b67 bump dev 2019-05-12 05:12:58 +02:00
panni b3f062956d core: re-fix ass/ssa tags in srt in pysubs2 0.2.3 2019-05-12 05:12:34 +02:00
panni 1a853a780c core: update pysubs2 to 0.2.3 2019-05-12 05:01:38 +02:00
panni 5c47ddeb2d core: update chinese encodings; #646 2019-05-12 04:49:30 +02:00
panni b51deb5d01 core: subliminal: don't replace \r with \n by default; fixes utf-16 character transformation issues; fixes #646 2019-05-12 04:48:23 +02:00
panni cbf5ea69be core: cf: update cloudscraper to 1.1.9; fix keyerror 2019-05-08 15:57:33 +02:00
panni e139ffefe6 bump dev 2019-05-08 04:18:25 +02:00
panni dc0a8deb40 core: cf: testing
providers: subscene: testing
2019-05-08 04:14:04 +02:00
panni 97e93cd10a core: cf: update js2py; update cloudscraper to 1.1.5; 2019-05-08 01:31:21 +02:00
panni 03c934cf21 back to dev 2019-05-01 15:39:23 +02:00
panni 92d0d70258 Release 2.6.5.3062 2019-05-01 15:32:36 +02:00
panni d44298993c Release 2.6.5.3055 2019-05-01 15:32:19 +02:00
panni 12300d4115 Merge branch 'develop-2.6' 2019-05-01 15:29:42 +02:00
pannal b4f08f61a6 Update README.md 2019-05-01 06:00:01 +02:00
pannal 861a25be41 Update README.md 2019-05-01 05:59:21 +02:00
pannal 3e175109a6 Merge pull request #641 from fossabot/master
Add license scan report and status
2019-05-01 05:48:14 +02:00
fossabot fb2210f2fd Add license scan report and status
Signed-off-by: fossabot <badges@fossa.io>
2019-04-30 20:44:05 -07:00
panni e928918201 add cloudscaper LICENSE 2019-05-01 05:13:13 +02:00
panni df607e5772 bump dev 2019-05-01 04:49:30 +02:00
panni a7cc470645 core: log cf domain 2019-05-01 04:48:48 +02:00
panni 4e6421b928 core: dns: set env var empty if not configured 2019-05-01 04:36:03 +02:00
panni df48e8fccd providers: subscene: remove obsolete imports 2019-05-01 04:27:11 +02:00
panni 58111bf204 core: remove old cfscrape implementation 2019-05-01 04:25:04 +02:00
panni 8c02e75fed providers: titlovi: match cfsrc for src 2019-05-01 04:24:31 +02:00
panni 6f3f1cb4b5 core: cf: harden. 2019-05-01 04:24:09 +02:00
panni dd27997deb core: cf: add cloudscaper 1.1.1@496900e instead of cfscrape 2019-05-01 03:12:01 +02:00
panni a1f70d1d4d core: add ENV:dns_resolvers_timeout 2019-05-01 02:39:18 +02:00
panni 7da0bac643 skip warning 2019-05-01 02:33:46 +02:00
panni b3ab2a451c core: http: don't query DNS with IPs. thanks @fgump 2019-05-01 02:27:30 +02:00
panni 850f836ebd back to dev 2019-04-28 05:27:26 +02:00
panni d9fa9d03da back to dev 2019-04-28 05:22:24 +02:00
pannal 76c20dc3d7 Update README.md 2019-04-28 05:21:35 +02:00
panni 4568e222d1 release 2.6.5.3041 2019-04-28 05:11:45 +02:00
panni 344025226a add missing changelog entry 2019-04-28 05:11:09 +02:00
panni f546fcffce release 2.6.5.3039 2019-04-28 05:08:00 +02:00
panni 068c2d4d00 Merge remote-tracking branch 'origin/master'
# Conflicts:
#	Contents/Info.plist
2019-04-28 05:04:51 +02:00
panni ccf5a902e5 core: cf: only store cookie if it had a value 2019-04-28 05:03:04 +02:00
panni 8c72cf9057 bump dev 2019-04-28 04:45:17 +02:00
panni 1ce14aa231 core: http: remove debug 2019-04-28 04:44:27 +02:00
panni 643485b879 core: cf: optimize
providers: titlovi: optimize cf/captcha handling
2019-04-28 04:43:03 +02:00
pannal 5b3d9f26be Update README.md 2019-04-28 03:47:55 +02:00
panni 70674fbce7 i128n: remove obsolete trans 2019-04-28 03:30:35 +02:00
panni f48c0799c0 i128n: remove obsolete trans 2019-04-28 03:28:44 +02:00
pannal 3bc646187f Update de.json (POEditor.com) 2019-04-28 03:21:46 +02:00
pannal b692ebde6f Update de.json (POEditor.com) 2019-04-28 03:20:52 +02:00
panni d2a665624a core/config: add setting for one existing language to be enough, fixes #491 2019-04-28 03:10:33 +02:00
panni 10c8b8ceff core: dns: be a tad smarter 2019-04-27 06:43:46 +02:00
panni 92edfc7312 bump dev 2019-04-27 06:37:43 +02:00
panni eeaeb80f0f core/compat: dns: support nameservers via ENV[dns_resolvers]; don't fall back to default DNS when configured custom DNS failed 2019-04-27 06:37:09 +02:00
panni 6204572ddc core: only reference guessed title if there actually is one 2019-04-26 15:32:59 +02:00
pannal 14f2f45f20 Update README.md 2019-04-22 05:37:47 +02:00
pannal 8ac6c9d7a7 Update README.md 2019-04-22 05:31:29 +02:00
panni 96bdf606e2 back to dev 2019-04-21 03:46:25 +02:00
129 changed files with 63283 additions and 1719 deletions
+165
View File
@@ -1,3 +1,168 @@
2.6.5.3217
subscene, addic7ed
- either of those providers might impose a reCAPTCHA verification. In order to use those providers, please create an account at an AntiCaptcha service ([anti-captcha.com](http://getcaptchasolution.com/kkvviom7nh) or [deathbycaptcha.com](http://deathbycaptcha.com)), add funds, then supply your credentials/apikey in the configuration
Changelog
- core: also extract (missing) embedded subtitles when SearchAllRecentlyAddedMissing is running
- core: core: clarify detecting streams (in logs)
- core: UnRAR: set binary to executable, even if not checked out from git; might fix #693
- core: bazarr-backport: morpheus65535/bazarr#703: use proper language code detection instead of a wild guess; should fix bad existing subtitle detection
- core: bazarr-backport: morpheus65535/bazarr#660: fix BOM encoding stuff
- core: bazarr-backport: morpheus65535/bazarr#656 further generalize formats; skip release group match if format match failed
- core: fix stream detection when using mediainfo (#711)
- config/core: make periodic SZ-internal subtitle maintenance interval configurable
- providers: add BSPlayer Subtitles
- providers: add ScrewZira (Hebrew)
2.6.5.3183
subscene, addic7ed
- either of those providers might impose a reCAPTCHA verification. In order to use those providers, please create an account at an AntiCaptcha service ([anti-captcha.com](http://getcaptchasolution.com/kkvviom7nh) or [deathbycaptcha.com](http://deathbycaptcha.com)), add funds, then supply your credentials/apikey in the configuration
Changelog
- core: don't fall back to default providers if none enabled
- core: don't process any further if stream info is missing
- core: support using mediainfo for retrieving MP4 MOV_TEXT subtitle stream titles (PMS bug)
- core: fix embedded subtitle extraction in some cases (#681, #680)
- core: scanning: add additional INFO logging for undetected languages
- core: bazarr-backport: remove existing subtitle file, to support MergerFS
- core: bazarr-backport: generic 10 minute throttling if uncaught exception occurs
- providers: addic7ed: fix recaptcha solving; fix show ID retrieval (#681)
- providers: addic7ed: add timeout on authentication error
- providers: addic7ed: fix shows with dots in them (Mayans M.C.)
- providers: addic7ed: fix detection of completed subtitle for non-english users (#686)
- providers: addic7ed: add more timeouts in the login process
- providers: argenteam: bazarr-backport: use new url; fixes
2.6.5.3152
subscene, addic7ed
- either of those providers might impose a reCAPTCHA verification. In order to use those providers, please create an account at an AntiCaptcha service ([anti-captcha.com](http://getcaptchasolution.com/kkvviom7nh) or [deathbycaptcha.com](http://deathbycaptcha.com)), add funds, then supply your credentials/apikey in the configuration
Changelog
- core: fix core issue possibly impacting results on OpenSubtitles in certain conditions
- core: fix default values of opensubtitles-skip-wrong-fps, use_https; fix #676
- core: fix for determining whether to search under certain circumstances; fixes #666
- core: #664 fix missing language processing of multiple videos refreshed at once
- core: #661 fix match strictness when determining preexisting external subtitles
- providers: titlovi: New implementation of Titlovi using API (thanks @viking1304)
2.6.5.3124
subscene, addic7ed and titlovi
- either of those providers might impose a reCAPTCHA verification. In order to use those providers, please create an account at an AntiCaptcha service ([anti-captcha.com](http://getcaptchasolution.com/kkvviom7nh) or [deathbycaptcha.com](http://deathbycaptcha.com)), add funds, then supply your credentials/apikey in the configuration
Changelog
- core: http: fallback to default DNS when normal resolving fails; fixes #657
- core: extract embedded/menu: fix detection of unknown streams; don't use unknown streams if a known language was previously found
- core: language: use replacement map from bazarr
- providers: titlovi: fix matching
- providers: subscene: fix unknown language code error when "empty" result is returned
- providers: subscene: add support for pt-BR (based on Diaoul/subliminal@b22cf08)
- providers: subscene: explicitly set account filters for languages
- providers: subscene: limit alternative searches to 3; set throttle to 8
- providers: subscene: move login/cookies to initialization sequence
- submod: generic: en: fix ";='s
2.6.5.3109
subscene, addic7ed and titlovi
- either of those providers might impose a reCAPTCHA verification. In order to use those providers, please create an account at an AntiCaptcha service ([anti-captcha.com](http://getcaptchasolution.com/kkvviom7nh) or [deathbycaptcha.com](http://deathbycaptcha.com)), add funds, then supply your credentials/apikey in the configuration
Changelog
- providers: add Napisy24 (polish)
- providers: subscene: reduce provider load by possibly half
- providers: subscene: support logging in (username/password are now required)
- providers: subscene: fallback to non year results if none found with year
2.6.5.3099
subscene, addic7ed and titlovi
- either of those providers might impose a reCAPTCHA verification. In order to use those providers, please create an account at an AntiCaptcha service ([anti-captcha.com](http://getcaptchasolution.com/kkvviom7nh) or [deathbycaptcha.com](http://deathbycaptcha.com)), add funds, then supply your credentials/apikey in the configuration
Changelog
- core: allow system DNS again by putting "system" as the DNS
- providers: subscene: fix again (subscene, contact us please, so we can end this)
2.6.5.3092
subscene, addic7ed and titlovi
- either of those providers might impose a reCAPTCHA verification. In order to use those providers, please create an account at an AntiCaptcha service ([anti-captcha.com](http://getcaptchasolution.com/kkvviom7nh) or [deathbycaptcha.com](http://deathbycaptcha.com)), add funds, then supply your credentials/apikey in the configuration
Changelog
- providers: subscene: fix endpoint (hopefully for longer now)
- providers: subscene: don't search for season packs (broken for now; relieves 50% of server load on provider)
- providers: subscene: don't calculate video fn for now
- providers: argenteam: backport fixes from bazarr
- subtitle: try decoding with utf-16 by default as well (zho/farsi)
- submod: HI: remove music tags by default
- core: compat (bazarr): add env var SZ_KEEP_ENCODING to keep encoding of subtitles
2.6.5.3074
Changelog
- core: cf: bypass cf 95% of the time without captchas
- core: fix breaking line endings of certain languages (chinese, UTF-16); fixes #646
- core: update pysubs2 to 0.2.3
2.6.5.3062
Changelog
- core: cf: optimize
- core: http: don't query DNS with IPs. thanks @fgump (fixes sonarr/radarr)
2.6.5.3041
Changelog
- core: only reference guessed title if there actually is one
- core: cf: optimize
- core/config: add setting for one existing language to be enough, fixes #491
- core/compat: dns: support nameservers via ENV[dns_resolvers]; don't fall back to default DNS when configured custom DNS failed
- providers: titlovi: prevent repeated captcha solving for CF
2.6.5.3017
Changelog
- core: SRT parsing: handle (bad) ASS color tag in SRT
- core: auto extract embedded: only use one unknown sub for first language
- core: better embedded streams language detection
- core: optimizations
- core: extract embedded: fix is_unknown check
- core: don't raise exception when subtitle not found inside archive
- core: search external subtitles: fix condition
- core: better plex transcoder path detection
- core: use Log.Warn instead of Log.Warning (#619, #629, #633)
- core: also check for "plex transcoder.exe" in case of windows (fixes #619)
- core: auto extract: use mbcs encoding for paths on windows
- core: Fix issue scandir not returning the name of the file inside Docker images on ARM systems. (thanks @giejay)
- core: also clean PYTHONHOME when calling external notification app
- core: update certifi to 2019.3.9
- core: scan_video: add series/title as alternative by scanning filename itself without parent folders
- core: add generic solution for solving captchas using anti captcha services
- core: increase cache time to 180d (was: 30d)
- core: guess_matches: handle multiple title matches; fixes bazarr#403
- windows: fix compatibility issues with plex transcoder
- compat: use lowercase paths on subtitle detection
- providers: addic7ed: re-enable (using paid anti captch service)
- providers: assrt: assume undefined Chinese flavor as Simplified (chs/zho-Hans)
- providers: subscene: make it work again by bypassing cf
- providers: subscene: don't fail on missing cover
- providers: titlovi: re-enable (might need paid anti captch service)
- providers: opensubtitles: fix only_foreign handling
- providers: opensubtitles: show subtitles with possibly mismatched series when manually listing subs
- menu: list subtitles: show subtitles with bad season/episode values as well
- refiners: omdb: fix imdb ids with spaces
2.6.4.2911
- core: improve file cache (windows especially); use fixed-length cache filenames; fixes #600
+8 -56
View File
@@ -21,20 +21,21 @@ import support
import interface
sys.modules["interface"] = interface
from subzero.constants import OS_PLEX_USERAGENT, PERSONAL_MEDIA_IDENTIFIER
from subzero.constants import OS_PLEX_USERAGENT
from interface.menu import *
from support.plex_media import media_to_videos, get_media_item_ids
from support.extract import agent_extract_embedded
from support.scanning import scan_videos
from support.storage import save_subtitles, store_subtitle_info, get_subtitle_storage
from support.storage import save_subtitles, store_subtitle_info
from support.items import is_wanted
from support.config import config
from support.lib import get_intent
from support.helpers import track_usage, get_title_for_video_metadata, get_identifier, cast_bool, \
audio_streams_match_languages
from support.helpers import track_usage, get_title_for_video_metadata, get_identifier, cast_bool
from support.history import get_history
from support.data import dispatch_migrate
from support.activities import activity
from support.download import download_best_subtitles
from support.localmedia import find_subtitles
def Start():
@@ -96,57 +97,7 @@ def Start():
def update_local_media(videos, ignore_parts_cleanup=None):
for video in videos:
support.localmedia.find_subtitles(video["plex_part"], ignore_parts_cleanup=ignore_parts_cleanup)
def agent_extract_embedded(video_part_map):
try:
subtitle_storage = get_subtitle_storage()
to_extract = []
item_count = 0
for scanned_video, part_info in video_part_map.iteritems():
plexapi_item = scanned_video.plexapi_metadata["item"]
stored_subs = subtitle_storage.load_or_new(plexapi_item)
valid_langs_in_media = audio_streams_match_languages(scanned_video, config.get_lang_list(ordered=True))
if not config.lang_list.difference(valid_langs_in_media):
Log.Debug("Skipping embedded subtitle extraction for %s, audio streams are in correct language(s)",
plexapi_item.rating_key)
continue
for plexapi_part in get_all_parts(plexapi_item):
item_count = item_count + 1
used_one_unknown_stream = False
for requested_language in config.lang_list:
embedded_subs = stored_subs.get_by_provider(plexapi_part.id, requested_language, "embedded")
current = stored_subs.get_any(plexapi_part.id, requested_language) or \
requested_language in scanned_video.external_subtitle_languages
if not embedded_subs:
stream_data = get_embedded_subtitle_streams(plexapi_part, requested_language=requested_language,
skip_unknown=used_one_unknown_stream)
if stream_data:
stream = stream_data[0]["stream"]
if stream_data[0]["is_unknown"]:
used_one_unknown_stream = True
to_extract.append(({scanned_video: part_info}, plexapi_part, str(stream.index),
str(requested_language), not current))
if not cast_bool(Prefs["subtitles.search_after_autoextract"]):
scanned_video.subtitle_languages.update({requested_language})
else:
Log.Debug("Skipping embedded subtitle extraction for %s, already got %r from %s",
plexapi_item.rating_key, requested_language, embedded_subs[0].id)
if to_extract:
Log.Info("Triggering extraction of %d embedded subtitles of %d items", len(to_extract), item_count)
Thread.Create(multi_extract_embedded, stream_list=to_extract, refresh=True, with_mods=True,
single_thread=not config.advanced.auto_extract_multithread)
except:
Log.Error("Something went wrong when auto-extracting subtitles, continuing: %s", traceback.format_exc())
find_subtitles(video["plex_part"], ignore_parts_cleanup=ignore_parts_cleanup)
class SubZeroAgent(object):
@@ -311,7 +262,8 @@ class SubZeroAgent(object):
class SubZeroSubtitlesAgentMovies(SubZeroAgent, Agent.Movies):
contributes_to = ['com.plexapp.agents.imdb', 'com.plexapp.agents.xbmcnfo', 'com.plexapp.agents.themoviedb', 'com.plexapp.agents.hama']
contributes_to = ['com.plexapp.agents.imdb', 'com.plexapp.agents.xbmcnfo', 'com.plexapp.agents.themoviedb',
'com.plexapp.agents.hama', 'tv.plex.agents.movie']
score_prefs_key = "subtitles.search.minimumMovieScore2"
agent_type_verbose = "Movies"
+29 -26
View File
@@ -7,14 +7,16 @@ from subzero.language import Language
from sub_mod import SubtitleModificationsMenu
from menu_helpers import debounce, SubFolderObjectContainer, default_thumb, add_incl_excl_options, get_item_task_data, \
set_refresh_menu_state, route, extract_embedded_sub
set_refresh_menu_state, route
from support.extract import extract_embedded_sub
from refresh_item import RefreshItem
from subzero.constants import PREFIX
from support.config import config, TEXT_SUBTITLE_EXTS
from support.helpers import timestamp, df, get_language, display_language, get_language_from_stream, is_stream_forced
from support.helpers import timestamp, df, get_language, display_language, get_language_from_stream
from support.items import get_item_kind_from_rating_key, get_item, get_current_sub, get_item_title, save_stored_sub
from support.plex_media import get_plex_metadata, get_part, get_embedded_subtitle_streams
from support.plex_media import get_plex_metadata, get_part, get_embedded_subtitle_streams, is_stream_forced, \
update_stream_info
from support.scanning import scan_videos
from support.scheduler import scheduler
from support.storage import get_subtitle_storage
@@ -118,6 +120,8 @@ def ItemDetailsMenu(rating_key, title=None, base_title=None, item_title=None, ra
if not os.path.exists(part.file):
continue
update_stream_info(part)
part_id = str(part.id)
part_index += 1
@@ -670,29 +674,28 @@ def ListEmbeddedSubsForItemMenu(**kwargs):
stream = stream_data["stream"]
is_forced = stream_data["is_forced"]
if language:
oc.add(DirectoryObject(
key=Callback(TriggerExtractEmbeddedSubForItemMenu, randomize=timestamp(),
stream_index=str(stream.index), language=language, with_mods=True, **kwargs),
title=_(u"Extract stream %(stream_index)s, %(language)s%(unknown_state)s%(forced_state)s"
u"%(stream_title)s with default mods",
stream_index=stream.index,
language=display_language(language),
unknown_state=_(" (unknown)") if is_unknown else "",
forced_state=_(" (forced)") if is_forced else "",
stream_title=" (\"%s\")" % stream.title if stream.title else ""),
))
oc.add(DirectoryObject(
key=Callback(TriggerExtractEmbeddedSubForItemMenu, randomize=timestamp(),
stream_index=str(stream.index), language=language, **kwargs),
title=_(u"Extract stream %(stream_index)s, %(language)s%(unknown_state)s%(forced_state)s"
u"%(stream_title)s",
stream_index=stream.index,
language=display_language(language),
unknown_state=_(" (unknown)") if is_unknown else "",
forced_state=_(" (forced)") if is_forced else "",
stream_title=" (\"%s\")" % stream.title if stream.title else ""),
))
oc.add(DirectoryObject(
key=Callback(TriggerExtractEmbeddedSubForItemMenu, randomize=timestamp(),
stream_index=str(stream.index), language=language, with_mods=True, **kwargs),
title=_(u"Extract stream %(stream_index)s, %(language)s%(unknown_state)s%(forced_state)s"
u"%(stream_title)s with default mods",
stream_index=stream.index,
language=display_language(language),
unknown_state=_(" (unknown)") if is_unknown else "",
forced_state=_(" (forced)") if is_forced else "",
stream_title=" (\"%s\")" % stream.title if stream.title else ""),
))
oc.add(DirectoryObject(
key=Callback(TriggerExtractEmbeddedSubForItemMenu, randomize=timestamp(),
stream_index=str(stream.index), language=language, **kwargs),
title=_(u"Extract stream %(stream_index)s, %(language)s%(unknown_state)s%(forced_state)s"
u"%(stream_title)s",
stream_index=stream.index,
language=display_language(language),
unknown_state=_(" (unknown)") if is_unknown else "",
forced_state=_(" (forced)") if is_forced else "",
stream_title=" (\"%s\")" % stream.title if stream.title else ""),
))
return oc
+4 -54
View File
@@ -12,19 +12,16 @@ from requests import HTTPError
from item_details import ItemDetailsMenu
from refresh_item import RefreshItem
from menu_helpers import add_incl_excl_options, dig_tree, set_refresh_menu_state, \
default_thumb, debounce, ObjectContainer, SubFolderObjectContainer, route, \
extract_embedded_sub
default_thumb, debounce, ObjectContainer, SubFolderObjectContainer, route
from main import fatality, InclExclMenu
from advanced import DispatchRestart
from subzero.constants import ART, PREFIX, DEPENDENCY_MODULE_NAMES
from support.plex_media import get_all_parts, get_embedded_subtitle_streams
from support.extract import season_extract_embedded
from support.scheduler import scheduler
from support.config import config
from support.helpers import timestamp, df, display_language
from support.ignore import get_decision_list
from support.items import get_all_items, get_items_info, get_item_kind_from_rating_key, get_item, MI_KEY, \
get_item_title, get_item_thumb
from support.storage import get_subtitle_storage
from support.items import get_all_items, get_items_info, get_item_kind_from_rating_key, get_item, get_item_title
from support.i18n import _
# init GUI
@@ -174,53 +171,6 @@ def SeasonExtractEmbedded(**kwargs):
return MetadataMenu(randomize=timestamp(), title=item_title, **kwargs)
def multi_extract_embedded(stream_list, refresh=False, with_mods=False, single_thread=True, extract_mode="a",
history_storage=None):
def execute():
for video_part_map, plexapi_part, stream_index, language, set_current in stream_list:
plexapi_item = video_part_map.keys()[0].plexapi_metadata["item"]
extract_embedded_sub(rating_key=plexapi_item.rating_key, part_id=plexapi_part.id,
plex_item=plexapi_item, part=plexapi_part, scanned_videos=video_part_map,
stream_index=stream_index, set_current=set_current,
language=language, with_mods=with_mods, refresh=refresh, extract_mode=extract_mode,
history_storage=history_storage)
if single_thread:
with Thread.Lock(key="extract_embedded"):
execute()
else:
execute()
def season_extract_embedded(rating_key, requested_language, with_mods=False, force=False):
# get stored subtitle info for item id
subtitle_storage = get_subtitle_storage()
try:
for data in get_all_items(key="children", value=rating_key, base="library/metadata"):
item = get_item(data[MI_KEY])
if item:
stored_subs = subtitle_storage.load_or_new(item)
for part in get_all_parts(item):
embedded_subs = stored_subs.get_by_provider(part.id, requested_language, "embedded")
current = stored_subs.get_any(part.id, requested_language)
if not embedded_subs or force:
stream_data = get_embedded_subtitle_streams(part, requested_language=requested_language)
if stream_data:
stream = stream_data[0]["stream"]
set_current = not current or force
refresh = not current
extract_embedded_sub(rating_key=item.rating_key, part_id=part.id,
stream_index=str(stream.index), set_current=set_current,
refresh=refresh, language=requested_language, with_mods=with_mods,
extract_mode="m")
finally:
subtitle_storage.destroy()
@route(PREFIX + '/ignore_list')
def IgnoreListMenu():
ref_list = get_decision_list()
@@ -368,7 +318,7 @@ def ValidatePrefs():
"subtitle_destination_folder", "include", "include_exclude_paths", "include_exclude_sz_files",
"new_style_cache", "dbm_supported", "lang_list", "providers", "normal_subs", "forced_only", "forced_also",
"plex_transcoder", "refiner_settings", "unrar", "adv_cfg_path", "use_custom_dns",
"has_anticaptcha", "anticaptcha_cls"]:
"has_anticaptcha", "anticaptcha_cls", "mediainfo_bin"]:
value = getattr(config, attr)
if isinstance(value, dict):
+3 -99
View File
@@ -1,29 +1,16 @@
# coding=utf-8
import traceback
import types
import datetime
import subprocess
import os
import operator
from func import enable_channel_wrapper, route_wrapper, register_route_function
from subzero.lib.io import get_viable_encoding
from subzero.language import Language
from func import enable_channel_wrapper, route_wrapper
from support.i18n import is_localized_string, _
from support.items import get_kind, get_item_thumb, get_item, get_item_kind_from_item, refresh_item
from support.helpers import get_video_display_title, pad_title, display_language, quote_args, is_stream_forced, \
get_title_for_video_metadata, mswindows
from support.history import get_history
from support.items import get_item_thumb
from support.helpers import get_video_display_title, pad_title
from support.ignore import get_decision_list
from support.lib import get_intent
from support.config import config
from subzero.constants import ICON_SUB, ICON
from support.plex_media import get_part, get_plex_metadata
from support.scheduler import scheduler
from support.scanning import scan_videos
from support.storage import save_subtitles
from subliminal_patch.subtitle import ModifiedSubtitle
default_thumb = R(ICON_SUB)
main_icon = ICON if not config.is_development else "icon-dev.jpg"
@@ -156,89 +143,6 @@ def debounce(func):
return func
def extract_embedded_sub(**kwargs):
rating_key = kwargs["rating_key"]
part_id = kwargs.pop("part_id")
stream_index = kwargs.pop("stream_index")
with_mods = kwargs.pop("with_mods", False)
language = Language.fromietf(kwargs.pop("language"))
refresh = kwargs.pop("refresh", True)
set_current = kwargs.pop("set_current", True)
plex_item = kwargs.pop("plex_item", get_item(rating_key))
item_type = get_item_kind_from_item(plex_item)
part = kwargs.pop("part", get_part(plex_item, part_id))
scanned_videos = kwargs.pop("scanned_videos", None)
extract_mode = kwargs.pop("extract_mode", "a")
any_successful = False
if part:
if not scanned_videos:
metadata = get_plex_metadata(rating_key, part_id, item_type, plex_item=plex_item)
scanned_videos = scan_videos([metadata], ignore_all=True, skip_hashing=True)
for stream in part.streams:
# subtitle stream
if str(stream.index) == stream_index:
is_forced = is_stream_forced(stream)
bn = os.path.basename(part.file)
set_refresh_menu_state(_(u"Extracting subtitle %(stream_index)s of %(filename)s",
stream_index=stream_index,
filename=bn))
Log.Info(u"Extracting stream %s (%s) of %s", stream_index, str(language), bn)
out_codec = stream.codec if stream.codec != "mov_text" else "srt"
args = [
config.plex_transcoder, "-i", part.file, "-map", "0:%s" % stream_index, "-f", out_codec, "-"
]
cmdline = quote_args(args)
Log.Debug(u"Calling: %s", cmdline)
if mswindows:
Log.Debug("MSWindows: Fixing encoding")
cmdline = cmdline.encode("mbcs")
output = None
try:
output = subprocess.check_output(cmdline, stderr=subprocess.PIPE, shell=True)
except:
Log.Error("Extraction failed: %s", traceback.format_exc())
if output:
subtitle = ModifiedSubtitle(language, mods=config.default_mods if with_mods else None)
subtitle.content = output
subtitle.provider_name = "embedded"
subtitle.id = "stream_%s" % stream_index
subtitle.score = 0
subtitle.set_encoding("utf-8")
# fixme: speedup video; only video.name is needed
video = scanned_videos.keys()[0]
save_successful = save_subtitles(scanned_videos, {video: [subtitle]}, mode="m",
set_current=set_current)
set_refresh_menu_state(None)
if save_successful and refresh:
refresh_item(rating_key)
# add item to history
item_title = get_title_for_video_metadata(video.plexapi_metadata,
add_section_title=False, add_episode_title=True)
history = get_history()
history.add(item_title, video.id, section_title=video.plexapi_metadata["section"],
thumb=video.plexapi_metadata["super_thumb"],
subtitle=subtitle, mode=extract_mode)
history.destroy()
any_successful = True
return any_successful
class SZObjectContainer(ObjectContainer):
def __init__(self, *args, **kwargs):
skip_pin_lock = kwargs.pop("skip_pin_lock", False)
+8 -4
View File
@@ -19,6 +19,10 @@ sys.modules["support.i18n"] = i18n
helpers._ = i18n._
import history
sys.modules["support.history"] = history
import plex_media
sys.modules["support.plex_media"] = plex_media
@@ -49,6 +53,10 @@ import missing_subtitles
sys.modules["support.missing_subtitles"] = missing_subtitles
import extract
sys.modules["support.extract"] = extract
import tasks
sys.modules["support.tasks"] = tasks
@@ -57,10 +65,6 @@ import ignore
sys.modules["support.ignore"] = ignore
import history
sys.modules["support.history"] = history
import data
sys.modules["support.data"] = data
+82 -21
View File
@@ -1,5 +1,6 @@
# coding=utf-8
import copy
import json
import os
import re
import inspect
@@ -7,12 +8,17 @@ import sys
import rarfile
import jstyleson
import datetime
import stat
import traceback
import socket
import requests
import subliminal
import subliminal_patch
import subzero.constants
import lib
from subliminal.exceptions import ServiceUnavailable, DownloadLimitExceeded, AuthenticationError
from subliminal.exceptions import ServiceUnavailable, DownloadLimitExceeded, AuthenticationError, \
DownloadLimitPerDayExceeded
from subliminal_patch.core import is_windows_special_path
from whichdb import whichdb
@@ -21,6 +27,7 @@ from subzero.language import Language
from subliminal.cli import MutexLock
from subzero.lib.io import FileIO, get_viable_encoding
from subzero.lib.dict import Dicked
from subzero.lib.which import find_executable
from subzero.util import get_root_path
from subzero.constants import PLUGIN_NAME, PLUGIN_IDENTIFIER, MOVIE, SHOW, MEDIA_TYPE_TO_STRING
from subzero.prefs import get_user_prefs, update_user_prefs
@@ -57,14 +64,22 @@ def int_or_default(s, default):
return default
VALID_THROTTLE_EXCEPTIONS = (TooManyRequests, DownloadLimitExceeded, ServiceUnavailable, APIThrottled)
VALID_THROTTLE_EXCEPTIONS = (TooManyRequests, DownloadLimitExceeded, DownloadLimitPerDayExceeded,
ServiceUnavailable, APIThrottled, requests.Timeout, requests.ReadTimeout, socket.timeout)
def_timeout = (datetime.timedelta(minutes=20), "20 minutes")
PROVIDER_THROTTLE_MAP = {
"default": {
TooManyRequests: (datetime.timedelta(hours=1), "1 hour"),
DownloadLimitExceeded: (datetime.timedelta(hours=3), "3 hours"),
DownloadLimitPerDayExceeded: (datetime.timedelta(hours=4), "4 hours"),
ServiceUnavailable: (datetime.timedelta(minutes=20), "20 minutes"),
APIThrottled: (datetime.timedelta(minutes=10), "10 minutes"),
AuthenticationError: (datetime.timedelta(hours=2), "2 hours"),
requests.Timeout: def_timeout,
socket.timeout: def_timeout,
requests.ReadTimeout: def_timeout,
},
"opensubtitles": {
TooManyRequests: (datetime.timedelta(hours=3), "3 hours"),
@@ -74,6 +89,7 @@ PROVIDER_THROTTLE_MAP = {
"addic7ed": {
DownloadLimitExceeded: (datetime.timedelta(hours=3), "3 hours"),
TooManyRequests: (datetime.timedelta(minutes=5), "5 minutes"),
AuthenticationError: (datetime.timedelta(hours=24), "24 hours"),
}
}
@@ -143,14 +159,16 @@ class Config(object):
refiner_settings = None
exact_filenames = False
only_one = False
any_language_is_enough = False
embedded_auto_extract = False
ietf_as_alpha3 = False
unrar = None
adv_cfg_path = None
use_custom_dns = False
use_custom_dns = None
anticaptcha_token = None
anticaptcha_cls = None
has_anticaptcha = False
mediainfo_bin = None
store_recently_played_amount = 40
@@ -233,9 +251,12 @@ class Config(object):
self.no_refresh = os.environ.get("SZ_NO_REFRESH", False)
self.plex_transcoder = self.get_plex_transcoder()
self.only_one = cast_bool(Prefs['subtitles.only_one'])
self.any_language_is_enough = Prefs['subtitles.any_language_is_enough']
self.embedded_auto_extract = cast_bool(Prefs["subtitles.embedded.autoextract"])
self.ietf_as_alpha3 = cast_bool(Prefs["subtitles.language.ietf_normalize"])
self.use_custom_dns = cast_bool(Prefs['use_custom_dns'])
self.use_custom_dns = self.parse_custom_dns()
if not self.advanced.dont_use_mediainfo_mp4:
self.mediainfo_bin = self.advanced.mediainfo_bin or find_executable("mediainfo")
self.initialized = True
def migrate_prefs(self):
@@ -320,6 +341,19 @@ class Config(object):
for exe in try_executables:
rarfile.UNRAR_TOOL = exe
rarfile.ORIG_UNRAR_TOOL = exe
if os.path.isfile(exe) and not os.access(exe, os.X_OK):
st = os.stat(exe)
try:
Log.Debug("setting generic executable permissions for %s", exe)
# fixme: too broad?
os.chmod(exe, st.st_mode | stat.S_IXUSR | stat.S_IXGRP | stat.S_IXOTH)
except:
Log.Debug("failed setting generic executable permissions for %s: %s", exe, traceback.format_exc())
try:
Log.Debug("setting executable permissions for %s", exe)
os.chmod(exe, st.st_mode | stat.S_IEXEC)
except:
Log.Debug("failed setting executable permissions for %s: %s", exe, traceback.format_exc())
try:
rarfile.custom_check([rarfile.UNRAR_TOOL], True)
except:
@@ -639,12 +673,18 @@ class Config(object):
if not agent.primary:
continue
for t in list(agent.media_types):
if t.media_type in (MOVIE, SHOW):
related_agents = Plex.primary_agent(agent.identifier, t.media_type)
media_types = [t.media_type for t in list(agent.media_types)]
# the new movie agent doesn't populate its media types, workaround
if not media_types and agent.identifier == "tv.plex.agents.movie":
media_types = [MOVIE]
for media_type in media_types:
if media_type in (MOVIE, SHOW):
related_agents = Plex.primary_agent(agent.identifier, media_type)
for a in related_agents:
if a.identifier == PLUGIN_IDENTIFIER and a.enabled:
enabled_for_primary_agents[MEDIA_TYPE_TO_STRING[t.media_type]].append(agent.identifier)
enabled_for_primary_agents[MEDIA_TYPE_TO_STRING[media_type]].append(agent.identifier)
# find the libraries that use them
for library in self.sections:
@@ -758,6 +798,7 @@ class Config(object):
return {'opensubtitles': cast_bool(Prefs['provider.opensubtitles.enabled']),
# 'thesubdb': Prefs['provider.thesubdb.enabled'],
'podnapisi': cast_bool(Prefs['provider.podnapisi.enabled']),
'napisy24': cast_bool(Prefs['provider.napisy24.enabled']),
'titlovi': cast_bool(Prefs['provider.titlovi.enabled']),
'addic7ed': cast_bool(Prefs['provider.addic7ed.enabled']) and self.has_anticaptcha,
'tvsubtitles': cast_bool(Prefs['provider.tvsubtitles.enabled']),
@@ -770,7 +811,9 @@ class Config(object):
'argenteam': cast_bool(Prefs['provider.argenteam.enabled']),
'subscenter': False,
'assrt': cast_bool(Prefs['provider.assrt.enabled']),
}
'bsplayer': cast_bool(Prefs['provider.bsplayer.enabled']),
'screwzira': cast_bool(Prefs['provider.screwzira.enabled']),
}
@property
def providers_enabled(self):
@@ -798,6 +841,9 @@ class Config(object):
providers["argenteam"] = False
providers["assrt"] = False
providers["subscene"] = False
providers["napisy24"] = False
providers["bsplayer"] = False
providers["screwzira"] = False
providers_forced_off = dict(providers)
if not self.unrar and providers["legendastv"]:
@@ -838,14 +884,12 @@ class Config(object):
providers = property(get_providers)
def get_provider_settings(self):
os_use_https = self.advanced.providers.opensubtitles.use_https \
if self.advanced.providers.opensubtitles.use_https is not None else True
os_skip_wrong_fps = self.advanced.providers.opensubtitles.skip_wrong_fps \
if self.advanced.providers.opensubtitles.skip_wrong_fps is not None else True
os_use_https = self.advanced.providers.opensubtitles.get("use_https", True)
os_skip_wrong_fps = self.advanced.providers.opensubtitles.get("skip_wrong_fps", True)
provider_settings = {'addic7ed': {'username': Prefs['provider.addic7ed.username'],
'password': Prefs['provider.addic7ed.password'],
'is_vip': cast_bool(Prefs['provider.addic7ed.is_vip']),
},
'opensubtitles': {'username': Prefs['provider.opensubtitles.username'],
'password': Prefs['provider.opensubtitles.password'],
@@ -861,8 +905,18 @@ class Config(object):
'only_foreign': self.forced_only,
'also_foreign': self.forced_also,
},
'titlovi': {
'username': Prefs['provider.titlovi.username'],
'password': Prefs['provider.titlovi.password'],
},
'napisy24': {
'username': Prefs['provider.napisy24.username'],
'password': Prefs['provider.napisy24.password'],
},
'subscene': {
'only_foreign': self.forced_only,
'username': Prefs['provider.subscene.username'],
'password': Prefs['provider.subscene.password'],
},
'legendastv': {'username': Prefs['provider.legendastv.username'],
'password': Prefs['provider.legendastv.password'],
@@ -891,10 +945,10 @@ class Config(object):
throttle_data = PROVIDER_THROTTLE_MAP.get(name, PROVIDER_THROTTLE_MAP["default"]).get(cls, None) or \
PROVIDER_THROTTLE_MAP["default"].get(cls, None)
if not throttle_data:
return
throttle_delta, throttle_description = throttle_data
if throttle_data:
throttle_delta, throttle_description = throttle_data
else:
throttle_delta, throttle_description = datetime.timedelta(minutes=10), "10 minutes"
if "provider_throttle" not in Dict:
Dict["provider_throttle"] = {}
@@ -1078,6 +1132,16 @@ class Config(object):
def text_based_formats(self):
return self.advanced.text_subtitle_formats or TEXT_SUBTITLE_EXTS
def parse_custom_dns(self):
custom_dns = Prefs['use_custom_dns2'].strip()
os.environ["dns_resolvers"] = ""
if custom_dns and custom_dns != "system":
ips = filter(lambda x: x, [d.strip() for d in custom_dns.split(",")])
if ips:
os.environ["dns_resolvers"] = json.dumps(ips)
return os.environ["dns_resolvers"]
def init_subliminal_patches(self):
# configure custom subtitle destination folders for scanning pre-existing subs
Log.Debug("Patching subliminal ...")
@@ -1088,9 +1152,6 @@ class Config(object):
subliminal_patch.core.DOWNLOAD_TRIES = int(Prefs['subtitles.try_downloads'])
subliminal.score.episode_scores["addic7ed_boost"] = int(Prefs['provider.addic7ed.boost_by2'])
if self.use_custom_dns:
subliminal_patch.http.set_custom_resolver()
config = Config()
config.initialize()
+25 -8
View File
@@ -33,19 +33,35 @@ def get_missing_languages(video, part):
alpha3_map = {}
if config.ietf_as_alpha3:
for language in languages:
if language.country:
if language and language.country:
alpha3_map[language.alpha3] = language.country
language.country = None
have_languages = video.subtitle_languages.copy()
if config.ietf_as_alpha3:
for language in have_languages:
if language.country:
if language and language.country:
alpha3_map[language.alpha3] = language.country
language.country = None
missing_languages = (languages - have_languages)
if config.any_language_is_enough != "Always search for all configured languages":
not_in_forced = "foreign" in config.any_language_is_enough
if "External or embedded subtitle" in config.any_language_is_enough:
langs = video.subtitle_languages if not not_in_forced else \
filter(lambda l: not l.forced, video.subtitle_languages)
if langs:
Log.Debug("We have at least one subtitle for any configured language.")
return set()
elif "External subtitle" in config.any_language_is_enough:
langs = video.external_subtitle_languages if not not_in_forced else \
filter(lambda l: not l.forced, video.external_subtitle_languages)
if langs:
Log.Debug("We have at least one external subtitle for any configured language.")
return set()
# all languages are found if we either really have subs for all languages or we only want to have exactly one language
# and we've only found one (the case for a selected language, Prefs['subtitles.only_one'] (one found sub matches any language))
found_one_which_is_enough = len(video.subtitle_languages) >= 1 and Prefs['subtitles.only_one']
@@ -54,7 +70,7 @@ def get_missing_languages(video, part):
Log.Debug('Only one language was requested, and we\'ve got a subtitle for %s', video)
else:
Log.Debug('All languages %r exist for %s', languages, video)
return False
return set()
# re-add country codes to the missing languages, in case we've removed them above
if config.ietf_as_alpha3:
@@ -90,21 +106,22 @@ def language_hook(provider):
def download_best_subtitles(video_part_map, min_score=0, throttle_time=None, providers=None):
hearing_impaired = Prefs['subtitles.search.hearingImpaired']
languages = set([Language.rebuild(l) for l in config.lang_list])
missing_languages = []
if not languages:
return
use_videos = []
missing_languages = set()
for video, part in video_part_map.iteritems():
if not video.ignore_all:
missing_languages = get_missing_languages(video, part)
p_missing_languages = get_missing_languages(video, part)
else:
missing_languages = languages
p_missing_languages = languages
if missing_languages:
Log.Info(u"%s has missing languages: %s", os.path.basename(video.name), missing_languages)
if p_missing_languages:
Log.Info(u"%s has missing languages: %s", os.path.basename(video.name), p_missing_languages)
refine_video(video, refiner_settings=config.refiner_settings)
use_videos.append(video)
missing_languages.update(p_missing_languages)
# prepare blacklist
blacklist = get_blacklist_from_part_map(video_part_map, languages)
+208
View File
@@ -0,0 +1,208 @@
# coding=utf-8
import os
import subprocess
import traceback
from support.helpers import quote_args, mswindows, get_title_for_video_metadata, cast_bool, \
audio_streams_match_languages
from support.i18n import _
from support.items import get_item_kind_from_item, refresh_item, get_all_items, get_item, MI_KEY
from support.storage import get_subtitle_storage, save_subtitles
from support.config import config
from support.history import get_history
from support.plex_media import get_all_parts, get_embedded_subtitle_streams, get_part, get_plex_metadata, \
update_stream_info, is_stream_forced
from support.scanning import scan_videos
from subzero.language import Language
from subliminal_patch.subtitle import ModifiedSubtitle
def agent_extract_embedded(video_part_map, set_as_existing=False):
try:
subtitle_storage = get_subtitle_storage()
to_extract = []
item_count = 0
threads = []
for scanned_video, part_info in video_part_map.iteritems():
plexapi_item = scanned_video.plexapi_metadata["item"]
stored_subs = subtitle_storage.load_or_new(plexapi_item)
valid_langs_in_media = \
audio_streams_match_languages(scanned_video, config.get_lang_list(ordered=True))
if not config.lang_list.difference(valid_langs_in_media):
Log.Debug("Skipping embedded subtitle extraction for %s, audio streams are in correct language(s)",
plexapi_item.rating_key)
continue
for plexapi_part in get_all_parts(plexapi_item):
item_count = item_count + 1
used_one_unknown_stream = False
used_one_known_stream = False
for requested_language in config.lang_list:
skip_unknown = used_one_unknown_stream or used_one_known_stream
embedded_subs = stored_subs.get_by_provider(plexapi_part.id, requested_language, "embedded")
current = stored_subs.get_any(plexapi_part.id, requested_language) or \
requested_language in scanned_video.external_subtitle_languages
if not embedded_subs:
stream_data = get_embedded_subtitle_streams(plexapi_part, requested_language=requested_language,
skip_unknown=skip_unknown)
if stream_data and stream_data[0]["language"]:
stream = stream_data[0]["stream"]
if stream_data[0]["is_unknown"]:
used_one_unknown_stream = True
else:
used_one_known_stream = True
to_extract.append(({scanned_video: part_info}, plexapi_part, str(stream.index),
str(requested_language), not current))
if not cast_bool(Prefs["subtitles.search_after_autoextract"]) or set_as_existing:
scanned_video.subtitle_languages.update({requested_language})
else:
Log.Debug("Skipping embedded subtitle extraction for %s, already got %r from %s",
plexapi_item.rating_key, requested_language, embedded_subs[0].id)
if to_extract:
Log.Info("Triggering extraction of %d embedded subtitles of %d items", len(to_extract), item_count)
threads.append(Thread.Create(multi_extract_embedded, stream_list=to_extract, refresh=True, with_mods=True,
single_thread=not config.advanced.auto_extract_multithread))
return threads
except:
Log.Error("Something went wrong when auto-extracting subtitles, continuing: %s", traceback.format_exc())
def multi_extract_embedded(stream_list, refresh=False, with_mods=False, single_thread=True, extract_mode="a",
history_storage=None):
def execute():
for video_part_map, plexapi_part, stream_index, language, set_current in stream_list:
plexapi_item = video_part_map.keys()[0].plexapi_metadata["item"]
extract_embedded_sub(rating_key=plexapi_item.rating_key, part_id=plexapi_part.id,
plex_item=plexapi_item, part=plexapi_part, scanned_videos=video_part_map,
stream_index=stream_index, set_current=set_current,
language=language, with_mods=with_mods, refresh=refresh, extract_mode=extract_mode,
history_storage=history_storage)
if single_thread:
with Thread.Lock(key="extract_embedded"):
execute()
else:
execute()
def season_extract_embedded(rating_key, requested_language, with_mods=False, force=False):
# get stored subtitle info for item id
subtitle_storage = get_subtitle_storage()
try:
for data in get_all_items(key="children", value=rating_key, base="library/metadata"):
item = get_item(data[MI_KEY])
if item:
stored_subs = subtitle_storage.load_or_new(item)
for part in get_all_parts(item):
embedded_subs = stored_subs.get_by_provider(part.id, requested_language, "embedded")
current = stored_subs.get_any(part.id, requested_language)
if not embedded_subs or force:
stream_data = get_embedded_subtitle_streams(part, requested_language=requested_language)
if stream_data:
stream = stream_data[0]["stream"]
set_current = not current or force
refresh = not current
extract_embedded_sub(rating_key=item.rating_key, part_id=part.id,
stream_index=str(stream.index), set_current=set_current,
refresh=refresh, language=requested_language, with_mods=with_mods,
extract_mode="m")
finally:
subtitle_storage.destroy()
def extract_embedded_sub(**kwargs):
rating_key = kwargs["rating_key"]
part_id = kwargs.pop("part_id")
stream_index = kwargs.pop("stream_index")
with_mods = kwargs.pop("with_mods", False)
language = Language.fromietf(kwargs.pop("language"))
refresh = kwargs.pop("refresh", True)
set_current = kwargs.pop("set_current", True)
plex_item = kwargs.pop("plex_item", get_item(rating_key))
item_type = get_item_kind_from_item(plex_item)
part = kwargs.pop("part", get_part(plex_item, part_id))
scanned_videos = kwargs.pop("scanned_videos", None)
extract_mode = kwargs.pop("extract_mode", "a")
any_successful = False
from interface.menu_helpers import set_refresh_menu_state
if part:
if not scanned_videos:
metadata = get_plex_metadata(rating_key, part_id, item_type, plex_item=plex_item)
scanned_videos = scan_videos([metadata], ignore_all=True, skip_hashing=True)
update_stream_info(part)
for stream in part.streams:
# subtitle stream
if str(stream.index) == stream_index:
is_forced = is_stream_forced(stream)
bn = os.path.basename(part.file)
set_refresh_menu_state(_(u"Extracting subtitle %(stream_index)s of %(filename)s",
stream_index=stream_index,
filename=bn))
Log.Info(u"Extracting stream %s (%s) of %s", stream_index, str(language), bn)
out_codec = stream.codec if stream.codec != "mov_text" else "srt"
args = [
config.plex_transcoder, "-i", part.file, "-map", "0:%s" % stream_index, "-f", out_codec, "-"
]
cmdline = quote_args(args)
Log.Debug(u"Calling: %s", cmdline)
if mswindows:
Log.Debug("MSWindows: Fixing encoding")
cmdline = cmdline.encode("mbcs")
output = None
try:
output = subprocess.check_output(cmdline, stderr=subprocess.PIPE, shell=True)
except:
Log.Error("Extraction failed: %s", traceback.format_exc())
if output:
subtitle = ModifiedSubtitle(language, mods=config.default_mods if with_mods else None)
subtitle.content = output
subtitle.provider_name = "embedded"
subtitle.id = "stream_%s" % stream_index
subtitle.score = 0
subtitle.set_encoding("utf-8")
# fixme: speedup video; only video.name is needed
video = scanned_videos.keys()[0]
save_successful = save_subtitles(scanned_videos, {video: [subtitle]}, mode="m",
set_current=set_current)
set_refresh_menu_state(None)
if save_successful and refresh:
refresh_item(rating_key)
# add item to history
item_title = get_title_for_video_metadata(video.plexapi_metadata,
add_section_title=False, add_episode_title=True)
history = get_history()
history.add(item_title, video.id, section_title=video.plexapi_metadata["section"],
thumb=video.plexapi_metadata["super_thumb"],
subtitle=subtitle, mode=extract_mode)
history.destroy()
any_successful = True
return any_successful
+3 -10
View File
@@ -394,7 +394,7 @@ def get_language_from_stream(lang_code):
return Language.fromietf(lang)
elif lang:
try:
return language_from_stream(lang)
return language_from_stream(lang_code)
except LanguageError:
pass
@@ -437,17 +437,10 @@ def get_language(lang_short):
def display_language(l):
if not l:
return "Unknown"
return _(str(l.basename).lower()) + ((u" (%s)" % _("forced")) if l.forced else "")
def is_stream_forced(stream):
stream_title = getattr(stream, "title", "") or ""
forced = getattr(stream, "forced", False)
if not forced and stream_title and "forced" in stream_title.strip().lower():
forced = True
return forced
class PartUnknownException(Exception):
pass
+2 -1
View File
@@ -7,6 +7,7 @@ import helpers
import subtitlehelpers
from config import config as sz_config
from subzero.language import ENDSWITH_LANGUAGECODE_RE
SECONDARY_TAGS = ['forced', 'normal', 'default', 'embedded', 'embedded-forced', 'custom', 'hi', 'cc', 'sdh']
@@ -125,7 +126,7 @@ def find_subtitles(part, ignore_parts_cleanup=None):
root = split_tag[0]
# get associated media file name without language
sub_fn = subtitlehelpers.ENDSWITH_LANGUAGECODE_RE.sub("", root)
sub_fn = ENDSWITH_LANGUAGECODE_RE.sub("", root)
# subtitle basename and basename without possible language tag not found in collected
# media files? kill.
+3 -2
View File
@@ -7,7 +7,8 @@ import os
from babelfish import LanguageReverseError
from support.config import config, TEXT_SUBTITLE_EXTS
from support.helpers import get_plex_item_display_title, cast_bool, get_language_from_stream, is_stream_forced
from support.helpers import get_plex_item_display_title, cast_bool, get_language_from_stream
from support.plex_media import is_stream_forced, update_stream_info
from support.items import get_item
from support.lib import Plex
from support.storage import get_subtitle_storage
@@ -35,7 +36,7 @@ def item_discover_missing_subs(rating_key, kind="show", added_at=None, section_t
for media in item.media:
existing_subs = {"internal": [], "external": [], "own_external": [], "count": 0}
for part in media.parts:
update_stream_info(part)
# did we already download an external subtitle before?
if subtitle_target_dir and stored_subs:
for language in languages_set:
+97 -27
View File
@@ -1,6 +1,7 @@
# coding=utf-8
import os
import subprocess
import helpers
from items import get_item
@@ -26,6 +27,9 @@ tvdb_guid_identifier = "com.plexapp.agents.thetvdb://"
def get_plexapi_stream_info(plex_item, part_id=None):
if not plex_item:
return
d = {"stream": {}}
data = d["stream"]
@@ -100,6 +104,9 @@ def media_to_videos(media, kind="series"):
plex_episode = get_item(ep.id)
stream_info = get_plexapi_stream_info(plex_episode)
if not stream_info:
continue
for item in media.seasons[season].episodes[episode].items:
for part in item.parts:
videos.append(
@@ -121,22 +128,24 @@ def media_to_videos(media, kind="series"):
)
else:
stream_info = get_plexapi_stream_info(plex_item)
imdb_id = None
if imdb_guid_identifier in media.guid:
imdb_id = media.guid[len(imdb_guid_identifier):].split("?")[0]
for item in media.items:
for part in item.parts:
videos.append(
get_metadata_dict(plex_item, part, dict(stream_info, **{"plex_part": part, "type": "movie",
"title": media.title, "id": media.id,
"super_thumb": plex_item.thumb,
"series_id": None, "year": year,
"season_id": None, "imdb_id": imdb_id,
"original_title": original_title,
"series_tvdb_id": None, "tvdb_id": None,
"section": plex_item.section.title})
)
)
if stream_info:
imdb_id = None
if imdb_guid_identifier in media.guid:
imdb_id = media.guid[len(imdb_guid_identifier):].split("?")[0]
for item in media.items:
for part in item.parts:
videos.append(
get_metadata_dict(plex_item, part, dict(stream_info, **{"plex_part": part, "type": "movie",
"title": media.title, "id": media.id,
"super_thumb": plex_item.thumb,
"series_id": None, "year": year,
"season_id": None, "imdb_id": imdb_id,
"original_title": original_title,
"series_tvdb_id": None, "tvdb_id": None,
"section": plex_item.section.title})
)
)
return videos
@@ -174,42 +183,99 @@ def get_all_parts(plex_item):
return parts
def update_stream_info(part):
try:
return update_stream_info_(part)
except:
Log.Exception("Getting Mediainfo failed for: %s", part.file)
def update_stream_info_(part):
if config.mediainfo_bin and part.container == "mp4":
cmdline = '%s --Inform="Text;-%%ID%%_%%Title%%" %s' % (config.mediainfo_bin, helpers.quote(part.file))
result = subprocess.check_output(cmdline, stderr=subprocess.PIPE, shell=True)
if result:
try:
stream_titles = {}
for pair in result[1:].split("-"):
sid, title = pair.split("_")
stream_titles[int(sid.strip())] = title.strip()
except:
pass
else:
filled = []
for stream in part.streams:
if stream.index is None:
Log.Debug("Found stream with no index: %r", stream)
index = stream.index+1 if stream.index is not None else 1
if index in stream_titles:
stream.title = stream_titles[index]
filled.append(index-1)
if filled:
Log.Debug("Filled missing MP4 stream title info for streams: %s", filled)
def is_stream_forced(stream):
stream_title = getattr(stream, "title", "") or ""
forced = getattr(stream, "forced", False)
if not forced and stream_title and "forced" in stream_title.strip().lower():
forced = True
return forced
def get_embedded_subtitle_streams(part, requested_language=None, skip_duplicate_unknown=True, skip_unknown=False):
streams = []
streams_unknown = []
all_streams = []
has_unknown = False
found_requested_language = False
update_stream_info(part)
for stream in part.streams:
# subtitle stream
if stream.stream_type == 3 and not stream.stream_key and stream.codec in TEXT_SUBTITLE_EXTS:
is_forced = helpers.is_stream_forced(stream)
is_forced = is_stream_forced(stream)
language = helpers.get_language_from_stream(stream.language_code)
if language:
language = Language.rebuild(language, forced=is_forced)
is_unknown = False
found_requested_language = requested_language and requested_language == language
stream_data = None
if not language and config.treat_und_as_first:
if not language:
# only consider first unknown subtitle stream
if has_unknown and skip_duplicate_unknown:
continue
if config.treat_und_as_first:
if has_unknown and skip_duplicate_unknown:
Log.Debug("skipping duplicate unknown")
continue
language = Language.rebuild(list(config.lang_list)[0], forced=is_forced)
language = Language.rebuild(list(config.lang_list)[0], forced=is_forced)
else:
language = None
is_unknown = True
has_unknown = True
streams_unknown.append({"stream": stream, "is_unknown": is_unknown, "language": language,
"is_forced": is_forced})
stream_data = {"stream": stream, "is_unknown": is_unknown, "language": language,
"is_forced": is_forced}
streams_unknown.append(stream_data)
if not requested_language or found_requested_language:
streams.append({"stream": stream, "is_unknown": is_unknown, "language": language,
"is_forced": is_forced})
stream_data = {"stream": stream, "is_unknown": is_unknown, "language": language,
"is_forced": is_forced}
streams.append(stream_data)
if found_requested_language:
break
if streams_unknown and not found_requested_language and not skip_unknown:
streams = streams_unknown
if stream_data:
all_streams.append(stream_data)
if requested_language:
if streams_unknown and not found_requested_language and not skip_unknown:
streams = streams_unknown
else:
streams = all_streams
return streams
@@ -245,6 +311,9 @@ def get_plex_metadata(rating_key, part_id, item_type, plex_item=None):
stream_info = get_plexapi_stream_info(plex_item, part_id)
if not stream_info:
return
# get normalized metadata
# fixme: duplicated logic of media_to_videos
if item_type == "episode":
@@ -366,3 +435,4 @@ class PMSMediaProxy(object):
m = m.children[0]
return parts
+11 -6
View File
@@ -4,7 +4,7 @@ import helpers
from babelfish.exceptions import LanguageError
from support.lib import Plex, get_intent
from support.plex_media import get_stream_fps
from support.plex_media import get_stream_fps, is_stream_forced, update_stream_info
from support.storage import get_subtitle_storage
from support.config import config, TEXT_SUBTITLE_EXTS
from support.subtitlehelpers import get_subtitles_from_metadata
@@ -29,7 +29,7 @@ def prepare_video(pms_video_info, ignore_all=False, hints=None, rating_key=None,
if ignore_all:
Log.Debug("Force refresh intended.")
Log.Debug("Detecting streams: %s, external_subtitles=%s, embedded_subtitles=%s" % (
Log.Debug("Detecting streams: %s, account_for_external_subtitles=%s, account_for_embedded_subtitles=%s" % (
plex_part.file, external_subtitles, embedded_subtitles))
known_embedded = []
@@ -46,23 +46,25 @@ def prepare_video(pms_video_info, ignore_all=False, hints=None, rating_key=None,
# fixme: skip the whole scanning process if known_embedded == wanted languages?
audio_languages = []
if plexpy_part:
update_stream_info(plexpy_part)
for stream in plexpy_part.streams:
if stream.stream_type == 2:
lang = None
try:
lang = language_from_stream(stream.language_code)
except LanguageError:
Log.Debug("Couldn't detect embedded audio stream language: %s", stream.language_code)
Log.Info("Couldn't detect embedded audio stream language: %s", stream.language_code)
# treat unknown language as lang1?
if not lang and config.treat_und_as_first:
lang = Language.rebuild(list(config.lang_list)[0])
Log.Info("Assuming language %s for audio stream: %s", lang, getattr(stream, "index", None))
audio_languages.append(lang)
# subtitle stream
elif stream.stream_type == 3 and embedded_subtitles:
is_forced = helpers.is_stream_forced(stream)
is_forced = is_stream_forced(stream)
if ((config.forced_only or config.forced_also) and is_forced) or not is_forced:
# embedded subtitle
@@ -73,11 +75,13 @@ def prepare_video(pms_video_info, ignore_all=False, hints=None, rating_key=None,
try:
lang = language_from_stream(stream.language_code)
except LanguageError:
Log.Debug("Couldn't detect embedded subtitle stream language: %s", stream.language_code)
Log.Info("Couldn't detect embedded subtitle stream language: %s", stream.language_code)
# treat unknown language as lang1?
if not lang and config.treat_und_as_first:
lang = Language.rebuild(list(config.lang_list)[0])
Log.Info("Assuming language %s for subtitle stream: %s", lang,
getattr(stream, "index", None))
if lang:
if is_forced:
@@ -127,7 +131,8 @@ def prepare_video(pms_video_info, ignore_all=False, hints=None, rating_key=None,
set_existing_languages(video, pms_video_info, external_subtitles=external_subtitles,
embedded_subtitles=embedded_subtitles, known_embedded=known_embedded,
stored_subs=stored_subs, languages=config.lang_list,
only_one=config.only_one, known_metadata_subs=known_metadata_subs)
only_one=config.only_one, known_metadata_subs=known_metadata_subs,
match_strictness=config.ext_match_strictness)
# add video fps info
video.fps = plex_part.fps
+2 -14
View File
@@ -5,6 +5,7 @@ import helpers
from config import config, SUBTITLE_EXTS, TEXT_SUBTITLE_EXTS
from bs4 import UnicodeDammit
from subzero.language import match_ietf_language
class SubtitleHelper(object):
@@ -85,19 +86,6 @@ class VobSubSubtitleHelper(SubtitleHelper):
#####################################################################################################################
IETF_MATCH = ".+\.([^-.]+)(?:-[A-Za-z]+)?$"
ENDSWITH_LANGUAGECODE_RE = re.compile("\.([^-.]{2,3})(?:-[A-Za-z]{2,})?$")
def match_ietf_language(s):
language_match = re.match(".+\.([^\.]+)$" if not helpers.cast_bool(Prefs["subtitles.language.ietf_display"])
else IETF_MATCH, s)
if language_match and len(language_match.groups()) == 1:
language = language_match.groups()[0]
return language
return s
class DefaultSubtitleHelper(SubtitleHelper):
@classmethod
def is_helper_for(cls, filename):
@@ -133,7 +121,7 @@ class DefaultSubtitleHelper(SubtitleHelper):
# Attempt to extract the language from the filename (e.g. Avatar (2009).eng)
# IETF support thanks to
# https://github.com/hpsbranco/LocalMedia.bundle/commit/4fad9aefedece78a1fa96401304351347f644369
lang_part = match_ietf_language(file)
lang_part = match_ietf_language(file, ietf=helpers.cast_bool(Prefs["subtitles.language.ietf_display"]))
if lang_part != file:
language = Locale.Language.Match(lang_part)
elif config.only_one:
+19 -4
View File
@@ -19,6 +19,7 @@ from support.config import config
from support.items import get_recent_items, get_item, is_wanted, get_item_title
from support.helpers import track_usage, get_title_for_video_metadata, cast_bool, PartUnknownException
from support.plex_media import get_plex_metadata
from support.extract import agent_extract_embedded
from support.scanning import scan_videos
from support.i18n import _
from download import download_best_subtitles, pre_download_hook, post_download_hook, language_hook
@@ -170,12 +171,15 @@ class SubtitleListingMixin(object):
else:
s.wrong_season_ep = True
orig_matches = matches.copy()
score, score_without_hash = compute_score(matches, s, video, hearing_impaired=use_hearing_impaired)
unsorted_subtitles.append(
(s, compute_score(matches, s, video, hearing_impaired=use_hearing_impaired), matches))
scored_subtitles = sorted(unsorted_subtitles, key=operator.itemgetter(1), reverse=True)
(s, score, score_without_hash, matches, orig_matches))
scored_subtitles = sorted(unsorted_subtitles, key=operator.itemgetter(1, 2), reverse=True)
subtitles = []
for subtitle, score, matches in scored_subtitles:
for subtitle, score, score_without_hash, matches, orig_matches in scored_subtitles:
# check score
if score < min_score and not subtitle.wrong_series:
Log.Info(u'%s: Score %d is below min_score (%d)', self.name, score, min_score)
@@ -449,6 +453,17 @@ class SearchAllRecentlyAddedMissing(Task):
Log.Debug(u"%s: Looking for missing subtitles: %s", self.name, get_item_title(plex_item))
scanned_parts = scan_videos([metadata], providers=providers)
# auto extract embedded
if config.embedded_auto_extract:
if config.plex_transcoder:
ts = agent_extract_embedded(scanned_parts, set_as_existing=True)
if ts:
Log.Debug("Waiting for %i extraction threads to finish" % len(ts))
for t in ts:
t.join()
else:
Log.Warn("Plex Transcoder not found, can't auto extract")
downloaded_subtitles = download_best_subtitles(scanned_parts, min_score=min_score,
providers=providers)
hit_providers = downloaded_subtitles is not None
@@ -655,7 +670,7 @@ class FindBetterSubtitles(DownloadSubtitleMixin, SubtitleListingMixin, Task):
min_score_series = int(Prefs["subtitles.search.minimumTVScore2"].strip())
min_score_movies = int(Prefs["subtitles.search.minimumMovieScore2"].strip())
min_score_extracted_series = config.advanced.find_better_as_extracted_tv_score or 352
min_score_extracted_movies = config.advanced.find_better_as_extracted_movie_score or 82
min_score_extracted_movies = config.advanced.find_better_as_extracted_movie_score or 112
overwrite_manually_modified = cast_bool(
Prefs["scheduler.tasks.FindBetterSubtitles.overwrite_manually_modified"])
overwrite_manually_selected = cast_bool(
+108 -6
View File
@@ -205,6 +205,19 @@
],
"default": "Never"
},
{
"id": "subtitles.any_language_is_enough",
"label": "Don't search for subtitles if a subtitle in any configured language exists as",
"type": "enum",
"values": [
"External or embedded subtitle",
"External or embedded subtitle (not foreign/forced)",
"External subtitle",
"External subtitle (not foreign/forced)",
"Always search for all configured languages"
],
"default": "Always search for all configured languages"
},
{
"id": "subtitles.language.ietf_display",
"label": "Display languages with country attribute as ISO 639-1 (e.g. pt-BR = pt)",
@@ -275,7 +288,7 @@
},
{
"id": "anticaptcha.service",
"label": "AntiCaptcha-Service (needs paid account; enables Addic7ed, titlovi)",
"label": "AntiCaptcha-Service (needs paid account; enables Addic7ed)",
"type": "enum",
"values": [
"none",
@@ -322,6 +335,26 @@
"type": "bool",
"default": "true"
},
{
"id": "provider.napisy24.enabled",
"label": "Provider: Enable Napisy24 (pl)",
"type": "bool",
"default": "false"
},
{
"id": "provider.napisy24.username",
"label": "Napisy24 Username",
"type": "text",
"default": ""
},
{
"id": "provider.napisy24.password",
"label": "Napisy24 Password",
"type": "text",
"option": "hidden",
"default": "",
"secure": "true"
},
{
"id": "provider.addic7ed.enabled",
"label": "Provider: Enable Addic7ed (needs AntiCaptcha)",
@@ -342,6 +375,12 @@
"default": "",
"secure": "true"
},
{
"id": "provider.addic7ed.is_vip",
"label": "Addic7ed VIP? (80 vs 40 downloads per day)",
"type": "bool",
"default": "false"
},
{
"id": "provider.addic7ed.boost_by2",
"label": "Addic7ed: boost score (if requirements met)",
@@ -376,10 +415,24 @@
},
{
"id": "provider.titlovi.enabled",
"label": "Provider: Enable Titlovi.com (might need AntiCaptcha)",
"label": "Provider: Enable Titlovi.com (User and Password required)",
"type": "bool",
"default": "true"
},
{
"id": "provider.titlovi.username",
"label": "Titlovi Username",
"type": "text",
"default": ""
},
{
"id": "provider.titlovi.password",
"label": "Titlovi Password",
"type": "text",
"option": "hidden",
"default": "",
"secure": "true"
},
{
"id": "provider.legendastv.enabled",
"label": "Provider: Enable Legendas TV (mostly pt-BR; UNRAR NEEDED)",
@@ -418,6 +471,20 @@
"type": "bool",
"default": "true"
},
{
"id": "provider.subscene.username",
"label": "SubScene Username",
"type": "text",
"default": ""
},
{
"id": "provider.subscene.password",
"label": "SubScene Password",
"type": "text",
"option": "hidden",
"default": "",
"secure": "true"
},
{
"id": "provider.supersubtitles.enabled",
"label": "Provider: Enable feliratok.info (Hungarian)",
@@ -448,6 +515,18 @@
"type": "text",
"default": ""
},
{
"id": "provider.bsplayer.enabled",
"label": "Provider: Enable BSPlayer Subtitles",
"type": "bool",
"default": "true"
},
{
"id": "provider.screwzira.enabled",
"label": "Provider: Enable ScrewZira (Hebrew)",
"type": "bool",
"default": "false"
},
{
"id": "providers.multithreading",
"label": "Search enabled providers simultaneously (multithreading)",
@@ -733,6 +812,29 @@
"type": "bool",
"default": "false"
},
{
"id": "scheduler.tasks.SubtitleStorageMaintenance.frequency",
"label": "Scheduler: Periodically run subtitle storage maintenance (SZ internal)",
"type": "enum",
"values": [
"never",
"every 6 hours",
"every 12 hours",
"every 24 hours",
"every 1 days",
"every 2 days",
"every 3 days",
"every 4 days",
"every 1 weeks",
"every 2 weeks",
"every 3 weeks",
"every 4 weeks",
"every 5 weeks",
"every 6 weeks",
"every 12 weeks"
],
"default": "every 1 weeks"
},
{
"id": "history_size",
"label": "History: amount of items to store historical data for",
@@ -847,10 +949,10 @@
"default": "15"
},
{
"id": "use_custom_dns",
"label": "Use Google DNS (for \"problematic\" countries)",
"type": "bool",
"default": "false"
"id": "use_custom_dns2",
"label": "Use custom DNS (IPs, comma-separated, set to 'system' for system DNS. Default: Google/CF)",
"type": "text",
"default": "1.1.1.1, 8.8.8.8"
},
{
"id": "proxy",
+3 -3
View File
@@ -13,7 +13,7 @@
<key>CFBundleSignature</key>
<string>????</string>
<key>CFBundleVersion</key>
<string>2.6.5.3017</string>
<string>2.6.5.3247</string>
<key>PlexFrameworkVersion</key>
<string>2</string>
<key>PlexPluginClass</key>
@@ -23,7 +23,7 @@
<key>PlexPluginConsoleLogging</key>
<string>0</string>
<key>PlexPluginDevMode</key>
<string>0</string>
<string>1</string>
<key>PlexPluginCodePolicy</key>
<!-- this allows channels to access some python methods which are otherwise blocked, as well as import external code libraries, and interact with the PMS HTTP API -->
<string>Elevated</string>
@@ -32,7 +32,7 @@
&lt;h1&gt;Sub-Zero for Plex&lt;/h1&gt;&lt;i&gt;Subtitles done right&lt;/i&gt;
Version 2.6.5.3017
Version 2.6.5.3247 DEV
Originally based on @bramwalet's awesome &lt;a href=&quot;https://github.com/bramwalet/Subliminal.bundle&quot;&gt;Subliminal.bundle&lt;/a&gt;
@@ -0,0 +1 @@
__path__ = __import__('pkgutil').extend_path(__path__, __name__)
@@ -0,0 +1,196 @@
from __future__ import absolute_import
import functools
from collections import namedtuple
from threading import RLock
_CacheInfo = namedtuple("CacheInfo", ["hits", "misses", "maxsize", "currsize"])
@functools.wraps(functools.update_wrapper)
def update_wrapper(
wrapper,
wrapped,
assigned=functools.WRAPPER_ASSIGNMENTS,
updated=functools.WRAPPER_UPDATES,
):
"""
Patch two bugs in functools.update_wrapper.
"""
# workaround for http://bugs.python.org/issue3445
assigned = tuple(attr for attr in assigned if hasattr(wrapped, attr))
wrapper = functools.update_wrapper(wrapper, wrapped, assigned, updated)
# workaround for https://bugs.python.org/issue17482
wrapper.__wrapped__ = wrapped
return wrapper
class _HashedSeq(list):
__slots__ = 'hashvalue'
def __init__(self, tup, hash=hash):
self[:] = tup
self.hashvalue = hash(tup)
def __hash__(self):
return self.hashvalue
def _make_key(
args,
kwds,
typed,
kwd_mark=(object(),),
fasttypes=set([int, str, frozenset, type(None)]),
sorted=sorted,
tuple=tuple,
type=type,
len=len,
):
'Make a cache key from optionally typed positional and keyword arguments'
key = args
if kwds:
sorted_items = sorted(kwds.items())
key += kwd_mark
for item in sorted_items:
key += item
if typed:
key += tuple(type(v) for v in args)
if kwds:
key += tuple(type(v) for k, v in sorted_items)
elif len(key) == 1 and type(key[0]) in fasttypes:
return key[0]
return _HashedSeq(key)
def lru_cache(maxsize=100, typed=False):
"""Least-recently-used cache decorator.
If *maxsize* is set to None, the LRU features are disabled and the cache
can grow without bound.
If *typed* is True, arguments of different types will be cached separately.
For example, f(3.0) and f(3) will be treated as distinct calls with
distinct results.
Arguments to the cached function must be hashable.
View the cache statistics named tuple (hits, misses, maxsize, currsize) with
f.cache_info(). Clear the cache and statistics with f.cache_clear().
Access the underlying function with f.__wrapped__.
See: http://en.wikipedia.org/wiki/Cache_algorithms#Least_Recently_Used
"""
# Users should only access the lru_cache through its public API:
# cache_info, cache_clear, and f.__wrapped__
# The internals of the lru_cache are encapsulated for thread safety and
# to allow the implementation to change (including a possible C version).
def decorating_function(user_function):
cache = dict()
stats = [0, 0] # make statistics updateable non-locally
HITS, MISSES = 0, 1 # names for the stats fields
make_key = _make_key
cache_get = cache.get # bound method to lookup key or return None
_len = len # localize the global len() function
lock = RLock() # because linkedlist updates aren't threadsafe
root = [] # root of the circular doubly linked list
root[:] = [root, root, None, None] # initialize by pointing to self
nonlocal_root = [root] # make updateable non-locally
PREV, NEXT, KEY, RESULT = 0, 1, 2, 3 # names for the link fields
if maxsize == 0:
def wrapper(*args, **kwds):
# no caching, just do a statistics update after a successful call
result = user_function(*args, **kwds)
stats[MISSES] += 1
return result
elif maxsize is None:
def wrapper(*args, **kwds):
# simple caching without ordering or size limit
key = make_key(args, kwds, typed)
result = cache_get(
key, root
) # root used here as a unique not-found sentinel
if result is not root:
stats[HITS] += 1
return result
result = user_function(*args, **kwds)
cache[key] = result
stats[MISSES] += 1
return result
else:
def wrapper(*args, **kwds):
# size limited caching that tracks accesses by recency
key = make_key(args, kwds, typed) if kwds or typed else args
with lock:
link = cache_get(key)
if link is not None:
# record recent use of the key by moving it
# to the front of the list
root, = nonlocal_root
link_prev, link_next, key, result = link
link_prev[NEXT] = link_next
link_next[PREV] = link_prev
last = root[PREV]
last[NEXT] = root[PREV] = link
link[PREV] = last
link[NEXT] = root
stats[HITS] += 1
return result
result = user_function(*args, **kwds)
with lock:
root, = nonlocal_root
if key in cache:
# getting here means that this same key was added to the
# cache while the lock was released. since the link
# update is already done, we need only return the
# computed result and update the count of misses.
pass
elif _len(cache) >= maxsize:
# use the old root to store the new key and result
oldroot = root
oldroot[KEY] = key
oldroot[RESULT] = result
# empty the oldest link and make it the new root
root = nonlocal_root[0] = oldroot[NEXT]
oldkey = root[KEY]
root[KEY] = root[RESULT] = None
# now update the cache dictionary for the new links
del cache[oldkey]
cache[key] = oldroot
else:
# put result in a new link at the front of the list
last = root[PREV]
link = [last, root, key, result]
last[NEXT] = root[PREV] = cache[key] = link
stats[MISSES] += 1
return result
def cache_info():
"""Report cache statistics"""
with lock:
return _CacheInfo(stats[HITS], stats[MISSES], maxsize, len(cache))
def cache_clear():
"""Clear the cache and cache statistics"""
with lock:
cache.clear()
root = nonlocal_root[0]
root[:] = [root, root, None, None]
stats[:] = [0, 0]
wrapper.__wrapped__ = user_function
wrapper.cache_info = cache_info
wrapper.cache_clear = cache_clear
return update_wrapper(wrapper, user_function)
return decorating_function
@@ -1,3 +1,3 @@
from .core import where
from .core import contents, where
__version__ = "2019.03.09"
__version__ = "2020.06.20"
+12 -2
View File
@@ -1,2 +1,12 @@
from certifi import where
print(where())
import argparse
from certifi import contents, where
parser = argparse.ArgumentParser()
parser.add_argument("-c", "--contents", action="store_true")
args = parser.parse_args()
if args.contents:
print(contents())
else:
print(where())
+209 -247
View File
@@ -58,38 +58,6 @@ AfvDbbnvRG15RjF+Cv6pgsH/76tuIMRQyV+dTZsXjAzlAcmgQWpzU/qlULRuJQ/7
TBj0/VLZjmmx6BEP3ojY+x1J96relc8geMJgEtslQIxq/H5COEBkEveegeGTLg==
-----END CERTIFICATE-----
# Issuer: CN=VeriSign Class 3 Public Primary Certification Authority - G3 O=VeriSign, Inc. OU=VeriSign Trust Network/(c) 1999 VeriSign, Inc. - For authorized use only
# Subject: CN=VeriSign Class 3 Public Primary Certification Authority - G3 O=VeriSign, Inc. OU=VeriSign Trust Network/(c) 1999 VeriSign, Inc. - For authorized use only
# Label: "Verisign Class 3 Public Primary Certification Authority - G3"
# Serial: 206684696279472310254277870180966723415
# MD5 Fingerprint: cd:68:b6:a7:c7:c4:ce:75:e0:1d:4f:57:44:61:92:09
# SHA1 Fingerprint: 13:2d:0d:45:53:4b:69:97:cd:b2:d5:c3:39:e2:55:76:60:9b:5c:c6
# SHA256 Fingerprint: eb:04:cf:5e:b1:f3:9a:fa:76:2f:2b:b1:20:f2:96:cb:a5:20:c1:b9:7d:b1:58:95:65:b8:1c:b9:a1:7b:72:44
-----BEGIN CERTIFICATE-----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==
-----END CERTIFICATE-----
# Issuer: CN=Entrust.net Certification Authority (2048) O=Entrust.net OU=www.entrust.net/CPS_2048 incorp. by ref. (limits liab.)/(c) 1999 Entrust.net Limited
# Subject: CN=Entrust.net Certification Authority (2048) O=Entrust.net OU=www.entrust.net/CPS_2048 incorp. by ref. (limits liab.)/(c) 1999 Entrust.net Limited
# Label: "Entrust.net Premium 2048 Secure Server CA"
@@ -152,39 +120,6 @@ ksLi4xaNmjICq44Y3ekQEe5+NauQrz4wlHrQMz2nZQ/1/I6eYs9HRCwBXbsdtTLS
R9I4LtD+gdwyah617jzV/OeBHRnDJELqYzmp
-----END CERTIFICATE-----
# Issuer: CN=AddTrust External CA Root O=AddTrust AB OU=AddTrust External TTP Network
# Subject: CN=AddTrust External CA Root O=AddTrust AB OU=AddTrust External TTP Network
# Label: "AddTrust External Root"
# Serial: 1
# MD5 Fingerprint: 1d:35:54:04:85:78:b0:3f:42:42:4d:bf:20:73:0a:3f
# SHA1 Fingerprint: 02:fa:f3:e2:91:43:54:68:60:78:57:69:4d:f5:e4:5b:68:85:18:68
# SHA256 Fingerprint: 68:7f:a4:51:38:22:78:ff:f0:c8:b1:1f:8d:43:d5:76:67:1c:6e:b2:bc:ea:b4:13:fb:83:d9:65:d0:6d:2f:f2
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----
# Issuer: CN=Entrust Root Certification Authority O=Entrust, Inc. OU=www.entrust.net/CPS is incorporated by reference/(c) 2006 Entrust, Inc.
# Subject: CN=Entrust Root Certification Authority O=Entrust, Inc. OU=www.entrust.net/CPS is incorporated by reference/(c) 2006 Entrust, Inc.
# Label: "Entrust Root Certification Authority"
@@ -771,36 +706,6 @@ vEsXCS+0yx5DaMkHJ8HSXPfqIbloEpw8nL+e/IBcm2PN7EeqJSdnoDfzAIJ9VNep
+OkuE6N36B9K
-----END CERTIFICATE-----
# Issuer: CN=Class 2 Primary CA O=Certplus
# Subject: CN=Class 2 Primary CA O=Certplus
# Label: "Certplus Class 2 Primary CA"
# Serial: 177770208045934040241468760488327595043
# MD5 Fingerprint: 88:2c:8c:52:b8:a2:3c:f3:f7:bb:03:ea:ae:ac:42:0b
# SHA1 Fingerprint: 74:20:74:41:72:9c:dd:92:ec:79:31:d8:23:10:8d:c2:81:92:e2:bb
# SHA256 Fingerprint: 0f:99:3c:8a:ef:97:ba:af:56:87:14:0e:d5:9a:d1:82:1b:b4:af:ac:f0:aa:9a:58:b5:d5:7a:33:8a:3a:fb:cb
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----
# Issuer: CN=DST Root CA X3 O=Digital Signature Trust Co.
# Subject: CN=DST Root CA X3 O=Digital Signature Trust Co.
# Label: "DST Root CA X3"
@@ -1219,36 +1124,6 @@ t0QmwCbAr1UwnjvVNioZBPRcHv/PLLf/0P2HQBHVESO7SMAhqaQoLf0V+LBOK/Qw
WyH8EZE0vkHve52Xdf+XlcCWWC/qu0bXu+TZLg==
-----END CERTIFICATE-----
# Issuer: CN=Deutsche Telekom Root CA 2 O=Deutsche Telekom AG OU=T-TeleSec Trust Center
# Subject: CN=Deutsche Telekom Root CA 2 O=Deutsche Telekom AG OU=T-TeleSec Trust Center
# Label: "Deutsche Telekom Root CA 2"
# Serial: 38
# MD5 Fingerprint: 74:01:4a:91:b1:08:c4:58:ce:47:cd:f0:dd:11:53:08
# SHA1 Fingerprint: 85:a4:08:c0:9c:19:3e:5d:51:58:7d:cd:d6:13:30:fd:8c:de:37:bf
# SHA256 Fingerprint: b6:19:1a:50:d0:c3:97:7f:7d:a9:9b:cd:aa:c8:6a:22:7d:ae:b9:67:9e:c7:0b:a3:b0:c9:d9:22:71:c1:70:d3
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----
# Issuer: CN=Cybertrust Global Root O=Cybertrust, Inc
# Subject: CN=Cybertrust Global Root O=Cybertrust, Inc
# Label: "Cybertrust Global Root"
@@ -1559,47 +1434,6 @@ uLjbvrW5KfnaNwUASZQDhETnv0Mxz3WLJdH0pmT1kvarBes96aULNmLazAZfNou2
XjG4Kvte9nHfRCaexOYNkbQudZWAUWpLMKawYqGT8ZvYzsRjdT9ZR7E=
-----END CERTIFICATE-----
# Issuer: CN=Staat der Nederlanden Root CA - G2 O=Staat der Nederlanden
# Subject: CN=Staat der Nederlanden Root CA - G2 O=Staat der Nederlanden
# Label: "Staat der Nederlanden Root CA - G2"
# Serial: 10000012
# MD5 Fingerprint: 7c:a5:0f:f8:5b:9a:7d:6d:30:ae:54:5a:e3:42:a2:8a
# SHA1 Fingerprint: 59:af:82:79:91:86:c7:b4:75:07:cb:cf:03:57:46:eb:04:dd:b7:16
# SHA256 Fingerprint: 66:8c:83:94:7d:a6:3b:72:4b:ec:e1:74:3c:31:a0:e6:ae:d0:db:8e:c5:b3:1b:e3:77:bb:78:4f:91:b6:71:6f
-----BEGIN CERTIFICATE-----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==
-----END CERTIFICATE-----
# Issuer: CN=Hongkong Post Root CA 1 O=Hongkong Post
# Subject: CN=Hongkong Post Root CA 1 O=Hongkong Post
# Label: "Hongkong Post Root CA 1"
@@ -2200,6 +2034,45 @@ t/2jioSgrGK+KwmHNPBqAbubKVY8/gA3zyNs8U6qtnRGEmyR7jTV7JqR50S+kDFy
SjnRBUkLp7Y3gaVdjKozXoEofKd9J+sAro03
-----END CERTIFICATE-----
# Issuer: CN=EC-ACC O=Agencia Catalana de Certificacio (NIF Q-0801176-I) OU=Serveis Publics de Certificacio/Vegeu https://www.catcert.net/verarrel (c)03/Jerarquia Entitats de Certificacio Catalanes
# Subject: CN=EC-ACC O=Agencia Catalana de Certificacio (NIF Q-0801176-I) OU=Serveis Publics de Certificacio/Vegeu https://www.catcert.net/verarrel (c)03/Jerarquia Entitats de Certificacio Catalanes
# Label: "EC-ACC"
# Serial: -23701579247955709139626555126524820479
# MD5 Fingerprint: eb:f5:9d:29:0d:61:f9:42:1f:7c:c2:ba:6d:e3:15:09
# SHA1 Fingerprint: 28:90:3a:63:5b:52:80:fa:e6:77:4c:0b:6d:a7:d6:ba:a6:4a:f2:e8
# SHA256 Fingerprint: 88:49:7f:01:60:2f:31:54:24:6a:e2:8c:4d:5a:ef:10:f1:d8:7e:bb:76:62:6f:4a:e0:b7:f9:5b:a7:96:87:99
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----
# Issuer: CN=Hellenic Academic and Research Institutions RootCA 2011 O=Hellenic Academic and Research Institutions Cert. Authority
# Subject: CN=Hellenic Academic and Research Institutions RootCA 2011 O=Hellenic Academic and Research Institutions Cert. Authority
# Label: "Hellenic Academic and Research Institutions RootCA 2011"
@@ -3453,46 +3326,6 @@ AAoACxGV2lZFA4gKn2fQ1XmxqI1AbQ3CekD6819kR5LLU7m7Wc5P/dAVUwHY3+vZ
5nbv0CO7O6l5s9UCKc2Jo5YPSjXnTkLAdc0Hz+Ys63su
-----END CERTIFICATE-----
# Issuer: CN=Certinomis - Root CA O=Certinomis OU=0002 433998903
# Subject: CN=Certinomis - Root CA O=Certinomis OU=0002 433998903
# Label: "Certinomis - Root CA"
# Serial: 1
# MD5 Fingerprint: 14:0a:fd:8d:a8:28:b5:38:69:db:56:7e:61:22:03:3f
# SHA1 Fingerprint: 9d:70:bb:01:a5:a4:a0:18:11:2e:f7:1c:01:b9:32:c5:34:e7:88:a8
# SHA256 Fingerprint: 2a:99:f5:bc:11:74:b7:3c:bb:1d:62:08:84:e0:1c:34:e5:1c:cb:39:78:da:12:5f:0e:33:26:88:83:bf:41:58
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----
# Issuer: CN=OISTE WISeKey Global Root GB CA O=WISeKey OU=OISTE Foundation Endorsed
# Subject: CN=OISTE WISeKey Global Root GB CA O=WISeKey OU=OISTE Foundation Endorsed
# Label: "OISTE WISeKey Global Root GB CA"
@@ -3849,47 +3682,6 @@ CkcO8DdZEv8tmZQoTipPNU0zWgIxAOp1AE47xDqUEpHJWEadIRNyp4iciuRMStuW
1KyLa2tJElMzrdfkviT8tQp21KW8EA==
-----END CERTIFICATE-----
# Issuer: CN=LuxTrust Global Root 2 O=LuxTrust S.A.
# Subject: CN=LuxTrust Global Root 2 O=LuxTrust S.A.
# Label: "LuxTrust Global Root 2"
# Serial: 59914338225734147123941058376788110305822489521
# MD5 Fingerprint: b2:e1:09:00:61:af:f7:f1:91:6f:c4:ad:8d:5e:3b:7c
# SHA1 Fingerprint: 1e:0e:56:19:0a:d1:8b:25:98:b2:04:44:ff:66:8a:04:17:99:5f:3f
# SHA256 Fingerprint: 54:45:5f:71:29:c2:0b:14:47:c4:18:f9:97:16:8f:24:c5:8f:c5:02:3b:f5:da:5b:e2:eb:6e:1d:d8:90:2e:d5
-----BEGIN CERTIFICATE-----
MIIFwzCCA6ugAwIBAgIUCn6m30tEntpqJIWe5rgV0xZ/u7EwDQYJKoZIhvcNAQEL
BQAwRjELMAkGA1UEBhMCTFUxFjAUBgNVBAoMDUx1eFRydXN0IFMuQS4xHzAdBgNV
BAMMFkx1eFRydXN0IEdsb2JhbCBSb290IDIwHhcNMTUwMzA1MTMyMTU3WhcNMzUw
MzA1MTMyMTU3WjBGMQswCQYDVQQGEwJMVTEWMBQGA1UECgwNTHV4VHJ1c3QgUy5B
LjEfMB0GA1UEAwwWTHV4VHJ1c3QgR2xvYmFsIFJvb3QgMjCCAiIwDQYJKoZIhvcN
AQEBBQADggIPADCCAgoCggIBANeFl78RmOnwYoNMPIf5U2o3C/IPPIfOb9wmKb3F
ibrJgz337spbxm1Jc7TJRqMbNBM/wYlFV/TZsfs2ZUv7COJIcRHIbjuend+JZTem
hfY7RBi2xjcwYkSSl2l9QjAk5A0MiWtj3sXh306pFGxT4GHO9hcvHTy95iJMHZP1
EMShduxq3sVs35a0VkBCwGKSMKEtFZSg0iAGCW5qbeXrt77U8PEVfIvmTroTzEsn
Xpk8F12PgX8zPU/TPxvsXD/wPEx1bvKm1Z3aLQdjAsZy6ZS8TEmVT4hSyNvoaYL4
zDRbIvCGp4m9SAptZoFtyMhk+wHh9OHe2Z7d21vUKpkmFRseTJIpgp7VkoGSQXAZ
96Tlk0u8d2cx3Rz9MXANF5kM+Qw5GSoXtTBxVdUPrljhPS80m8+f9niFwpN6cj5m
j5wWEWCPnolvZ77gR1o7DJpni89Gxq44o/KnvObWhWszJHAiS8sIm7vI+AIpHb4g
DEa/a4ebsypmQjVGbKq6rfmYe+lQVRQxv7HaLe2ArWgk+2mr2HETMOZns4dA/Yl+
8kPREd8vZS9kzl8UubG/Mb2HeFpZZYiq/FkySIbWTLkpS5XTdvN3JW1CHDiDTf2j
X5t/Lax5Gw5CMZdjpPuKadUiDTSQMC6otOBttpSsvItO13D8xTiOZCXhTTmQzsmH
hFhxAgMBAAGjgagwgaUwDwYDVR0TAQH/BAUwAwEB/zBCBgNVHSAEOzA5MDcGByuB
KwEBAQowLDAqBggrBgEFBQcCARYeaHR0cHM6Ly9yZXBvc2l0b3J5Lmx1eHRydXN0
Lmx1MA4GA1UdDwEB/wQEAwIBBjAfBgNVHSMEGDAWgBT/GCh2+UgFLKGu8SsbK7JT
+Et8szAdBgNVHQ4EFgQU/xgodvlIBSyhrvErGyuyU/hLfLMwDQYJKoZIhvcNAQEL
BQADggIBAGoZFO1uecEsh9QNcH7X9njJCwROxLHOk3D+sFTAMs2ZMGQXvw/l4jP9
BzZAcg4atmpZ1gDlaCDdLnINH2pkMSCEfUmmWjfrRcmF9dTHF5kH5ptV5AzoqbTO
jFu1EVzPig4N1qx3gf4ynCSecs5U89BvolbW7MM3LGVYvlcAGvI1+ut7MV3CwRI9
loGIlonBWVx65n9wNOeD4rHh4bhY79SV5GCc8JaXcozrhAIuZY+kt9J/Z93I055c
qqmkoCUUBpvsT34tC38ddfEz2O3OuHVtPlu5mB0xDVbYQw8wkbIEa91WvpWAVWe+
2M2D2RjuLg+GLZKecBPs3lHJQ3gCpU3I+V/EkVhGFndadKpAvAefMLmx9xIX3eP/
JEAdemrRTxgKqpAd60Ae36EeRJIQmvKN4dFLRp7oRUKX6kWZ8+xm1QL68qZKJKre
zrnK+T+Tb/mjuuqlPpmt/f97mfVl7vBZKGfXkJWkE4SphMHozs51k2MavDzq1WQf
LSoSOcbDWjLtR5EWDrw4wVDej8oqkDQc7kGUnF4ZLvhFSZl0kbAEb+MEWrGrKqv+
x9CWttrhSmQGbmBNvUJO/3jaJMobtNeWOWyu8Q6qp31IiyBMz2TWuJdGsE7RKlY6
oJO9r4Ak4Ap+58rVyuiFVdw2KuGUaJPHZnJED4AhMmwlxyOAgwrr
-----END CERTIFICATE-----
# Issuer: CN=TUBITAK Kamu SM SSL Kok Sertifikasi - Surum 1 O=Turkiye Bilimsel ve Teknolojik Arastirma Kurumu - TUBITAK OU=Kamu Sertifikasyon Merkezi - Kamu SM
# Subject: CN=TUBITAK Kamu SM SSL Kok Sertifikasi - Surum 1 O=Turkiye Bilimsel ve Teknolojik Arastirma Kurumu - TUBITAK OU=Kamu Sertifikasyon Merkezi - Kamu SM
# Label: "TUBITAK Kamu SM SSL Kok Sertifikasi - Surum 1"
@@ -4656,3 +4448,173 @@ L5/ndtFhKvshuzHQqp9HpLIiyhY6UFfEW0NnxWViA0kB60PZ2Pierc+xYw5F9KBa
LJstxabArahH9CdMOA0uG0k7UvToiIMrVCjU8jVStDKDYmlkDJGcn5fqdBb9HxEG
mpv0
-----END CERTIFICATE-----
# Issuer: CN=Entrust Root Certification Authority - G4 O=Entrust, Inc. OU=See www.entrust.net/legal-terms/(c) 2015 Entrust, Inc. - for authorized use only
# Subject: CN=Entrust Root Certification Authority - G4 O=Entrust, Inc. OU=See www.entrust.net/legal-terms/(c) 2015 Entrust, Inc. - for authorized use only
# Label: "Entrust Root Certification Authority - G4"
# Serial: 289383649854506086828220374796556676440
# MD5 Fingerprint: 89:53:f1:83:23:b7:7c:8e:05:f1:8c:71:38:4e:1f:88
# SHA1 Fingerprint: 14:88:4e:86:26:37:b0:26:af:59:62:5c:40:77:ec:35:29:ba:96:01
# SHA256 Fingerprint: db:35:17:d1:f6:73:2a:2d:5a:b9:7c:53:3e:c7:07:79:ee:32:70:a6:2f:b4:ac:42:38:37:24:60:e6:f0:1e:88
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----
# Issuer: CN=Microsoft ECC Root Certificate Authority 2017 O=Microsoft Corporation
# Subject: CN=Microsoft ECC Root Certificate Authority 2017 O=Microsoft Corporation
# Label: "Microsoft ECC Root Certificate Authority 2017"
# Serial: 136839042543790627607696632466672567020
# MD5 Fingerprint: dd:a1:03:e6:4a:93:10:d1:bf:f0:19:42:cb:fe:ed:67
# SHA1 Fingerprint: 99:9a:64:c3:7f:f4:7d:9f:ab:95:f1:47:69:89:14:60:ee:c4:c3:c5
# SHA256 Fingerprint: 35:8d:f3:9d:76:4a:f9:e1:b7:66:e9:c9:72:df:35:2e:e1:5c:fa:c2:27:af:6a:d1:d7:0e:8e:4a:6e:dc:ba:02
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----
# Issuer: CN=Microsoft RSA Root Certificate Authority 2017 O=Microsoft Corporation
# Subject: CN=Microsoft RSA Root Certificate Authority 2017 O=Microsoft Corporation
# Label: "Microsoft RSA Root Certificate Authority 2017"
# Serial: 40975477897264996090493496164228220339
# MD5 Fingerprint: 10:ff:00:ff:cf:c9:f8:c7:7a:c0:ee:35:8e:c9:0f:47
# SHA1 Fingerprint: 73:a5:e6:4a:3b:ff:83:16:ff:0e:dc:cc:61:8a:90:6e:4e:ae:4d:74
# SHA256 Fingerprint: c7:41:f7:0f:4b:2a:8d:88:bf:2e:71:c1:41:22:ef:53:ef:10:eb:a0:cf:a5:e6:4c:fa:20:f4:18:85:30:73:e0
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----
# Issuer: CN=e-Szigno Root CA 2017 O=Microsec Ltd.
# Subject: CN=e-Szigno Root CA 2017 O=Microsec Ltd.
# Label: "e-Szigno Root CA 2017"
# Serial: 411379200276854331539784714
# MD5 Fingerprint: de:1f:f6:9e:84:ae:a7:b4:21:ce:1e:58:7d:d1:84:98
# SHA1 Fingerprint: 89:d4:83:03:4f:9e:9a:48:80:5f:72:37:d4:a9:a6:ef:cb:7c:1f:d1
# SHA256 Fingerprint: be:b0:0b:30:83:9b:9b:c3:2c:32:e4:44:79:05:95:06:41:f2:64:21:b1:5e:d0:89:19:8b:51:8a:e2:ea:1b:99
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----
# Issuer: O=CERTSIGN SA OU=certSIGN ROOT CA G2
# Subject: O=CERTSIGN SA OU=certSIGN ROOT CA G2
# Label: "certSIGN Root CA G2"
# Serial: 313609486401300475190
# MD5 Fingerprint: 8c:f1:75:8a:c6:19:cf:94:b7:f7:65:20:87:c3:97:c7
# SHA1 Fingerprint: 26:f9:93:b4:ed:3d:28:27:b0:b9:4b:a7:e9:15:1d:a3:8d:92:e5:32
# SHA256 Fingerprint: 65:7c:fe:2f:a7:3f:aa:38:46:25:71:f3:32:a2:36:3a:46:fc:e7:02:09:51:71:07:02:cd:fb:b6:ee:da:33:05
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----
+49 -4
View File
@@ -4,12 +4,57 @@
certifi.py
~~~~~~~~~~
This module returns the installation location of cacert.pem.
This module returns the installation location of cacert.pem or its contents.
"""
import os
try:
from importlib.resources import path as get_path, read_text
def where():
f = os.path.dirname(__file__)
_CACERT_CTX = None
_CACERT_PATH = None
return os.path.join(f, 'cacert.pem')
def where():
# This is slightly terrible, but we want to delay extracting the file
# in cases where we're inside of a zipimport situation until someone
# actually calls where(), but we don't want to re-extract the file
# on every call of where(), so we'll do it once then store it in a
# global variable.
global _CACERT_CTX
global _CACERT_PATH
if _CACERT_PATH is None:
# This is slightly janky, the importlib.resources API wants you to
# manage the cleanup of this file, so it doesn't actually return a
# path, it returns a context manager that will give you the path
# when you enter it and will do any cleanup when you leave it. In
# the common case of not needing a temporary file, it will just
# return the file system location and the __exit__() is a no-op.
#
# We also have to hold onto the actual context manager, because
# it will do the cleanup whenever it gets garbage collected, so
# we will also store that at the global level as well.
_CACERT_CTX = get_path("certifi", "cacert.pem")
_CACERT_PATH = str(_CACERT_CTX.__enter__())
return _CACERT_PATH
except ImportError:
# This fallback will work for Python versions prior to 3.7 that lack the
# importlib.resources module but relies on the existing `where` function
# so won't address issues with environments like PyOxidizer that don't set
# __file__ on modules.
def read_text(_module, _path, encoding="ascii"):
with open(where(), "r", encoding=encoding) as data:
return data.read()
# If we don't have importlib.resources, then we will just do the old logic
# of assuming we're on the filesystem and munge the path directly.
def where():
f = os.path.dirname(__file__)
return os.path.join(f, "cacert.pem")
def contents():
return read_text("certifi", "cacert.pem", encoding="ascii")
@@ -1,392 +0,0 @@
# coding=utf-8
import logging
import random
import re
import os
import json
import base64
from copy import deepcopy
from time import sleep
from collections import OrderedDict
from .jsfuck import jsunfuck
import js2py
from requests.sessions import Session
from subliminal_patch.pitcher import pitchers
try:
from requests_toolbelt.utils import dump
except ImportError:
pass
try:
from urlparse import urlparse
from urlparse import urlunparse
except ImportError:
from urllib.parse import urlparse
from urllib.parse import urlunparse
brotli_available = True
try:
from brotli import decompress as brdec
except:
brotli_available = False
logger = logging.getLogger(__name__)
__version__ = "2.0.3"
# Orignally written by https://github.com/Anorov/cloudflare-scrape
# Rewritten by VeNoMouS - <venom@gen-x.co.nz> for https://github.com/VeNoMouS/Sick-Beard - 24/3/2018 NZDT
DEFAULT_USER_AGENTS = [
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36",
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/65.0.3325.181 Chrome/65.0.3325.181 Safari/537.36",
"Mozilla/5.0 (Linux; Android 7.0; Moto G (5) Build/NPPS25.137-93-8) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.137 Mobile Safari/537.36",
"Mozilla/5.0 (iPhone; CPU iPhone OS 7_0_4 like Mac OS X) AppleWebKit/537.51.1 (KHTML, like Gecko) Version/7.0 Mobile/11B554a Safari/9537.53",
"Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:60.0) Gecko/20100101 Firefox/60.0",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.13; rv:59.0) Gecko/20100101 Firefox/59.0",
"Mozilla/5.0 (Windows NT 6.3; Win64; x64; rv:57.0) Gecko/20100101 Firefox/57.0",
]
BUG_REPORT = """\
Cloudflare may have changed their technique, or there may be a bug in the script.
"""
cur_path = os.path.abspath(os.path.dirname(__file__))
if brotli_available:
brwsrs = os.path.join(cur_path, "browsers_br.json")
with open(brwsrs, "r") as f:
UA_COMBO = json.load(f, object_pairs_hook=OrderedDict)["chrome"]
else:
brwsrs = os.path.join(cur_path, "browsers.json")
UA_COMBO = []
with open(brwsrs, "r") as f:
_brwsrs = json.load(f, object_pairs_hook=OrderedDict)
for entry in _brwsrs:
_entry = OrderedDict(("-".join(a.capitalize() for a in key.split("-")), value)
for key, value in entry.iteritems())
_entry["User-Agent"] = None
UA_COMBO.append({"User-Agent": [entry["user-agent"]], "headers": _entry})
class NeedsCaptchaException(Exception):
pass
class CloudflareScraper(Session):
def __init__(self, *args, **kwargs):
self.delay = kwargs.pop('delay', 8)
self.debug = False
self._ua = None
self._hdrs = None
super(CloudflareScraper, self).__init__(*args, **kwargs)
if not self._ua:
# Set a random User-Agent if no custom User-Agent has been set
ua_combo = random.choice(UA_COMBO)
self._ua = random.choice(ua_combo["User-Agent"])
self._hdrs = ua_combo["headers"].copy()
self._hdrs["User-Agent"] = self._ua
self.headers['User-Agent'] = self._ua
def set_cloudflare_challenge_delay(self, delay):
if isinstance(delay, (int, float)) and delay > 0:
self.delay = delay
def is_cloudflare_challenge(self, resp):
if resp.headers.get('Server', '').startswith('cloudflare'):
if b'why_captcha' in resp.content or b'/cdn-cgi/l/chk_captcha' in resp.content:
raise NeedsCaptchaException
return (
resp.status_code in [429, 503]
and b"jschl_vc" in resp.content
and b"jschl_answer" in resp.content
)
return False
def debugRequest(self, req):
try:
print (dump.dump_all(req).decode('utf-8'))
except:
pass
def request(self, method, url, *args, **kwargs):
# self.headers = (
# OrderedDict(
# [
# ('User-Agent', self.headers['User-Agent']),
# ('Accept', 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'),
# ('Accept-Language', 'en-US,en;q=0.5'),
# ('Accept-Encoding', 'gzip, deflate'),
# ('Connection', 'close'),
# ('Upgrade-Insecure-Requests', '1')
# ]
# )
# )
self.headers = self._hdrs.copy()
resp = super(CloudflareScraper, self).request(method, url, *args, **kwargs)
if resp.headers.get('content-encoding') == 'br' and brotli_available:
resp._content = brdec(resp._content)
# Debug request
if self.debug:
self.debugRequest(resp)
# Check if Cloudflare anti-bot is on
try:
if self.is_cloudflare_challenge(resp):
# Work around if the initial request is not a GET,
# Superseed with a GET then re-request the orignal METHOD.
if resp.request.method != 'GET':
self.request('GET', resp.url)
resp = self.request(method, url, *args, **kwargs)
else:
resp = self.solve_cf_challenge(resp, **kwargs)
except NeedsCaptchaException:
# solve the captcha
site_key = re.search(r'data-sitekey="(.+?)"', resp.content).group(1)
challenge_s = re.search(r'type="hidden" name="s" value="(.+?)"', resp.content).group(1)
challenge_ray = re.search(r'data-ray="(.+?)"', resp.content).group(1)
if not all([site_key, challenge_s, challenge_ray]):
raise Exception("cf: Captcha site-key not found!")
pitcher = pitchers.get_pitcher()("cf", resp.request.url, site_key,
user_agent=self.headers["User-Agent"],
cookies=self.cookies.get_dict(),
is_invisible=True)
logger.info("cf: Solving captcha")
result = pitcher.throw()
if not result:
raise Exception("cf: Couldn't solve captcha!")
parsed_url = urlparse(resp.url)
domain = parsed_url.netloc
submit_url = '{}://{}/cdn-cgi/l/chk_captcha'.format(parsed_url.scheme, domain)
method = resp.request.method
cloudflare_kwargs = {
'allow_redirects': False,
'headers': {'Referer': resp.url},
'params': OrderedDict(
[
('s', challenge_s),
('g-recaptcha-response', result)
]
)
}
return self.request(method, submit_url, **cloudflare_kwargs)
return resp
def solve_cf_challenge(self, resp, **original_kwargs):
body = resp.text
# Cloudflare requires a delay before solving the challenge
if self.delay == 8:
try:
delay = float(re.search(r'submit\(\);\r?\n\s*},\s*([0-9]+)', body).group(1)) / float(1000)
if isinstance(delay, (int, float)):
self.delay = delay
except:
pass
sleep(self.delay)
parsed_url = urlparse(resp.url)
domain = parsed_url.netloc
submit_url = '{}://{}/cdn-cgi/l/chk_jschl'.format(parsed_url.scheme, domain)
cloudflare_kwargs = deepcopy(original_kwargs)
headers = cloudflare_kwargs.setdefault('headers', {'Referer': resp.url})
try:
params = cloudflare_kwargs.setdefault(
'params', OrderedDict(
[
('s', re.search(r'name="s"\svalue="(?P<s_value>[^"]+)', body).group('s_value')),
('jschl_vc', re.search(r'name="jschl_vc" value="(\w+)"', body).group(1)),
('pass', re.search(r'name="pass" value="(.+?)"', body).group(1)),
]
)
)
except Exception as e:
# Something is wrong with the page.
# This may indicate Cloudflare has changed their anti-bot
# technique. If you see this and are running the latest version,
# please open a GitHub issue so I can update the code accordingly.
raise ValueError("Unable to parse Cloudflare anti-bots page: {} {}".format(e.message, BUG_REPORT))
# Solve the Javascript challenge
params['jschl_answer'] = self.solve_challenge(body, domain)
# Requests transforms any request into a GET after a redirect,
# so the redirect has to be handled manually here to allow for
# performing other types of requests even as the first request.
method = resp.request.method
cloudflare_kwargs['allow_redirects'] = False
redirect = self.request(method, submit_url, **cloudflare_kwargs)
redirect_location = urlparse(redirect.headers['Location'])
if not redirect_location.netloc:
redirect_url = urlunparse(
(
parsed_url.scheme,
domain,
redirect_location.path,
redirect_location.params,
redirect_location.query,
redirect_location.fragment
)
)
return self.request(method, redirect_url, **original_kwargs)
return self.request(method, redirect.headers['Location'], **original_kwargs)
def solve_challenge(self, body, domain):
try:
js = re.search(
r"setTimeout\(function\(\){\s+(var s,t,o,p,b,r,e,a,k,i,n,g,f.+?\r?\n[\s\S]+?a\.value =.+?)\r?\n",
body
).group(1)
except Exception:
raise ValueError("Unable to identify Cloudflare IUAM Javascript on website. {}".format(BUG_REPORT))
js = re.sub(r"a\.value = ((.+).toFixed\(10\))?", r"\1", js)
js = re.sub(r'(e\s=\sfunction\(s\)\s{.*?};)', '', js, flags=re.DOTALL|re.MULTILINE)
js = re.sub(r"\s{3,}[a-z](?: = |\.).+", "", js).replace("t.length", str(len(domain)))
js = js.replace('; 121', '')
# Strip characters that could be used to exit the string context
# These characters are not currently used in Cloudflare's arithmetic snippet
js = re.sub(r"[\n\\']", "", js)
if 'toFixed' not in js:
raise ValueError("Error parsing Cloudflare IUAM Javascript challenge. {}".format(BUG_REPORT))
try:
jsEnv = """
var t = "{domain}";
var g = String.fromCharCode;
o = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=";
e = function(s) {{
s += "==".slice(2 - (s.length & 3));
var bm, r = "", r1, r2, i = 0;
for (; i < s.length;) {{
bm = o.indexOf(s.charAt(i++)) << 18 | o.indexOf(s.charAt(i++)) << 12 | (r1 = o.indexOf(s.charAt(i++))) << 6 | (r2 = o.indexOf(s.charAt(i++)));
r += r1 === 64 ? g(bm >> 16 & 255) : r2 === 64 ? g(bm >> 16 & 255, bm >> 8 & 255) : g(bm >> 16 & 255, bm >> 8 & 255, bm & 255);
}}
return r;
}};
function italics (str) {{ return '<i>' + this + '</i>'; }};
var document = {{
getElementById: function () {{
return {{'innerHTML': '{innerHTML}'}};
}}
}};
{js}
"""
innerHTML = re.search(
'<div(?: [^<>]*)? id="([^<>]*?)">([^<>]*?)<\/div>',
body,
re.MULTILINE | re.DOTALL
)
innerHTML = innerHTML.group(2).replace("'", r"\'") if innerHTML else ""
js = jsunfuck(jsEnv.format(domain=domain, innerHTML=innerHTML, js=js))
def atob(s):
return base64.b64decode('{}'.format(s)).decode('utf-8')
js2py.disable_pyimport()
context = js2py.EvalJs({'atob': atob})
result = context.eval(js)
except Exception:
logging.error("Error executing Cloudflare IUAM Javascript. {}".format(BUG_REPORT))
raise
try:
float(result)
except Exception:
raise ValueError("Cloudflare IUAM challenge returned unexpected answer. {}".format(BUG_REPORT))
return result
@classmethod
def create_scraper(cls, sess=None, **kwargs):
"""
Convenience function for creating a ready-to-go CloudflareScraper object.
"""
scraper = cls(**kwargs)
if sess:
attrs = ['auth', 'cert', 'cookies', 'headers', 'hooks', 'params', 'proxies', 'data']
for attr in attrs:
val = getattr(sess, attr, None)
if val:
setattr(scraper, attr, val)
return scraper
# Functions for integrating cloudflare-scrape with other applications and scripts
@classmethod
def get_tokens(cls, url, user_agent=None, debug=False, **kwargs):
scraper = cls.create_scraper()
scraper.debug = debug
if user_agent:
scraper.headers['User-Agent'] = user_agent
try:
resp = scraper.get(url, **kwargs)
resp.raise_for_status()
except Exception as e:
logging.error("'{}' returned an error. Could not collect tokens.".format(url))
raise
domain = urlparse(resp.url).netloc
cookie_domain = None
for d in scraper.cookies.list_domains():
if d.startswith('.') and d in ('.{}'.format(domain)):
cookie_domain = d
break
else:
raise ValueError("Unable to find Cloudflare cookies. Does the site actually have Cloudflare IUAM (\"I'm Under Attack Mode\") enabled?")
return (
{
'__cfduid': scraper.cookies.get('__cfduid', '', domain=cookie_domain),
'cf_clearance': scraper.cookies.get('cf_clearance', '', domain=cookie_domain)
},
scraper.headers['User-Agent']
)
@classmethod
def get_cookie_string(cls, url, user_agent=None, debug=False, **kwargs):
"""
Convenience function for building a Cookie HTTP header value.
"""
tokens, user_agent = cls.get_tokens(url, user_agent=user_agent, debug=debug, **kwargs)
return "; ".join("=".join(pair) for pair in tokens.items()), user_agent
create_scraper = CloudflareScraper.create_scraper
get_tokens = CloudflareScraper.get_tokens
get_cookie_string = CloudflareScraper.get_cookie_string
@@ -1,80 +0,0 @@
[
{
"connection": "close",
"accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
"user-agent": "Mozilla/5.0 (Windows NT 5.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2062.102 Safari/537.36",
"accept-encoding": "gzip,deflate",
"accept-language": "en-US,en;q=0.8"
},
{
"connection": "close",
"accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
"user-agent": "Mozilla/5.0 (Windows NT 5.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.101 Safari/537.36",
"accept-encoding": "gzip,deflate",
"accept-language": "en-US,en;q=0.8"
},
{
"connection": "close",
"accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
"upgrade-insecure-requests": "1",
"user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36",
"accept-language": "en-US,en;q=0.8",
"accept-encoding": "gzip, deflate, "
},
{
"connection": "close",
"accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
"upgrade-insecure-requests": "1",
"user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.75 Safari/537.36",
"accept-language": "en-US,en;q=0.8",
"accept-encoding": "gzip, deflate, "
},
{
"connection": "close",
"accept": "*/*",
"user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:30.0) Gecko/20100101 Firefox/30.0"
},
{
"connection": "close",
"accept": "image/jpeg, image/gif, image/pjpeg, application/x-ms-application, application/xaml+xml, application/x-ms-xbap, */*",
"accept-language": "en-US",
"user-agent": "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET4.0C; .NET4.0E)",
"accept-encoding": "gzip, deflate"
},
{
"connection": "close",
"accept": "text/html, application/xhtml+xml, */*",
"accept-language": "en-US",
"user-agent": "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0)",
"accept-encoding": "gzip, deflate"
},
{
"connection": "close",
"accept": "text/html, application/xhtml+xml, */*",
"accept-language": "en-US",
"user-agent": "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)",
"accept-encoding": "gzip, deflate",
"dnt": "1"
},
{
"connection": "close",
"user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:41.0) Gecko/20100101 Firefox/41.0",
"accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
"accept-language": "en-US,en;q=0.5",
"accept-encoding": "gzip, deflate"
},
{
"connection": "close",
"user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0",
"accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
"accept-language": "en-US,en;q=0.5",
"accept-encoding": "gzip, deflate"
},
{
"connection": "close",
"user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0",
"accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
"accept-language": "en-US,en;q=0.5",
"accept-encoding": "gzip, deflate"
}
]
@@ -0,0 +1,311 @@
import logging
import re
import sys
import ssl
from copy import deepcopy
from time import sleep
from collections import OrderedDict
from requests.sessions import Session
from requests.adapters import HTTPAdapter
from requests.packages.urllib3.util.ssl_ import create_urllib3_context
from .interpreters import JavaScriptInterpreter
from .user_agent import User_Agent
try:
from requests_toolbelt.utils import dump
except ImportError:
pass
try:
import brotli
except ImportError:
pass
try:
from urlparse import urlparse
from urlparse import urlunparse
except ImportError:
from urllib.parse import urlparse
from urllib.parse import urlunparse
##########################################################################################################################################################
__version__ = '1.1.9'
BUG_REPORT = 'Cloudflare may have changed their technique, or there may be a bug in the script.'
##########################################################################################################################################################
class CipherSuiteAdapter(HTTPAdapter):
def __init__(self, cipherSuite=None, **kwargs):
self.cipherSuite = cipherSuite
if hasattr(ssl, 'PROTOCOL_TLS'):
self.ssl_context = create_urllib3_context(
ssl_version=getattr(ssl, 'PROTOCOL_TLSv1_3', ssl.PROTOCOL_TLSv1_2),
ciphers=self.cipherSuite
)
else:
self.ssl_context = create_urllib3_context(ssl_version=ssl.PROTOCOL_TLSv1)
super(CipherSuiteAdapter, self).__init__(**kwargs)
##########################################################################################################################################################
def init_poolmanager(self, *args, **kwargs):
kwargs['ssl_context'] = self.ssl_context
return super(CipherSuiteAdapter, self).init_poolmanager(*args, **kwargs)
##########################################################################################################################################################
def proxy_manager_for(self, *args, **kwargs):
kwargs['ssl_context'] = self.ssl_context
return super(CipherSuiteAdapter, self).proxy_manager_for(*args, **kwargs)
##########################################################################################################################################################
class CloudScraper(Session):
def __init__(self, *args, **kwargs):
self.debug = kwargs.pop('debug', False)
self.delay = kwargs.pop('delay', None)
self.interpreter = kwargs.pop('interpreter', 'js2py')
self.allow_brotli = kwargs.pop('allow_brotli', True if 'brotli' in sys.modules.keys() else False)
self.cipherSuite = None
super(CloudScraper, self).__init__(*args, **kwargs)
if 'requests' in self.headers['User-Agent']:
# Set a random User-Agent if no custom User-Agent has been set
self.headers = User_Agent(allow_brotli=self.allow_brotli).headers
self.mount('https://', CipherSuiteAdapter(self.loadCipherSuite()))
##########################################################################################################################################################
@staticmethod
def debugRequest(req):
try:
print(dump.dump_all(req).decode('utf-8'))
except: # noqa
pass
##########################################################################################################################################################
def loadCipherSuite(self):
if self.cipherSuite:
return self.cipherSuite
self.cipherSuite = ''
if hasattr(ssl, 'PROTOCOL_TLS'):
ciphers = [
'ECDHE-ECDSA-AES128-GCM-SHA256', 'ECDHE-RSA-AES128-GCM-SHA256', 'ECDHE-ECDSA-AES256-GCM-SHA384',
'ECDHE-RSA-AES256-GCM-SHA384', 'ECDHE-ECDSA-CHACHA20-POLY1305-SHA256', 'ECDHE-RSA-CHACHA20-POLY1305-SHA256',
'ECDHE-RSA-AES128-CBC-SHA', 'ECDHE-RSA-AES256-CBC-SHA', 'RSA-AES128-GCM-SHA256', 'RSA-AES256-GCM-SHA384',
'ECDHE-RSA-AES128-GCM-SHA256', 'RSA-AES256-SHA', '3DES-EDE-CBC'
]
if hasattr(ssl, 'PROTOCOL_TLSv1_3'):
ciphers.insert(0, ['GREASE_3A', 'GREASE_6A', 'AES128-GCM-SHA256', 'AES256-GCM-SHA256', 'AES256-GCM-SHA384', 'CHACHA20-POLY1305-SHA256'])
ctx = ssl.SSLContext(getattr(ssl, 'PROTOCOL_TLSv1_3', ssl.PROTOCOL_TLSv1_2))
for cipher in ciphers:
try:
ctx.set_ciphers(cipher)
self.cipherSuite = '{}:{}'.format(self.cipherSuite, cipher).rstrip(':')
except ssl.SSLError:
pass
return self.cipherSuite
##########################################################################################################################################################
def request(self, method, url, *args, **kwargs):
ourSuper = super(CloudScraper, self)
resp = ourSuper.request(method, url, *args, **kwargs)
if resp.headers.get('Content-Encoding') == 'br':
if self.allow_brotli and resp._content:
resp._content = brotli.decompress(resp.content)
else:
logging.warning('Brotli content detected, But option is disabled, we will not continue.')
return resp
# Debug request
if self.debug:
self.debugRequest(resp)
# Check if Cloudflare anti-bot is on
if self.isChallengeRequest(resp):
if resp.request.method != 'GET':
# Work around if the initial request is not a GET,
# Supersede with a GET then re-request the original METHOD.
self.request('GET', resp.url)
resp = ourSuper.request(method, url, *args, **kwargs)
else:
# Solve Challenge
resp = self.sendChallengeResponse(resp, **kwargs)
return resp
##########################################################################################################################################################
@staticmethod
def isChallengeRequest(resp):
if resp.headers.get('Server', '').startswith('cloudflare'):
if b'why_captcha' in resp.content or b'/cdn-cgi/l/chk_captcha' in resp.content:
raise ValueError('Captcha')
return (
resp.status_code in [429, 503]
and all(s in resp.content for s in [b'jschl_vc', b'jschl_answer'])
)
return False
##########################################################################################################################################################
def sendChallengeResponse(self, resp, **original_kwargs):
body = resp.text
# Cloudflare requires a delay before solving the challenge
if not self.delay:
try:
delay = float(re.search(r'submit\(\);\r?\n\s*},\s*([0-9]+)', body).group(1)) / float(1000)
if isinstance(delay, (int, float)):
self.delay = delay
except: # noqa
pass
sleep(self.delay)
parsed_url = urlparse(resp.url)
domain = parsed_url.netloc
submit_url = '{}://{}/cdn-cgi/l/chk_jschl'.format(parsed_url.scheme, domain)
cloudflare_kwargs = deepcopy(original_kwargs)
try:
params = OrderedDict()
s = re.search(r'name="s"\svalue="(?P<s_value>[^"]+)', body)
if s:
params['s'] = s.group('s_value')
params.update(
[
('jschl_vc', re.search(r'name="jschl_vc" value="(\w+)"', body).group(1)),
('pass', re.search(r'name="pass" value="(.+?)"', body).group(1))
]
)
params = cloudflare_kwargs.setdefault('params', params)
except Exception as e:
raise ValueError('Unable to parse Cloudflare anti-bots page: {} {}'.format(e.message, BUG_REPORT))
# Solve the Javascript challenge
params['jschl_answer'] = JavaScriptInterpreter.dynamicImport(self.interpreter).solveChallenge(body, domain)
# Requests transforms any request into a GET after a redirect,
# so the redirect has to be handled manually here to allow for
# performing other types of requests even as the first request.
cloudflare_kwargs['allow_redirects'] = False
redirect = self.request(resp.request.method, submit_url, **cloudflare_kwargs)
redirect_location = urlparse(redirect.headers['Location'])
if not redirect_location.netloc:
redirect_url = urlunparse(
(
parsed_url.scheme,
domain,
redirect_location.path,
redirect_location.params,
redirect_location.query,
redirect_location.fragment
)
)
return self.request(resp.request.method, redirect_url, **original_kwargs)
return self.request(resp.request.method, redirect.headers['Location'], **original_kwargs)
##########################################################################################################################################################
@classmethod
def create_scraper(cls, sess=None, **kwargs):
"""
Convenience function for creating a ready-to-go CloudScraper object.
"""
scraper = cls(**kwargs)
if sess:
attrs = ['auth', 'cert', 'cookies', 'headers', 'hooks', 'params', 'proxies', 'data']
for attr in attrs:
val = getattr(sess, attr, None)
if val:
setattr(scraper, attr, val)
return scraper
##########################################################################################################################################################
# Functions for integrating cloudscraper with other applications and scripts
@classmethod
def get_tokens(cls, url, **kwargs):
scraper = cls.create_scraper(
debug=kwargs.pop('debug', False),
delay=kwargs.pop('delay', None),
interpreter=kwargs.pop('interpreter', 'js2py'),
allow_brotli=kwargs.pop('allow_brotli', True),
)
try:
resp = scraper.get(url, **kwargs)
resp.raise_for_status()
except Exception:
logging.error('"{}" returned an error. Could not collect tokens.'.format(url))
raise
domain = urlparse(resp.url).netloc
# noinspection PyUnusedLocal
cookie_domain = None
for d in scraper.cookies.list_domains():
if d.startswith('.') and d in ('.{}'.format(domain)):
cookie_domain = d
break
else:
raise ValueError('Unable to find Cloudflare cookies. Does the site actually have Cloudflare IUAM ("I\'m Under Attack Mode") enabled?')
return (
{
'__cfduid': scraper.cookies.get('__cfduid', '', domain=cookie_domain),
'cf_clearance': scraper.cookies.get('cf_clearance', '', domain=cookie_domain)
},
scraper.headers['User-Agent']
)
##########################################################################################################################################################
@classmethod
def get_cookie_string(cls, url, **kwargs):
"""
Convenience function for building a Cookie HTTP header value.
"""
tokens, user_agent = cls.get_tokens(url, **kwargs)
return '; '.join('='.join(pair) for pair in tokens.items()), user_agent
##########################################################################################################################################################
create_scraper = CloudScraper.create_scraper
get_tokens = CloudScraper.get_tokens
get_cookie_string = CloudScraper.get_cookie_string
@@ -0,0 +1,89 @@
import re
import sys
import logging
import abc
if sys.version_info >= (3, 4):
ABC = abc.ABC # noqa
else:
ABC = abc.ABCMeta('ABC', (), {})
##########################################################################################################################################################
BUG_REPORT = 'Cloudflare may have changed their technique, or there may be a bug in the script.'
##########################################################################################################################################################
interpreters = {}
class JavaScriptInterpreter(ABC):
@abc.abstractmethod
def __init__(self, name):
interpreters[name] = self
@classmethod
def dynamicImport(cls, name):
if name not in interpreters:
try:
__import__('{}.{}'.format(cls.__module__, name))
if not isinstance(interpreters.get(name), JavaScriptInterpreter):
raise ImportError('The interpreter was not initialized.')
except ImportError:
logging.error('Unable to load {} interpreter'.format(name))
raise
return interpreters[name]
@abc.abstractmethod
def eval(self, jsEnv, js):
pass
def solveChallenge(self, body, domain):
try:
js = re.search(
r'setTimeout\(function\(\){\s+(var s,t,o,p,b,r,e,a,k,i,n,g,f.+?\r?\n[\s\S]+?a\.value =.+?)\r?\n',
body
).group(1)
except Exception:
raise ValueError('Unable to identify Cloudflare IUAM Javascript on website. {}'.format(BUG_REPORT))
js = re.sub(r'\s{2,}', ' ', js, flags=re.MULTILINE | re.DOTALL).replace('\'; 121\'', '')
js += '\na.value;'
jsEnv = '''
String.prototype.italics=function(str) {{return "<i>" + this + "</i>";}};
var document = {{
createElement: function () {{
return {{ firstChild: {{ href: "https://{domain}/" }} }}
}},
getElementById: function () {{
return {{"innerHTML": "{innerHTML}"}};
}}
}};
'''
try:
innerHTML = re.search(
r'<div(?: [^<>]*)? id="([^<>]*?)">([^<>]*?)</div>',
body,
re.MULTILINE | re.DOTALL
)
innerHTML = innerHTML.group(2) if innerHTML else ''
except: # noqa
logging.error('Error extracting Cloudflare IUAM Javascript. {}'.format(BUG_REPORT))
raise
try:
result = self.eval(
re.sub(r'\s{2,}', ' ', jsEnv.format(domain=domain, innerHTML=innerHTML), flags=re.MULTILINE | re.DOTALL),
js
)
float(result)
except Exception:
logging.error('Error executing Cloudflare IUAM Javascript. {}'.format(BUG_REPORT))
raise
return result
@@ -0,0 +1,32 @@
from __future__ import absolute_import
import js2py
import logging
import base64
from . import JavaScriptInterpreter
from .jsunfuck import jsunfuck
class ChallengeInterpreter(JavaScriptInterpreter):
def __init__(self):
super(ChallengeInterpreter, self).__init__('js2py')
def eval(self, jsEnv, js):
if js2py.eval_js('(+(+!+[]+[+!+[]]+(!![]+[])[!+[]+!+[]+!+[]]+[!+[]+!+[]]+[+[]])+[])[+!+[]]') == '1':
logging.warning('WARNING - Please upgrade your js2py https://github.com/PiotrDabkowski/Js2Py, applying work around for the meantime.')
js = jsunfuck(js)
def atob(s):
return base64.b64decode('{}'.format(s)).decode('utf-8')
js2py.disable_pyimport()
context = js2py.EvalJs({'atob': atob})
result = context.eval('{}{}'.format(jsEnv, js))
return result
ChallengeInterpreter()
@@ -80,18 +80,18 @@ CONSTRUCTORS = {
'RegExp': 'Function("return/"+false+"/")()'
}
def jsunfuck(jsfuckString):
for key in sorted(MAPPING, key=lambda k: len(MAPPING[k]), reverse=True):
if MAPPING.get(key) in jsfuckString:
jsfuckString = jsfuckString.replace(MAPPING.get(key), '"{}"'.format(key))
for key in sorted(SIMPLE, key=lambda k: len(SIMPLE[k]), reverse=True):
if SIMPLE.get(key) in jsfuckString:
jsfuckString = jsfuckString.replace(SIMPLE.get(key), '{}'.format(key))
#for key in sorted(CONSTRUCTORS, key=lambda k: len(CONSTRUCTORS[k]), reverse=True):
# for key in sorted(CONSTRUCTORS, key=lambda k: len(CONSTRUCTORS[k]), reverse=True):
# if CONSTRUCTORS.get(key) in jsfuckString:
# jsfuckString = jsfuckString.replace(CONSTRUCTORS.get(key), '{}'.format(key))
return jsfuckString
return jsfuckString
@@ -0,0 +1,46 @@
import base64
import logging
import subprocess
from . import JavaScriptInterpreter
##########################################################################################################################################################
BUG_REPORT = 'Cloudflare may have changed their technique, or there may be a bug in the script.'
##########################################################################################################################################################
class ChallengeInterpreter(JavaScriptInterpreter):
def __init__(self):
super(ChallengeInterpreter, self).__init__('nodejs')
def eval(self, jsEnv, js):
try:
js = 'var atob = function(str) {return Buffer.from(str, "base64").toString("binary");};' \
'var challenge = atob("%s");' \
'var context = {atob: atob};' \
'var options = {filename: "iuam-challenge.js", timeout: 4000};' \
'var answer = require("vm").runInNewContext(challenge, context, options);' \
'process.stdout.write(String(answer));' \
% base64.b64encode('{}{}'.format(jsEnv, js).encode('UTF-8')).decode('ascii')
return subprocess.check_output(['node', '-e', js])
except OSError as e:
if e.errno == 2:
raise EnvironmentError(
'Missing Node.js runtime. Node is required and must be in the PATH (check with `node -v`). Your Node binary may be called `nodejs` rather than `node`, '
'in which case you may need to run `apt-get install nodejs-legacy` on some Debian-based systems. (Please read the cloudscraper'
' README\'s Dependencies section: https://github.com/VeNoMouS/cloudscraper#dependencies.'
)
raise
except Exception:
logging.error('Error executing Cloudflare IUAM Javascript. %s' % BUG_REPORT)
raise
pass
ChallengeInterpreter()
@@ -0,0 +1,40 @@
import os
import json
import random
import logging
from collections import OrderedDict
##########################################################################################################################################################
class User_Agent():
##########################################################################################################################################################
def __init__(self, *args, **kwargs):
self.headers = None
self.loadUserAgent(*args, **kwargs)
##########################################################################################################################################################
def loadUserAgent(self, *args, **kwargs):
browser = kwargs.pop('browser', 'chrome')
user_agents = json.load(
open(os.path.join(os.path.dirname(__file__), 'browsers.json'), 'r'),
object_pairs_hook=OrderedDict
)
if not user_agents.get(browser):
logging.error('Sorry "{}" browser User-Agent was not found.'.format(browser))
raise
user_agent = random.choice(user_agents.get(browser))
self.headers = user_agent.get('headers')
self.headers['User-Agent'] = random.choice(user_agent.get('User-Agent'))
if not kwargs.get('allow_brotli', False):
if 'br' in self.headers['Accept-Encoding']:
self.headers['Accept-Encoding'] = ','.join([encoding for encoding in self.headers['Accept-Encoding'].split(',') if encoding.strip() != 'br']).strip()
File diff suppressed because it is too large Load Diff
+3 -10
View File
@@ -5,6 +5,7 @@ import re
from .translators.friendly_nodes import REGEXP_CONVERTER
from .utils.injector import fix_js_args
from types import FunctionType, ModuleType, GeneratorType, BuiltinFunctionType, MethodType, BuiltinMethodType
from math import floor, log10
import traceback
try:
import numpy
@@ -603,15 +604,7 @@ class PyJs(object):
elif typ == 'Boolean':
return Js('true') if self.value else Js('false')
elif typ == 'Number': #or self.Class=='Number':
if self.is_nan():
return Js('NaN')
elif self.is_infinity():
sign = '-' if self.value < 0 else ''
return Js(sign + 'Infinity')
elif isinstance(self.value,
long) or self.value.is_integer(): # dont print .0
return Js(unicode(int(self.value)))
return Js(unicode(self.value)) # accurate enough
return Js(unicode(js_dtoa(self.value)))
elif typ == 'String':
return self
else: #object
@@ -1046,7 +1039,7 @@ def PyJsComma(a, b):
return b
from .internals.simplex import JsException as PyJsException
from .internals.simplex import JsException as PyJsException, js_dtoa
import pyjsparser
pyjsparser.parser.ENABLE_JS2PY_ERRORS = lambda msg: MakeError('SyntaxError', msg)
@@ -116,10 +116,12 @@ def eval_js(js):
def eval_js6(js):
"""Just like eval_js but with experimental support for js6 via babel."""
return eval_js(js6_to_js5(js))
def translate_js6(js):
"""Just like translate_js but with experimental support for js6 via babel."""
return translate_js(js6_to_js5(js))
@@ -3,15 +3,19 @@ import re
import datetime
from desc import *
from simplex import *
from conversions import *
import six
from pyjsparser import PyJsParser
from itertools import izip
from .desc import *
from .simplex import *
from .conversions import *
from pyjsparser import PyJsParser
import six
if six.PY2:
from itertools import izip
else:
izip = zip
from conversions import *
from simplex import *
def Type(obj):
@@ -1,8 +1,8 @@
from code import Code
from simplex import MakeError
from opcodes import *
from operations import *
from trans_utils import *
from .code import Code
from .simplex import MakeError
from .opcodes import *
from .operations import *
from .trans_utils import *
SPECIAL_IDENTIFIERS = {'true', 'false', 'this'}
@@ -465,10 +465,11 @@ class ByteCodeGenerator:
self.emit('LOAD_OBJECT', tuple(data))
def Program(self, body, **kwargs):
old_tape_len = len(self.exe.tape)
self.emit('LOAD_UNDEFINED')
self.emit(body)
# add function tape !
self.exe.tape = self.function_declaration_tape + self.exe.tape
self.exe.tape = self.exe.tape[:old_tape_len] + self.function_declaration_tape + self.exe.tape[old_tape_len:]
def Pyimport(self, imp, **kwargs):
raise NotImplementedError(
@@ -735,17 +736,17 @@ def main():
#
# }
a.emit(d)
print a.declared_vars
print a.exe.tape
print len(a.exe.tape)
print(a.declared_vars)
print(a.exe.tape)
print(len(a.exe.tape))
a.exe.compile()
def log(this, args):
print args[0]
print(args[0])
return 999
print a.exe.run(a.exe.space.GlobalObj)
print(a.exe.run(a.exe.space.GlobalObj))
if __name__ == '__main__':
@@ -1,16 +1,17 @@
from opcodes import *
from space import *
from base import *
from .opcodes import *
from .space import *
from .base import *
class Code:
'''Can generate, store and run sequence of ops representing js code'''
def __init__(self, is_strict=False):
def __init__(self, is_strict=False, debug_mode=False):
self.tape = []
self.compiled = False
self.label_locs = None
self.is_strict = is_strict
self.debug_mode = debug_mode
self.contexts = []
self.current_ctx = None
@@ -22,6 +23,10 @@ class Code:
self.GLOBAL_THIS = None
self.space = None
# dbg
self.ctx_depth = 0
def get_new_label(self):
self._label_count += 1
return self._label_count
@@ -74,21 +79,35 @@ class Code:
# 0=normal, 1=return, 2=jump_outside, 3=errors
# execute_fragment_under_context returns:
# (return_value, typ, return_value/jump_loc/py_error)
# ctx.stack must be len 1 and its always empty after the call.
# IMPARTANT: It is guaranteed that the length of the ctx.stack is unchanged.
'''
old_curr_ctx = self.current_ctx
self.ctx_depth += 1
old_stack_len = len(ctx.stack)
old_ret_len = len(self.return_locs)
old_ctx_len = len(self.contexts)
try:
self.current_ctx = ctx
return self._execute_fragment_under_context(
ctx, start_label, end_label)
except JsException as err:
# undo the things that were put on the stack (if any)
# don't worry, I know the recovery is possible through try statement and for this reason try statement
# has its own context and stack so it will not delete the contents of the outer stack
del ctx.stack[:]
if self.debug_mode:
self._on_fragment_exit("js errors")
# undo the things that were put on the stack (if any) to ensure a proper error recovery
del ctx.stack[old_stack_len:]
del self.return_locs[old_ret_len:]
del self.contexts[old_ctx_len :]
return undefined, 3, err
finally:
self.ctx_depth -= 1
self.current_ctx = old_curr_ctx
assert old_stack_len == len(ctx.stack)
def _get_dbg_indent(self):
return self.ctx_depth * ' '
def _on_fragment_exit(self, mode):
print(self._get_dbg_indent() + 'ctx exit (%s)' % mode)
def _execute_fragment_under_context(self, ctx, start_label, end_label):
start, end = self.label_locs[start_label], self.label_locs[end_label]
@@ -97,16 +116,20 @@ class Code:
entry_level = len(self.contexts)
# for e in self.tape[start:end]:
# print e
if self.debug_mode:
print(self._get_dbg_indent() + 'ctx entry (from:%d, to:%d)' % (start, end))
while loc < len(self.tape):
#print loc, self.tape[loc]
if len(self.contexts) == entry_level and loc >= end:
if self.debug_mode:
self._on_fragment_exit('normal')
assert loc == end
assert len(ctx.stack) == (
1 + initial_len), 'Stack change must be equal to +1!'
delta_stack = len(ctx.stack) - initial_len
assert delta_stack == +1, 'Stack change must be equal to +1! got %d' % delta_stack
return ctx.stack.pop(), 0, None # means normal return
# execute instruction
if self.debug_mode:
print(self._get_dbg_indent() + str(loc), self.tape[loc])
status = self.tape[loc].eval(ctx)
# check status for special actions
@@ -116,9 +139,10 @@ class Code:
if len(self.contexts) == entry_level:
# check if jumped outside of the fragment and break if so
if not start <= loc < end:
assert len(ctx.stack) == (
1 + initial_len
), 'Stack change must be equal to +1!'
if self.debug_mode:
self._on_fragment_exit('jump outside loc:%d label:%d' % (loc, status))
delta_stack = len(ctx.stack) - initial_len
assert delta_stack == +1, 'Stack change must be equal to +1! got %d' % delta_stack
return ctx.stack.pop(), 2, status # jump outside
continue
@@ -137,7 +161,10 @@ class Code:
# return: (None, None)
else:
if len(self.contexts) == entry_level:
assert len(ctx.stack) == 1 + initial_len
if self.debug_mode:
self._on_fragment_exit('return')
delta_stack = len(ctx.stack) - initial_len
assert delta_stack == +1, 'Stack change must be equal to +1! got %d' % delta_stack
return undefined, 1, ctx.stack.pop(
) # return signal
return_value = ctx.stack.pop()
@@ -149,6 +176,8 @@ class Code:
continue
# next instruction
loc += 1
if self.debug_mode:
self._on_fragment_exit('internal error - unexpected end of tape, will crash')
assert False, 'Remember to add NOP at the end!'
def run(self, ctx, starting_loc=0):
@@ -156,7 +185,8 @@ class Code:
self.current_ctx = ctx
while loc < len(self.tape):
# execute instruction
#print loc, self.tape[loc]
if self.debug_mode:
print(loc, self.tape[loc])
status = self.tape[loc].eval(ctx)
# check status for special actions
@@ -42,6 +42,7 @@ def executable_code(code_str, space, global_context=True):
space.byte_generator.emit('LABEL', skip)
space.byte_generator.emit('NOP')
space.byte_generator.restore_state()
space.byte_generator.exe.compile(
start_loc=old_tape_len
) # dont read the code from the beginning, dont be stupid!
@@ -71,5 +72,5 @@ def _eval(this, args):
def log(this, args):
print ' '.join(map(to_string, args))
print(' '.join(map(to_string, args)))
return undefined
@@ -1,6 +1,6 @@
from __future__ import unicode_literals
# Type Conversions. to_type. All must return PyJs subclass instance
from simplex import *
from .simplex import *
def to_primitive(self, hint=None):
@@ -73,14 +73,7 @@ def to_string(self):
elif typ == 'Boolean':
return 'true' if self else 'false'
elif typ == 'Number': # or self.Class=='Number':
if is_nan(self):
return 'NaN'
elif is_infinity(self):
sign = '-' if self < 0 else ''
return sign + 'Infinity'
elif int(self) == self: # integer value!
return unicode(int(self))
return unicode(self) # todo make it print exactly like node.js
return js_dtoa(self)
else: # object
return to_string(to_primitive(self, 'String'))
@@ -1,29 +1,22 @@
from __future__ import unicode_literals
from base import Scope
from func_utils import *
from conversions import *
from .base import Scope
from .func_utils import *
from .conversions import *
import six
from prototypes.jsboolean import BooleanPrototype
from prototypes.jserror import ErrorPrototype
from prototypes.jsfunction import FunctionPrototype
from prototypes.jsnumber import NumberPrototype
from prototypes.jsobject import ObjectPrototype
from prototypes.jsregexp import RegExpPrototype
from prototypes.jsstring import StringPrototype
from prototypes.jsarray import ArrayPrototype
import prototypes.jsjson as jsjson
import prototypes.jsutils as jsutils
from .prototypes.jsboolean import BooleanPrototype
from .prototypes.jserror import ErrorPrototype
from .prototypes.jsfunction import FunctionPrototype
from .prototypes.jsnumber import NumberPrototype
from .prototypes.jsobject import ObjectPrototype
from .prototypes.jsregexp import RegExpPrototype
from .prototypes.jsstring import StringPrototype
from .prototypes.jsarray import ArrayPrototype
from .prototypes import jsjson
from .prototypes import jsutils
from .constructors import jsnumber, jsstring, jsarray, jsboolean, jsregexp, jsmath, jsobject, jsfunction, jsconsole
from constructors import jsnumber
from constructors import jsstring
from constructors import jsarray
from constructors import jsboolean
from constructors import jsregexp
from constructors import jsmath
from constructors import jsobject
from constructors import jsfunction
from constructors import jsconsole
def fill_proto(proto, proto_class, space):
@@ -155,7 +148,10 @@ def fill_space(space, byte_generator):
j = easy_func(creator, space)
j.name = unicode(typ)
j.prototype = space.ERROR_TYPES[typ]
set_protected(j, 'prototype', space.ERROR_TYPES[typ])
set_non_enumerable(space.ERROR_TYPES[typ], 'constructor', j)
def new_create(args, space):
message = get_arg(args, 0)
@@ -178,6 +174,7 @@ def fill_space(space, byte_generator):
setattr(space, err_type_name + u'Prototype', extra_err)
error_constructors[err_type_name] = construct_constructor(
err_type_name)
assert space.TypeErrorPrototype is not None
# RegExp
@@ -1,5 +1,5 @@
from simplex import *
from conversions import *
from .simplex import *
from .conversions import *
import six
if six.PY3:
@@ -1,5 +1,5 @@
from operations import *
from base import get_member, get_member_dot, PyJsFunction, Scope
from .operations import *
from .base import get_member, get_member_dot, PyJsFunction, Scope
class OP_CODE(object):
@@ -1,6 +1,6 @@
from __future__ import unicode_literals
from simplex import *
from conversions import *
from .simplex import *
from .conversions import *
# ------------------------------------------------------------------------------
# Unary operations
@@ -4,7 +4,7 @@ from __future__ import unicode_literals
import re
from ..conversions import *
from ..func_utils import *
from jsregexp import RegExpExec
from .jsregexp import RegExpExec
DIGS = set(u'0123456789')
WHITE = u"\u0009\u000A\u000B\u000C\u000D\u0020\u00A0\u1680\u180E\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007\u2008\u2009\u200A\u2028\u2029\u202F\u205F\u3000\uFEFF"
@@ -1,11 +1,9 @@
import pyjsparser
from space import Space
import fill_space
from byte_trans import ByteCodeGenerator
from code import Code
from simplex import MakeError
import sys
sys.setrecursionlimit(100000)
from .space import Space
from . import fill_space
from .byte_trans import ByteCodeGenerator
from .code import Code
from .simplex import *
pyjsparser.parser.ENABLE_JS2PY_ERRORS = lambda msg: MakeError(u'SyntaxError', unicode(msg))
@@ -16,8 +14,8 @@ def get_js_bytecode(js):
a.emit(d)
return a.exe.tape
def eval_js_vm(js):
a = ByteCodeGenerator(Code())
def eval_js_vm(js, debug=False):
a = ByteCodeGenerator(Code(debug_mode=debug))
s = Space()
a.exe.space = s
s.exe = a.exe
@@ -26,7 +24,10 @@ def eval_js_vm(js):
a.emit(d)
fill_space.fill_space(s, a)
# print a.exe.tape
if debug:
from pprint import pprint
pprint(a.exe.tape)
print()
a.exe.compile()
return a.exe.run(a.exe.space.GlobalObj)
@@ -1,6 +1,10 @@
from __future__ import unicode_literals
import six
if six.PY3:
basestring = str
long = int
xrange = range
unicode = str
#Undefined
class PyJsUndefined(object):
@@ -75,7 +79,7 @@ def is_callable(self):
def is_infinity(self):
return self == float('inf') or self == -float('inf')
return self == Infinity or self == -Infinity
def is_nan(self):
@@ -114,7 +118,7 @@ class JsException(Exception):
return self.mes.to_string().value
else:
if self.throw is not None:
from conversions import to_string
from .conversions import to_string
return to_string(self.throw)
else:
return self.typ + ': ' + self.message
@@ -131,3 +135,26 @@ def value_from_js_exception(js_exception, space):
return js_exception.throw
else:
return space.NewError(js_exception.typ, js_exception.message)
def js_dtoa(number):
if is_nan(number):
return u'NaN'
elif is_infinity(number):
if number > 0:
return u'Infinity'
return u'-Infinity'
elif number == 0.:
return u'0'
elif abs(number) < 1e-6 or abs(number) >= 1e21:
frac, exponent = unicode(repr(float(number))).split('e')
# Remove leading zeros from the exponent.
exponent = int(exponent)
return frac + ('e' if exponent < 0 else 'e+') + unicode(exponent)
elif abs(number) < 1e-4: # python starts to return exp notation while we still want the prec
frac, exponent = unicode(repr(float(number))).split('e-')
base = u'0.' + u'0' * (int(exponent) - 1) + frac.lstrip('-').replace('.', '')
return base if number > 0. else u'-' + base
elif isinstance(number, long) or number.is_integer(): # dont print .0
return unicode(int(number))
return unicode(repr(number)) # python representation should be equivalent.
@@ -1,5 +1,5 @@
from base import *
from simplex import *
from .base import *
from .simplex import *
class Space(object):
@@ -1,3 +1,10 @@
import six
if six.PY3:
basestring = str
long = int
xrange = range
unicode = str
def to_key(literal_or_identifier):
''' returns string representation of this object'''
if literal_or_identifier['type'] == 'Identifier':
@@ -6,8 +6,6 @@ if six.PY3:
xrange = range
unicode = str
# todo fix apply and bind
class FunctionPrototype:
def toString():
@@ -41,6 +39,7 @@ class FunctionPrototype:
return this.call(obj, args)
def bind(thisArg):
arguments_ = arguments
target = this
if not target.is_callable():
raise this.MakeError(
@@ -48,5 +47,5 @@ class FunctionPrototype:
if len(arguments) <= 1:
args = ()
else:
args = tuple([arguments[e] for e in xrange(1, len(arguments))])
args = tuple([arguments_[e] for e in xrange(1, len(arguments_))])
return this.PyJsBoundFunction(target, thisArg, args)
@@ -345,7 +345,7 @@ def BlockStatement(type, body):
body) # never returns empty string! In the worst case returns pass\n
def ExpressionStatement(type, expression, **ommit):
def ExpressionStatement(type, expression):
return trans(expression) + '\n' # end expression space with new line
@@ -43,6 +43,8 @@ python -c "import logging; logging.basicConfig(level=logging.DEBUG); logging.get
# subscenter:list
python -c "import logging; logging.basicConfig(level=logging.DEBUG); logging.getLogger('rebulk').setLevel(logging.WARNING); import subliminal_patch, subliminal; subliminal.region.configure('dogpile.cache.memory'); from subliminal_patch.core import SZProviderPool; from babelfish import Language; from subliminal.core import scan_video; print SZProviderPool(providers=['subscenter'], )['subscenter'].list_subtitles(scan_video('FULL_PATH'), languages=[Language('heb')])"
# subscene:list
python -c "import logging; logging.basicConfig(level=logging.DEBUG); logging.getLogger('rebulk').setLevel(logging.WARNING); import subliminal_patch, subliminal; subliminal.region.configure('dogpile.cache.memory'); from subliminal_patch.core import SZProviderPool; from subzero.language import Language; from subzero.video import parse_video; SZProviderPool(providers=['subscene'], provider_configs={'subscene': {'username': 'USERNAME', 'password': 'PASSWORD'}})['subscene'].list_subtitles(parse_video('FILENAME', {}, {'type': 'episode'}, dry_run=True), languages=[Language('eng')])"
# refining
python -c "import logging; logging.basicConfig(level=logging.DEBUG); logging.getLogger('rebulk').setLevel(logging.WARNING); import os; os.environ['U1pfT01EQl9LRVk'] = '789CF30DAC2C8B0AF433F5C9AD34290A712DF30D7135F12D0FB3E502006FDE081E'; import subliminal_patch, subliminal; subliminal.region.configure('dogpile.cache.memory'); from subzero.video import parse_video, refine_video; video = parse_video('FILE_NAME', {'type': 'episode'}, dry_run=True); print refine_video(video)"
+10
View File
@@ -163,3 +163,13 @@ class Pysubs2CLI(object):
elif args.transform_framerate is not None:
in_fps, out_fps = args.transform_framerate
subs.transform_framerate(in_fps, out_fps)
def __main__():
cli = Pysubs2CLI()
rv = cli(sys.argv[1:])
sys.exit(rv)
if __name__ == "__main__":
__main__()
+3 -1
View File
@@ -17,12 +17,14 @@ class Color(_Color):
return _Color.__new__(cls, r, g, b, a)
#: Version of the pysubs2 library.
VERSION = "0.2.1"
VERSION = "0.2.3"
PY3 = sys.version_info.major == 3
if PY3:
text_type = str
binary_string_type = bytes
else:
text_type = unicode
binary_string_type = str
@@ -12,3 +12,6 @@ class UnknownFormatIdentifierError(Pysubs2Error):
class FormatAutodetectionError(Pysubs2Error):
"""Subtitle format is ambiguous or unknown."""
class ContentNotUsable(Pysubs2Error):
"""Current content not usable for specified format"""
+1 -3
View File
@@ -3,7 +3,7 @@ from .microdvd import MicroDVDFormat
from .subrip import SubripFormat
from .jsonformat import JSONFormat
from .substation import SubstationFormat
from .txt_generic import TXTGenericFormat, MPL2Format
from .mpl2 import MPL2Format
from .exceptions import *
#: Dict mapping file extensions to format identifiers.
@@ -13,7 +13,6 @@ FILE_EXTENSION_TO_FORMAT_IDENTIFIER = {
".ssa": "ssa",
".sub": "microdvd",
".json": "json",
".txt": "txt_generic",
}
#: Dict mapping format identifiers to implementations (FormatBase subclasses).
@@ -23,7 +22,6 @@ FORMAT_IDENTIFIER_TO_FORMAT_CLASS = {
"ssa": SubstationFormat,
"microdvd": MicroDVDFormat,
"json": JSONFormat,
"txt_generic": TXTGenericFormat,
"mpl2": MPL2Format,
}
@@ -2,44 +2,48 @@
from __future__ import print_function, division, unicode_literals
import re
from numbers import Number
from pysubs2.time import times_to_ms
from .time import times_to_ms
from .formatbase import FormatBase
from .ssaevent import SSAEvent
from .ssastyle import SSAStyle
# thanks to http://otsaloma.io/gaupol/doc/api/aeidon.files.mpl2_source.html
MPL2_FORMAT = re.compile(r"^(?um)\[(-?\d+)\]\[(-?\d+)\](.*?)$")
class TXTGenericFormat(FormatBase):
@classmethod
def guess_format(cls, text):
if MPL2_FORMAT.match(text):
return "mpl2"
MPL2_FORMAT = re.compile(r"^(?um)\[(-?\d+)\]\[(-?\d+)\](.*)")
class MPL2Format(FormatBase):
@classmethod
def guess_format(cls, text):
return TXTGenericFormat.guess_format(text)
if MPL2_FORMAT.search(text):
return "mpl2"
@classmethod
def from_file(cls, subs, fp, format_, **kwargs):
def prepare_text(lines):
out = []
for s in lines.split("|"):
s = s.strip()
if s.startswith("/"):
out.append(r"{\i1}%s{\i0}" % s[1:])
continue
# line beginning with '/' is in italics
s = r"{\i1}%s{\i0}" % s[1:].strip()
out.append(s)
return "\n".join(out)
return "\\N".join(out)
subs.events = [SSAEvent(start=times_to_ms(s=float(start) / 10), end=times_to_ms(s=float(end) / 10),
text=prepare_text(text)) for start, end, text in MPL2_FORMAT.findall(fp.getvalue())]
@classmethod
def to_file(cls, subs, fp, format_, **kwargs):
raise NotImplemented
# TODO handle italics
for line in subs:
if line.is_comment:
continue
print("[{start}][{end}] {text}".format(start=int(line.start // 100),
end=int(line.end // 100),
text=line.plaintext.replace("\n", "|")),
file=fp)
@@ -41,6 +41,7 @@ class SSAStyle(object):
self.italic = False #: Italic
self.underline = False #: Underline (ASS only)
self.strikeout = False #: Strikeout (ASS only)
self.drawing = False #: Drawing (ASS only, see http://docs.aegisub.org/3.1/ASS_Tags/#drawing-tags
self.scalex = 100.0 #: Horizontal scaling (ASS only)
self.scaley = 100.0 #: Vertical scaling (ASS only)
self.spacing = 0.0 #: Letter spacing (ASS only)
@@ -78,7 +79,7 @@ class SSAStyle(object):
s += "%rpx " % self.fontsize
if self.bold: s += "bold "
if self.italic: s += "italic "
s += "'%s'>" % self.fontname
s += "{!r}>".format(self.fontname)
if not PY3: s = s.encode("utf-8")
return s
+15 -2
View File
@@ -5,6 +5,7 @@ from .formatbase import FormatBase
from .ssaevent import SSAEvent
from .ssastyle import SSAStyle
from .substation import parse_tags
from .exceptions import ContentNotUsable
from .time import ms_to_times, make_time, TIMESTAMP, timestamp_to_ms
#: Largest timestamp allowed in SubRip, ie. 99:59:59,999.
@@ -46,8 +47,16 @@ class SubripFormat(FormatBase):
following_lines[-1].append(line)
def prepare_text(lines):
# Handle the "happy" empty subtitle case, which is timestamp line followed by blank line(s)
# followed by number line and timestamp line of the next subtitle. Fixes issue #11.
if (len(lines) >= 2
and all(re.match("\s*$", line) for line in lines[:-1])
and re.match("\s*\d+\s*$", lines[-1])):
return ""
# Handle the general case.
s = "".join(lines).strip()
s = re.sub(r"\n* *\d+ *$", "", s) # strip number of next subtitle
s = re.sub(r"\n+ *\d+ *$", "", s) # strip number of next subtitle
s = re.sub(r"< *i *>", r"{\i1}", s)
s = re.sub(r"< */ *i *>", r"{\i0}", s)
s = re.sub(r"< *s *>", r"{\s1}", s)
@@ -73,6 +82,7 @@ class SubripFormat(FormatBase):
if sty.italic: fragment = "<i>%s</i>" % fragment
if sty.underline: fragment = "<u>%s</u>" % fragment
if sty.strikeout: fragment = "<s>%s</s>" % fragment
if sty.drawing: raise ContentNotUsable
body.append(fragment)
return re.sub("\n+", "\n", "".join(body).strip())
@@ -82,7 +92,10 @@ class SubripFormat(FormatBase):
for i, line in enumerate(visible_lines, 1):
start = ms_to_timestamp(line.start)
end = ms_to_timestamp(line.end)
text = prepare_text(line.text, subs.styles.get(line.style, SSAStyle.DEFAULT_STYLE))
try:
text = prepare_text(line.text, subs.styles.get(line.style, SSAStyle.DEFAULT_STYLE))
except ContentNotUsable:
continue
print("%d" % i, file=fp) # Python 2.7 compat
print(start, "-->", end, file=fp)
+22 -14
View File
@@ -4,7 +4,7 @@ from numbers import Number
from .formatbase import FormatBase
from .ssaevent import SSAEvent
from .ssastyle import SSAStyle
from .common import text_type, Color
from .common import text_type, Color, PY3, binary_string_type
from .time import make_time, ms_to_times, timestamp_to_ms, TIMESTAMP
SSA_ALIGNMENT = (1, 2, 3, 9, 10, 11, 5, 6, 7)
@@ -110,7 +110,7 @@ def parse_tags(text, style=SSAStyle.DEFAULT_STYLE, styles={}):
def apply_overrides(all_overrides):
s = style.copy()
for tag in re.findall(r"\\[ibus][10]|\\r[a-zA-Z_0-9 ]*", all_overrides):
for tag in re.findall(r"\\[ibusp][0-9]|\\r[a-zA-Z_0-9 ]*", all_overrides):
if tag == r"\r":
s = style.copy() # reset to original line style
elif tag.startswith(r"\r"):
@@ -122,6 +122,13 @@ def parse_tags(text, style=SSAStyle.DEFAULT_STYLE, styles={}):
elif "b" in tag: s.bold = "1" in tag
elif "u" in tag: s.underline = "1" in tag
elif "s" in tag: s.strikeout = "1" in tag
elif "p" in tag:
try:
scale = int(tag[2:])
except (ValueError, IndexError):
continue
s.drawing = scale > 0
return s
overrides = SSAEvent.OVERRIDE_SEQUENCE.findall(text)
@@ -150,14 +157,7 @@ class SubstationFormat(FormatBase):
if format_ == "ass":
return ass_rgba_to_color(v)
else:
try:
return ssa_rgb_to_color(v)
except ValueError:
try:
return ass_rgba_to_color(v)
except:
return Color(255, 255, 255, 0)
return ssa_rgb_to_color(v)
elif f in {"bold", "underline", "italic", "strikeout"}:
return v == "-1"
elif f in {"borderstyle", "encoding", "marginl", "marginr", "marginv", "layer", "alphalevel"}:
@@ -229,7 +229,7 @@ class SubstationFormat(FormatBase):
for k, v in subs.aegisub_project.items():
print(k, v, sep=": ", file=fp)
def field_to_string(f, v):
def field_to_string(f, v, line):
if f in {"start", "end"}:
return ms_to_timestamp(v)
elif f == "marked":
@@ -240,23 +240,31 @@ class SubstationFormat(FormatBase):
return "-1" if v else "0"
elif isinstance(v, (text_type, Number)):
return text_type(v)
elif not PY3 and isinstance(v, binary_string_type):
# A convenience feature, see issue #12 - accept non-unicode strings
# when they are ASCII; this is useful in Python 2, especially for non-text
# fields like style names, where requiring Unicode type seems too stringent
if all(ord(c) < 128 for c in v):
return text_type(v)
else:
raise TypeError("Encountered binary string with non-ASCII codepoint in SubStation field {!r} for line {!r} - please use unicode string instead of str".format(f, line))
elif isinstance(v, Color):
if format_ == "ass":
return color_to_ass_rgba(v)
else:
return color_to_ssa_rgb(v)
else:
raise TypeError("Unexpected type when writing a SubStation field")
raise TypeError("Unexpected type when writing a SubStation field {!r} for line {!r}".format(f, line))
print("\n[V4+ Styles]" if format_ == "ass" else "\n[V4 Styles]", file=fp)
print(STYLE_FORMAT_LINE[format_], file=fp)
for name, sty in subs.styles.items():
fields = [field_to_string(f, getattr(sty, f)) for f in STYLE_FIELDS[format_]]
fields = [field_to_string(f, getattr(sty, f), sty) for f in STYLE_FIELDS[format_]]
print("Style: %s" % name, *fields, sep=",", file=fp)
print("\n[Events]", file=fp)
print(EVENT_FORMAT_LINE[format_], file=fp)
for ev in subs.events:
fields = [field_to_string(f, getattr(ev, f)) for f in EVENT_FIELDS[format_]]
fields = [field_to_string(f, getattr(ev, f), ev) for f in EVENT_FIELDS[format_]]
print(ev.type, end=": ", file=fp)
print(*fields, sep=",", file=fp)
@@ -27,3 +27,8 @@ class ServiceUnavailable(ProviderError):
class DownloadLimitExceeded(ProviderError):
"""Exception raised by providers when download limit is exceeded."""
pass
class DownloadLimitPerDayExceeded(ProviderError):
"""Exception raised by providers when download limit is exceeded."""
pass
@@ -94,7 +94,8 @@ provider_manager = RegistrableExtensionManager('subliminal.providers', [
'podnapisi = subliminal.providers.podnapisi:PodnapisiProvider',
'shooter = subliminal.providers.shooter:ShooterProvider',
'thesubdb = subliminal.providers.thesubdb:TheSubDBProvider',
'tvsubtitles = subliminal.providers.tvsubtitles:TVsubtitlesProvider'
'tvsubtitles = subliminal.providers.tvsubtitles:TVsubtitlesProvider',
'screwzira = subliminal.providers.screwzira:ScrewZiraProvider'
])
#: Refiner manager
@@ -258,4 +258,4 @@ def fix_line_ending(content):
:rtype: bytes
"""
return content.replace(b'\r\n', b'\n').replace(b'\r', b'\n')
return content.replace(b'\r\n', b'\n')
@@ -12,6 +12,13 @@ from_subscene = {
'Malay': 'msa', 'Pashto': 'pus', 'Punjabi': 'pan', 'Swahili': 'swa'
}
from_subscene_with_country = {
'Brazillian Portuguese': ('por', 'BR')
}
to_subscene_with_country = {val: key for key, val in from_subscene_with_country.items()}
to_subscene = {v: k for k, v in from_subscene.items()}
exact_languages_alpha3 = [
@@ -34,12 +41,12 @@ language_ids = {
'mkd': 48, 'mal': 64, 'mni': 65, 'mon': 72, 'pus': 67, 'pol': 31,
'por': 32, 'pan': 66, 'rus': 34, 'srp': 35, 'sin': 58, 'slk': 36,
'slv': 37, 'som': 70, 'tgl': 53, 'tam': 59, 'tel': 63, 'tha': 40,
'tur': 41, 'ukr': 56, 'urd': 42, 'yor': 71
'tur': 41, 'ukr': 56, 'urd': 42, 'yor': 71, 'pt-BR': 4
}
# TODO: specify codes for unspecified_languages
unspecified_languages = [
'Big 5 code', 'Brazillian Portuguese', 'Bulgarian/ English',
'Big 5 code', 'Bulgarian/ English',
'Chinese BG code', 'Dutch/ English', 'English/ German',
'Hungarian/ English', 'Rohingya'
]
@@ -50,6 +57,8 @@ alpha3_of_code = {l.name: l.alpha3 for l in supported_languages}
supported_languages.update({Language(l) for l in to_subscene})
supported_languages.update({Language(lang, cr) for lang, cr in to_subscene_with_country})
class SubsceneConverter(LanguageReverseConverter):
codes = {l.name for l in supported_languages}
@@ -61,9 +70,15 @@ class SubsceneConverter(LanguageReverseConverter):
if alpha3 in to_subscene:
return to_subscene[alpha3]
if (alpha3, country) in to_subscene_with_country:
return to_subscene_with_country[(alpha3, country)]
raise ConfigurationError('Unsupported language for subscene: %s, %s, %s' % (alpha3, country, script))
def reverse(self, code):
if code in from_subscene_with_country:
return from_subscene_with_country[code]
if code in from_subscene:
return (from_subscene[code],)
@@ -27,16 +27,6 @@ class TitloviConverter(LanguageReverseConverter):
}
self.codes = set(self.from_titlovi.keys())
# temporary fix, should be removed as soon as API is used
self.lang_from_countrycode = {'ba': ('bos',),
'en': ('eng',),
'hr': ('hrv',),
'mk': ('mkd',),
'rs': ('srp',),
'rsc': ('srp', None, 'Cyrl'),
'si': ('slv',)
}
def convert(self, alpha3, country=None, script=None):
if (alpha3, country, script) in self.to_titlovi:
return self.to_titlovi[(alpha3, country, script)]
@@ -49,9 +39,5 @@ class TitloviConverter(LanguageReverseConverter):
if titlovi in self.from_titlovi:
return self.from_titlovi[titlovi]
# temporary fix, should be removed as soon as API is used
if titlovi in self.lang_from_countrycode:
return self.lang_from_countrycode[titlovi]
raise ConfigurationError('Unsupported language number for titlovi: %s' % titlovi)
@@ -30,7 +30,7 @@ from subliminal.core import guessit, ProviderPool, io, is_windows_special_path,
ThreadPoolExecutor, check_video
from subliminal_patch.exceptions import TooManyRequests, APIThrottled
from subzero.language import Language
from subzero.language import Language, ENDSWITH_LANGUAGECODE_RE, FULL_LANGUAGE_LIST
from scandir import scandir, scandir_generic as _scandir_generic
logger = logging.getLogger(__name__)
@@ -62,7 +62,7 @@ class SZProviderPool(ProviderPool):
def __init__(self, providers=None, provider_configs=None, blacklist=None, throttle_callback=None,
pre_download_hook=None, post_download_hook=None, language_hook=None):
#: Name of providers to use
self.providers = providers or provider_registry.names()
self.providers = providers
#: Provider configuration
self.provider_configs = provider_configs or {}
@@ -108,10 +108,12 @@ class SZProviderPool(ProviderPool):
try:
logger.info('Terminating provider %s', name)
self.initialized_providers[name].terminate()
except (requests.Timeout, socket.timeout):
except (requests.Timeout, socket.timeout) as e:
logger.error('Provider %r timed out, improperly terminated', name)
except:
self.throttle_callback(name, e)
except Exception as e:
logger.exception('Provider %r terminated unexpectedly', name)
self.throttle_callback(name, e)
del self.initialized_providers[name]
@@ -183,15 +185,13 @@ class SZProviderPool(ProviderPool):
return out
except (requests.Timeout, socket.timeout):
logger.error('Provider %r timed out', provider)
except (TooManyRequests, DownloadLimitExceeded, ServiceUnavailable, APIThrottled), e:
except (requests.Timeout, socket.timeout) as e:
logger.exception('Provider %r timed out', provider)
self.throttle_callback(provider, e)
return
except:
except Exception as e:
logger.exception('Unexpected error in provider %r: %s', provider, traceback.format_exc())
self.throttle_callback(provider, e)
def list_subtitles(self, video, languages):
"""List subtitles.
@@ -266,10 +266,11 @@ class SZProviderPool(ProviderPool):
requests.exceptions.ProxyError,
requests.exceptions.SSLError,
requests.Timeout,
socket.timeout):
logger.error('Provider %r connection error', subtitle.provider_name)
socket.timeout) as e:
logger.exception('Provider %r connection error', subtitle.provider_name)
self.throttle_callback(subtitle.provider_name, e)
except ResponseNotReady:
except ResponseNotReady as e:
logger.error('Provider %r response error, reinitializing', subtitle.provider_name)
try:
self[subtitle.provider_name].terminate()
@@ -277,20 +278,17 @@ class SZProviderPool(ProviderPool):
except:
logger.error('Provider %r reinitialization error: %s', subtitle.provider_name,
traceback.format_exc())
self.throttle_callback(subtitle.provider_name, e)
except rarfile.BadRarFile:
logger.error('Malformed RAR file from provider %r, skipping subtitle.', subtitle.provider_name)
logger.debug("RAR Traceback: %s", traceback.format_exc())
return False
except (TooManyRequests, DownloadLimitExceeded, ServiceUnavailable, APIThrottled), e:
self.throttle_callback(subtitle.provider_name, e)
self.discarded_providers.add(subtitle.provider_name)
return False
except:
except Exception as e:
logger.exception('Unexpected error in provider %r, Traceback: %s', subtitle.provider_name,
traceback.format_exc())
self.throttle_callback(subtitle.provider_name, e)
self.discarded_providers.add(subtitle.provider_name)
return False
@@ -309,7 +307,8 @@ class SZProviderPool(ProviderPool):
logger.error('Invalid subtitle')
return False
subtitle.normalize()
if not os.environ.get("SZ_KEEP_ENCODING", False):
subtitle.normalize()
return True
@@ -360,15 +359,16 @@ class SZProviderPool(ProviderPool):
orig_matches = matches.copy()
logger.debug('%r: Found matches %r', s, matches)
score, score_without_hash = compute_score(matches, s, video, hearing_impaired=use_hearing_impaired)
unsorted_subtitles.append(
(s, compute_score(matches, s, video, hearing_impaired=use_hearing_impaired), matches, orig_matches))
(s, score, score_without_hash, matches, orig_matches))
# sort subtitles by score
scored_subtitles = sorted(unsorted_subtitles, key=operator.itemgetter(1), reverse=True)
scored_subtitles = sorted(unsorted_subtitles, key=operator.itemgetter(1, 2), reverse=True)
# download best subtitles, falling back on the next on error
downloaded_subtitles = []
for subtitle, score, matches, orig_matches in scored_subtitles:
for subtitle, score, score_without_hash, matches, orig_matches in scored_subtitles:
# check score
if score < min_score:
logger.info('%r: Score %d is below min_score (%d)', subtitle, score, min_score)
@@ -472,7 +472,7 @@ if is_windows_special_path:
SZAsyncProviderPool = SZProviderPool
def scan_video(path, dont_use_actual_file=False, hints=None, providers=None, skip_hashing=False):
def scan_video(path, dont_use_actual_file=False, hints=None, providers=None, skip_hashing=False, hash_from=None):
"""Scan a video from a `path`.
patch:
@@ -537,28 +537,38 @@ def scan_video(path, dont_use_actual_file=False, hints=None, providers=None, ski
video.alternative_titles.append(alt_guess["title"])
logger.debug("Adding alternative title: %s", alt_guess["title"])
if dont_use_actual_file:
if dont_use_actual_file and not hash_from:
return video
# size and hashes
if not skip_hashing:
video.size = os.path.getsize(path)
hash_path = hash_from or path
video.size = os.path.getsize(hash_path)
if video.size > 10485760:
logger.debug('Size is %d', video.size)
osub_hash = None
if "bsplayer" in providers:
video.hashes['bsplayer'] = osub_hash = hash_opensubtitles(hash_path)
if "opensubtitles" in providers:
video.hashes['opensubtitles'] = hash_opensubtitles(path)
video.hashes['opensubtitles'] = osub_hash = osub_hash or hash_opensubtitles(hash_path)
if "shooter" in providers:
video.hashes['shooter'] = hash_shooter(path)
video.hashes['shooter'] = hash_shooter(hash_path)
if "thesubdb" in providers:
video.hashes['thesubdb'] = hash_thesubdb(path)
video.hashes['thesubdb'] = hash_thesubdb(hash_path)
if "napiprojekt" in providers:
try:
video.hashes['napiprojekt'] = hash_napiprojekt(path)
video.hashes['napiprojekt'] = hash_napiprojekt(hash_path)
except MemoryError:
logger.warning(u"Couldn't compute napiprojekt hash for %s", path)
logger.warning(u"Couldn't compute napiprojekt hash for %s", hash_path)
if "napisy24" in providers:
# Napisy24 uses the same hash as opensubtitles
video.hashes['napisy24'] = osub_hash or hash_opensubtitles(hash_path)
logger.debug('Computed hashes %r', video.hashes)
else:
@@ -567,14 +577,16 @@ def scan_video(path, dont_use_actual_file=False, hints=None, providers=None, ski
return video
def _search_external_subtitles(path, languages=None, only_one=False, scandir_generic=False):
def _search_external_subtitles(path, languages=None, only_one=False, scandir_generic=False, match_strictness="strict"):
dirpath, filename = os.path.split(path)
dirpath = dirpath or '.'
fileroot, fileext = os.path.splitext(filename)
fn_no_ext, fileext = os.path.splitext(filename)
fn_no_ext_lower = fn_no_ext.lower()
subtitles = {}
_scandir = _scandir_generic if scandir_generic else scandir
for entry in _scandir(dirpath):
if not entry.name and not scandir_generic:
if (not entry.name or entry.name in ('\x0c', '$', ',', '\x7f')) and not scandir_generic:
logger.debug('Could not determine the name of the file, retrying with scandir_generic')
return _search_external_subtitles(path, languages, only_one, True)
if not entry.is_file(follow_symlinks=False):
@@ -583,9 +595,11 @@ def _search_external_subtitles(path, languages=None, only_one=False, scandir_gen
p = entry.name
# keep only valid subtitle filenames
if not p.lower().startswith(fileroot.lower()) or not p.lower().endswith(SUBTITLE_EXTENSIONS):
if not p.lower().endswith(SUBTITLE_EXTENSIONS):
continue
# not p.lower().startswith(fileroot.lower()) or not
p_root, p_ext = os.path.splitext(p)
if not INCLUDE_EXOTIC_SUBS and p_ext not in (".srt", ".ass", ".ssa", ".vtt"):
continue
@@ -603,22 +617,34 @@ def _search_external_subtitles(path, languages=None, only_one=False, scandir_gen
if adv_tag:
forced = "forced" in adv_tag
# remove possible language code for matching
p_root_bare = ENDSWITH_LANGUAGECODE_RE.sub(
lambda m: "" if str(m.group(1)).lower() in FULL_LANGUAGE_LIST else m.group(0), p_root)
p_root_lower = p_root_bare.lower()
filename_matches = p_root_lower == fn_no_ext_lower
filename_contains = p_root_lower in fn_no_ext_lower
if not filename_matches:
if match_strictness == "strict" or (match_strictness == "loose" and not filename_contains):
continue
language = None
# extract the potential language code
language_code = p_root[len(fileroot):].replace('_', '-')[1:]
# default language is undefined
language = Language('und')
# attempt to parse
if language_code:
try:
language_code = p_root.rsplit(".", 1)[1].replace('_', '-')
try:
language = Language.fromietf(language_code)
language.forced = forced
except ValueError:
except (ValueError, LanguageReverseError):
logger.error('Cannot parse language code %r', language_code)
language = None
language_code = None
except IndexError:
language_code = None
elif not language_code and only_one:
if not language and not language_code and only_one:
language = Language.rebuild(list(languages)[0], forced=forced)
subtitles[p] = language
@@ -628,7 +654,7 @@ def _search_external_subtitles(path, languages=None, only_one=False, scandir_gen
return subtitles
def search_external_subtitles(path, languages=None, only_one=False):
def search_external_subtitles(path, languages=None, only_one=False, match_strictness="strict"):
"""
wrap original search_external_subtitles function to search multiple paths for one given video
# todo: cleanup and merge with _search_external_subtitles
@@ -649,10 +675,11 @@ def search_external_subtitles(path, languages=None, only_one=False):
if os.path.isdir(os.path.dirname(abspath)):
try:
subtitles.update(_search_external_subtitles(abspath, languages=languages,
only_one=only_one))
only_one=only_one, match_strictness=match_strictness))
except OSError:
subtitles.update(_search_external_subtitles(abspath, languages=languages,
only_one=only_one, scandir_generic=True))
only_one=only_one, match_strictness=match_strictness,
scandir_generic=True))
logger.debug("external subs: found %s", subtitles)
return subtitles
@@ -845,6 +872,9 @@ def save_subtitles(file_path, subtitles, single=False, directory=None, chmod=Non
logger.debug(u"Saving %r to %r", subtitle, subtitle_path)
content = subtitle.get_modified_content(format=format, debug=debug_mods)
if content:
if os.path.exists(subtitle_path):
os.remove(subtitle_path)
with open(subtitle_path, 'w') as f:
f.write(content)
subtitle.storage_path = subtitle_path
@@ -9,3 +9,8 @@ class TooManyRequests(ProviderError):
class APIThrottled(ProviderError):
pass
class ParseResponseError(ProviderError):
"""Exception raised by providers when they are not able to parse the response."""
pass
@@ -1,4 +1,5 @@
# coding=utf-8
import json
from collections import OrderedDict
import certifi
@@ -9,6 +10,8 @@ import logging
import requests
import xmlrpclib
import dns.resolver
import ipaddress
import re
from requests import exceptions
from urllib3.util import connection
@@ -16,7 +19,13 @@ from retry.api import retry_call
from exceptions import APIThrottled
from dogpile.cache.api import NO_VALUE
from subliminal.cache import region
from cfscrape import CloudflareScraper
from subliminal_patch.pitcher import pitchers
from cloudscraper import CloudScraper
try:
import brotli
except:
pass
try:
from urlparse import urlparse
@@ -26,18 +35,8 @@ except ImportError:
from subzero.lib.io import get_viable_encoding
logger = logging.getLogger(__name__)
pem_file = os.path.normpath(os.path.join(os.path.dirname(os.path.realpath(unicode(__file__, get_viable_encoding()))), "..", certifi.where()))
try:
default_ssl_context = ssl.create_default_context(cafile=pem_file)
except AttributeError:
# < Python 2.7.9
default_ssl_context = None
custom_resolver = dns.resolver.Resolver(configure=False)
# 8.8.8.8 is Google's public DNS server
custom_resolver.nameservers = ['8.8.8.8', '1.1.1.1']
pem_file = os.path.normpath(os.path.join(os.path.dirname(os.path.realpath(unicode(__file__, get_viable_encoding()))),
"..", certifi.where()))
class TimeoutSession(requests.Session):
@@ -55,44 +54,116 @@ class TimeoutSession(requests.Session):
class CertifiSession(TimeoutSession):
def __init__(self):
def __init__(self, verify=None):
super(CertifiSession, self).__init__()
self.verify = pem_file
self.verify = verify or pem_file
class CFSession(CloudflareScraper):
def __init__(self):
super(CFSession, self).__init__()
class NeedsCaptchaException(Exception):
pass
class CFSession(CloudScraper):
def __init__(self, *args, **kwargs):
super(CFSession, self).__init__(*args, **kwargs)
self.debug = os.environ.get("CF_DEBUG", False)
def _request(self, method, url, *args, **kwargs):
ourSuper = super(CloudScraper, self)
resp = ourSuper.request(method, url, *args, **kwargs)
if resp.headers.get('Content-Encoding') == 'br':
if self.allow_brotli and resp._content:
resp._content = brotli.decompress(resp.content)
else:
logging.warning('Brotli content detected, But option is disabled, we will not continue.')
return resp
# Debug request
if self.debug:
self.debugRequest(resp)
# Check if Cloudflare anti-bot is on
try:
if self.isChallengeRequest(resp):
if resp.request.method != 'GET':
# Work around if the initial request is not a GET,
# Supersede with a GET then re-request the original METHOD.
CloudScraper.request(self, 'GET', resp.url)
resp = ourSuper.request(method, url, *args, **kwargs)
else:
# Solve Challenge
resp = self.sendChallengeResponse(resp, **kwargs)
except ValueError, e:
if e.message == "Captcha":
parsed_url = urlparse(url)
domain = parsed_url.netloc
# solve the captcha
site_key = re.search(r'data-sitekey="(.+?)"', resp.content).group(1)
challenge_s = re.search(r'type="hidden" name="s" value="(.+?)"', resp.content).group(1)
challenge_ray = re.search(r'data-ray="(.+?)"', resp.content).group(1)
if not all([site_key, challenge_s, challenge_ray]):
raise Exception("cf: Captcha site-key not found!")
pitcher = pitchers.get_pitcher()("cf: %s" % domain, resp.request.url, site_key,
user_agent=self.headers["User-Agent"],
cookies=self.cookies.get_dict(),
is_invisible=True)
parsed_url = urlparse(resp.url)
logger.info("cf: %s: Solving captcha", domain)
result = pitcher.throw()
if not result:
raise Exception("cf: Couldn't solve captcha!")
submit_url = '{}://{}/cdn-cgi/l/chk_captcha'.format(parsed_url.scheme, domain)
method = resp.request.method
cloudflare_kwargs = {
'allow_redirects': False,
'headers': {'Referer': resp.url},
'params': OrderedDict(
[
('s', challenge_s),
('g-recaptcha-response', result)
]
)
}
return CloudScraper.request(self, method, submit_url, **cloudflare_kwargs)
return resp
def request(self, method, url, *args, **kwargs):
parsed_url = urlparse(url)
domain = parsed_url.netloc
cache_key = "cf_data2_%s" % domain
cache_key = "cf_data3_%s" % domain
if not self.cookies.get("__cfduid", "", domain=domain):
if not self.cookies.get("cf_clearance", "", domain=domain):
cf_data = region.get(cache_key)
if cf_data is not NO_VALUE:
cf_cookies, user_agent, hdrs = cf_data
cf_cookies, hdrs = cf_data
logger.debug("Trying to use old cf data for %s: %s", domain, cf_data)
for cookie, value in cf_cookies.iteritems():
self.cookies.set(cookie, value, domain=domain)
self._hdrs = hdrs
self._ua = user_agent
self.headers['User-Agent'] = self._ua
self.headers = hdrs
ret = super(CFSession, self).request(method, url, *args, **kwargs)
ret = self._request(method, url, *args, **kwargs)
try:
cf_data = self.get_cf_live_tokens(domain)
except:
pass
else:
if cf_data != region.get(cache_key) and cf_data[0]["__cfduid"] and cf_data[0]["cf_clearance"]:
logger.debug("Storing cf data for %s: %s", domain, cf_data)
region.set(cache_key, cf_data)
if cf_data and "cf_clearance" in cf_data[0] and cf_data[0]["cf_clearance"]:
if cf_data != region.get(cache_key):
logger.debug("Storing cf data for %s: %s", domain, cf_data)
region.set(cache_key, cf_data)
elif cf_data[0]["cf_clearance"]:
logger.debug("CF Live tokens not updated")
return ret
@@ -106,11 +177,11 @@ class CFSession(CloudflareScraper):
"Unable to find Cloudflare cookies. Does the site actually have "
"Cloudflare IUAM (\"I'm Under Attack Mode\") enabled?")
return (OrderedDict([
return (OrderedDict(filter(lambda x: x[1], [
("__cfduid", self.cookies.get("__cfduid", "", domain=cookie_domain)),
("cf_clearance", self.cookies.get("cf_clearance", "", domain=cookie_domain))
]),
self._ua, self._hdrs
])),
self.headers
)
@@ -166,12 +237,20 @@ class SubZeroRequestsTransport(xmlrpclib.SafeTransport):
# change our user agent to reflect Requests
user_agent = "Python XMLRPC with Requests (python-requests.org)"
proxies = None
xm_ver = 1
session_var = "PHPSESSID"
def __init__(self, use_https=True, verify=None, user_agent=None, timeout=10, *args, **kwargs):
self.verify = pem_file if verify is None else verify
self.use_https = use_https
self.user_agent = user_agent if user_agent is not None else self.user_agent
self.timeout = timeout
self.session = requests.Session()
self.session.headers['User-Agent'] = self.user_agent
# if 'requests' in self.session.headers['User-Agent']:
# # Set a random User-Agent if no custom User-Agent has been set
# self.session.headers = User_Agent(allow_brotli=False).headers
proxy = os.environ.get('SZ_HTTP_PROXY')
if proxy:
self.proxies = {
@@ -185,18 +264,40 @@ class SubZeroRequestsTransport(xmlrpclib.SafeTransport):
"""
Make an xmlrpc request.
"""
headers = {'User-Agent': self.user_agent}
url = self._build_url(host, handler)
cache_key = "xm%s_%s" % (self.xm_ver, host)
old_sessvar = self.session.cookies.get(self.session_var, "")
if not old_sessvar:
data = region.get(cache_key)
if data is not NO_VALUE:
logger.debug("Trying to re-use headers/cookies for %s" % host)
self.session.cookies, self.session.headers = data
old_sessvar = self.session.cookies.get(self.session_var, "")
try:
resp = requests.post(url, data=request_body, headers=headers,
stream=True, timeout=self.timeout, proxies=self.proxies,
verify=self.verify)
resp = self.session.post(url, data=request_body,
stream=True, timeout=self.timeout, proxies=self.proxies,
verify=self.verify)
if self.session_var in resp.cookies and resp.cookies[self.session_var] != old_sessvar:
logger.debug("Storing %s cookies" % host)
region.set(cache_key, [self.session.cookies, self.session.headers])
except ValueError:
logger.debug("Wiping cookies/headers cache (VE) for %s" % host)
region.delete(cache_key)
raise
except Exception:
logger.debug("Wiping cookies/headers cache (EX) for %s" % host)
region.delete(cache_key)
raise # something went wrong
else:
resp.raise_for_status()
try:
resp.raise_for_status()
except requests.exceptions.HTTPError:
logger.debug("Wiping cookies/headers cache (RE) for %s" % host)
region.delete(cache_key)
raise
try:
if 'x-ratelimit-remaining' in resp.headers and int(resp.headers['x-ratelimit-remaining']) <= 2:
@@ -226,25 +327,66 @@ _orig_create_connection = connection.create_connection
dns_cache = {}
def set_custom_resolver():
_custom_resolver = None
_custom_resolver_ips = None
def patch_create_connection():
if hasattr(connection.create_connection, "_sz_patched"):
return
def patched_create_connection(address, *args, **kwargs):
"""Wrap urllib3's create_connection to resolve the name elsewhere"""
# resolve hostname to an ip address; use your own
# resolver here, as otherwise the system resolver will be used.
global _custom_resolver, _custom_resolver_ips, dns_cache
host, port = address
if host in dns_cache:
ip = dns_cache[host]
logger.debug("Using %s=%s from cache", host, ip)
else:
try:
ip = custom_resolver.query(host)[0].address
dns_cache[host] = ip
except dns.exception.DNSException:
logger.warning("Couldn't resolve %s with DNS: %s", host, custom_resolver.nameservers)
return _orig_create_connection((host, port), *args, **kwargs)
logger.debug("Resolved %s to %s using %s", host, ip, custom_resolver.nameservers)
try:
ipaddress.ip_address(unicode(host))
except (ipaddress.AddressValueError, ValueError):
__custom_resolver_ips = os.environ.get("dns_resolvers", None)
return _orig_create_connection((ip, port), *args, **kwargs)
# resolver ips changed in the meantime?
if __custom_resolver_ips != _custom_resolver_ips:
_custom_resolver = None
_custom_resolver_ips = __custom_resolver_ips
dns_cache = {}
custom_resolver = _custom_resolver
if not custom_resolver:
if _custom_resolver_ips:
logger.debug("DNS: Trying to use custom DNS resolvers: %s", _custom_resolver_ips)
custom_resolver = dns.resolver.Resolver(configure=False)
custom_resolver.lifetime = os.environ.get("dns_resolvers_timeout", 8.0)
try:
custom_resolver.nameservers = json.loads(_custom_resolver_ips)
except:
logger.debug("DNS: Couldn't load custom DNS resolvers: %s", _custom_resolver_ips)
else:
_custom_resolver = custom_resolver
if custom_resolver:
if host in dns_cache:
ip = dns_cache[host]
logger.debug("DNS: Using %s=%s from cache", host, ip)
return _orig_create_connection((ip, port), *args, **kwargs)
else:
try:
ip = custom_resolver.query(host)[0].address
logger.debug("DNS: Resolved %s to %s using %s", host, ip, custom_resolver.nameservers)
dns_cache[host] = ip
return _orig_create_connection((ip, port), *args, **kwargs)
except dns.exception.DNSException:
logger.warning("DNS: Couldn't resolve %s with DNS: %s", host, custom_resolver.nameservers)
logger.debug("DNS: Falling back to default DNS or IP on %s", host)
return _orig_create_connection((host, port), *args, **kwargs)
patch_create_connection._sz_patched = True
connection.create_connection = patched_create_connection
patch_create_connection()
@@ -2,15 +2,20 @@
import logging
import re
import datetime
import types
import subliminal
import time
from random import randint
from dogpile.cache.api import NO_VALUE
from requests import Session
from subliminal.cache import region
from subliminal.exceptions import DownloadLimitExceeded, AuthenticationError
from subliminal.exceptions import DownloadLimitExceeded, AuthenticationError, ConfigurationError, \
DownloadLimitPerDayExceeded
from subliminal.providers.addic7ed import Addic7edProvider as _Addic7edProvider, \
Addic7edSubtitle as _Addic7edSubtitle, ParserBeautifulSoup, show_cells_re
Addic7edSubtitle as _Addic7edSubtitle, ParserBeautifulSoup
from subliminal.subtitle import fix_line_ending
from subliminal_patch.utils import sanitize
from subliminal_patch.exceptions import TooManyRequests
@@ -19,6 +24,8 @@ from subzero.language import Language
logger = logging.getLogger(__name__)
show_cells_re = re.compile(b'<td class="(?:version|vr)">.*?</td>', re.DOTALL)
#: Series header parsing regex
series_year_re = re.compile(r'^(?P<series>[ \w\'.:(),*&!?-]+?)(?: \((?P<year>\d{4})\))?$')
@@ -60,16 +67,22 @@ class Addic7edProvider(_Addic7edProvider):
'slk', 'slv', 'spa', 'sqi', 'srp', 'swe', 'tha', 'tur', 'ukr', 'vie', 'zho'
]} | {Language.fromietf(l) for l in ["sr-Latn", "sr-Cyrl"]}
vip = False
USE_ADDICTED_RANDOM_AGENTS = False
hearing_impaired_verifiable = True
subtitle_class = Addic7edSubtitle
server_url = 'https://www.addic7ed.com/'
sanitize_characters = {'-', ':', '(', ')', '.', '/'}
last_show_ids_fetch_key = "addic7ed_last_id_fetch"
def __init__(self, username=None, password=None, use_random_agents=False):
def __init__(self, username=None, password=None, use_random_agents=False, is_vip=False):
super(Addic7edProvider, self).__init__(username=username, password=password)
self.USE_ADDICTED_RANDOM_AGENTS = use_random_agents
self.vip = is_vip
if not all((username, password)):
raise ConfigurationError('Username and password must be specified')
def initialize(self):
self.session = Session()
@@ -101,13 +114,18 @@ class Addic7edProvider(_Addic7edProvider):
'remember': 'true'}
tries = 0
while tries < 3:
while tries <= 3:
tries += 1
r = self.session.get(self.server_url + 'login.php', timeout=10, headers={"Referer": self.server_url})
if "grecaptcha" in r.content:
if "g-recaptcha" in r.content or "grecaptcha" in r.content:
logger.info('Addic7ed: Solving captcha. This might take a couple of minutes, but should only '
'happen once every so often')
site_key = re.search(r'grecaptcha.execute\(\'(.+?)\',', r.content).group(1)
for g, s in (("g-recaptcha-response", r'g-recaptcha.+?data-sitekey=\"(.+?)\"'),
("recaptcha_response", r'grecaptcha.execute\(\'(.+?)\',')):
site_key = re.search(s, r.content).group(1)
if site_key:
break
if not site_key:
logger.error("Addic7ed: Captcha site-key not found!")
return
@@ -119,23 +137,31 @@ class Addic7edProvider(_Addic7edProvider):
result = pitcher.throw()
if not result:
raise Exception("Addic7ed: Couldn't solve captcha!")
if tries >= 3:
raise Exception("Addic7ed: Couldn't solve captcha!")
logger.info("Addic7ed: Couldn't solve captcha! Retrying")
time.sleep(4)
continue
data["recaptcha_response"] = result
data[g] = result
time.sleep(1)
r = self.session.post(self.server_url + 'dologin.php', data, allow_redirects=False, timeout=10,
headers={"Referer": self.server_url + "login.php"})
if "relax, slow down" in r.content:
raise TooManyRequests(self.username)
if r.status_code != 302:
if "User <b></b> doesn't exist" in r.content and tries <= 2:
logger.info("Addic7ed: Error, trying again. (%s/%s)", tries+1, 3)
tries += 1
continue
if "Wrong password" in r.content or "doesn't exist" in r.content:
raise AuthenticationError(self.username)
if r.status_code != 302:
if tries >= 3:
logger.error("Addic7ed: Something went wrong when logging in")
raise AuthenticationError(self.username)
logger.info("Addic7ed: Something went wrong when logging in; retrying")
time.sleep(4)
continue
break
store_verification("addic7ed", self.session)
@@ -143,10 +169,12 @@ class Addic7edProvider(_Addic7edProvider):
logger.debug('Addic7ed: Logged in')
self.logged_in = True
time.sleep(2)
def terminate(self):
self.session.close()
def get_show_id(self, series, year=None, country_code=None):
def get_show_id(self, series, year=None, country_code=None, ignore_cache=False):
"""Get the best matching show id for `series`, `year` and `country_code`.
First search in the result of :meth:`_get_show_ids` and fallback on a search with :meth:`_search_show_id`.
@@ -158,32 +186,45 @@ class Addic7edProvider(_Addic7edProvider):
:type country_code: str
:return: the show id, if found.
:rtype: int
"""
series_sanitized = sanitize(series).lower()
show_ids = self._get_show_ids()
show_id = None
ids_to_look_for = {sanitize(series).lower(), sanitize(series.replace(".", "")).lower()}
show_ids = self._get_show_ids()
if ignore_cache or not show_ids:
show_ids = self._get_show_ids.refresh(self)
# attempt with country
if not show_id and country_code:
logger.debug('Getting show id with country')
show_id = show_ids.get('%s %s' % (series_sanitized, country_code.lower()))
logger.debug("Trying show ids: %s", ids_to_look_for)
for series_sanitized in ids_to_look_for:
# attempt with country
if not show_id and country_code:
logger.debug('Getting show id with country')
show_id = show_ids.get('%s %s' % (series_sanitized, country_code.lower()))
# attempt with year
if not show_id and year:
logger.debug('Getting show id with year')
show_id = show_ids.get('%s %d' % (series_sanitized, year))
# attempt with year
if not show_id and year:
logger.debug('Getting show id with year')
show_id = show_ids.get('%s %d' % (series_sanitized, year))
# attempt clean
if not show_id:
logger.debug('Getting show id')
show_id = show_ids.get(series_sanitized)
# attempt clean
if not show_id:
logger.debug('Getting show id')
show_id = show_ids.get(series_sanitized)
# search as last resort
# broken right now
# if not show_id:
# logger.warning('Series %s not found in show ids', series)
# show_id = self._search_show_id(series)
if not show_id:
now = datetime.datetime.now()
last_fetch = region.get(self.last_show_ids_fetch_key)
# re-fetch show ids once per day if any show ID not found
if not ignore_cache and last_fetch != NO_VALUE and last_fetch + datetime.timedelta(days=1) < now:
logger.info("Show id not found; re-fetching show ids")
return self.get_show_id(series, year=year, country_code=country_code, ignore_cache=True)
logger.debug("Not refreshing show ids, as the last fetch has been too recent")
# search as last resort
# broken right now
# if not show_id:
# logger.warning('Series %s not found in show ids', series)
# show_id = self._search_show_id(series)
return show_id
@@ -197,6 +238,8 @@ class Addic7edProvider(_Addic7edProvider):
"""
# get the show page
logger.info('Getting show ids')
region.set(self.last_show_ids_fetch_key, datetime.datetime.now())
r = self.session.get(self.server_url + 'shows.php', timeout=10)
r.raise_for_status()
@@ -205,14 +248,15 @@ class Addic7edProvider(_Addic7edProvider):
# Assuming the site's markup is bad, and stripping it down to only contain what's needed.
show_cells = re.findall(show_cells_re, r.content)
if show_cells:
soup = ParserBeautifulSoup(b''.join(show_cells), ['lxml', 'html.parser'])
soup = ParserBeautifulSoup(b''.join(show_cells).decode('utf-8', 'ignore'), ['lxml', 'html.parser'])
else:
# If RegEx fails, fall back to original r.content and use 'html.parser'
soup = ParserBeautifulSoup(r.content, ['html.parser'])
# populate the show ids
show_ids = {}
for show in soup.select('td > h3 > a[href^="/show/"]'):
shows = soup.select('td > h3 > a[href^="/show/"]')
for show in shows:
show_clean = sanitize(show.text, default_characters=self.sanitize_characters)
try:
show_id = int(show['href'][6:])
@@ -230,6 +274,9 @@ class Addic7edProvider(_Addic7edProvider):
logger.debug('Found %d show ids', len(show_ids))
if not show_ids:
raise Exception("Addic7ed: No show IDs found!")
return show_ids
@region.cache_on_arguments(expiration_time=SHOW_EXPIRATION_TIME)
@@ -329,7 +376,7 @@ class Addic7edProvider(_Addic7edProvider):
# ignore incomplete subtitles
status = cells[5].text
if status != 'Completed':
if "%" in status:
logger.debug('Ignoring subtitle with status %s', status)
continue
@@ -355,6 +402,27 @@ class Addic7edProvider(_Addic7edProvider):
return subtitles
def download_subtitle(self, subtitle):
last_dls = region.get("addic7ed_dls")
now = datetime.datetime.now()
one_day = datetime.timedelta(hours=24)
def raise_limit():
logger.info("Addic7ed: Downloads per day exceeded (%s)", cap)
raise DownloadLimitPerDayExceeded
if not isinstance(last_dls, types.ListType):
last_dls = []
else:
# filter all non-expired DLs
last_dls = filter(lambda t: t + one_day > now, last_dls)
region.set("addic7ed_dls", last_dls)
cap = self.vip and 80 or 40
amount = len(last_dls)
if amount >= cap:
raise_limit()
# download the subtitle
r = self.session.get(self.server_url + subtitle.download_link, headers={'Referer': subtitle.page_link},
timeout=10)
@@ -366,7 +434,7 @@ class Addic7edProvider(_Addic7edProvider):
if not r.content:
# Provider wrongful return a status of 304 Not Modified with an empty content
# raise_for_status won't raise exception for that status code
logger.error('Unable to download subtitle. No data returned from provider')
logger.error('Addic7ed: Unable to download subtitle. No data returned from provider')
return
# detect download limit exceeded
@@ -374,3 +442,10 @@ class Addic7edProvider(_Addic7edProvider):
raise DownloadLimitExceeded
subtitle.content = fix_line_ending(r.content)
last_dls.append(datetime.datetime.now())
region.set("addic7ed_dls", last_dls)
logger.info("Addic7ed: Used %s/%s downloads", amount + 1, cap)
if amount + 1 >= cap:
raise_limit()
@@ -23,9 +23,10 @@ class ArgenteamSubtitle(Subtitle):
hearing_impaired_verifiable = False
_release_info = None
def __init__(self, language, download_link, movie_kind, title, season, episode, year, release, version, source,
def __init__(self, language, page_link, download_link, movie_kind, title, season, episode, year, release, version, source,
video_codec, tvdb_id, imdb_id, asked_for_episode=None, asked_for_release_group=None, *args, **kwargs):
super(ArgenteamSubtitle, self).__init__(language, download_link, *args, **kwargs)
super(ArgenteamSubtitle, self).__init__(language, page_link=page_link, *args, **kwargs)
self.page_link = page_link
self.download_link = download_link
self.movie_kind = movie_kind
self.title = title
@@ -135,7 +136,8 @@ class ArgenteamProvider(Provider, ProviderSubtitleArchiveMixin):
provider_name = 'argenteam'
languages = {Language.fromalpha2(l) for l in ['es']}
video_types = (Episode, Movie)
API_URL = "http://argenteam.net/api/v1/"
BASE_URL = "https://argenteam.net/"
API_URL = BASE_URL + "api/v1/"
subtitle_class = ArgenteamSubtitle
hearing_impaired_verifiable = False
language_list = list(languages)
@@ -240,12 +242,15 @@ class ArgenteamProvider(Provider, ProviderSubtitleArchiveMixin):
for r in content['releases']:
for s in r['subtitles']:
sub = ArgenteamSubtitle(language, s['uri'], "episode" if is_episode else "movie", returned_title,
movie_kind = "episode" if is_episode else "movie"
page_link = self.BASE_URL + movie_kind + "/" + str(aid)
# use https and new domain
download_link = s['uri'].replace('http://www.argenteam.net/', self.BASE_URL)
sub = ArgenteamSubtitle(language, page_link, download_link, movie_kind, returned_title,
season, episode, year, r.get('team'), r.get('tags'),
r.get('source'), r.get('codec'), content.get("tvdb"), imdb_id,
asked_for_release_group=video.release_group,
asked_for_episode=episode
)
asked_for_episode=episode)
subtitles.append(sub)
if has_multiple_ids:
@@ -0,0 +1,213 @@
# -*- coding: utf-8 -*-
from __future__ import absolute_import
import logging
import io
import os
from requests import Session
from guessit import guessit
from subliminal_patch.providers import Provider
from subliminal_patch.subtitle import Subtitle
from subliminal.utils import sanitize_release_group
from subliminal.subtitle import guess_matches
from subzero.language import Language
import gzip
import random
from time import sleep
from xml.etree import ElementTree
logger = logging.getLogger(__name__)
class BSPlayerSubtitle(Subtitle):
"""BSPlayer Subtitle."""
provider_name = 'bsplayer'
hash_verifiable = True
def __init__(self, language, filename, subtype, video, link):
super(BSPlayerSubtitle, self).__init__(language)
self.language = language
self.filename = filename
self.page_link = link
self.subtype = subtype
self.video = video
@property
def id(self):
return self.page_link
@property
def release_info(self):
return self.filename
def get_matches(self, video):
matches = set()
matches |= guess_matches(video, guessit(self.filename))
matches.add('hash')
return matches
class BSPlayerProvider(Provider):
"""BSPlayer Provider."""
languages = {Language('por', 'BR')} | {Language(l) for l in [
'ara', 'bul', 'ces', 'dan', 'deu', 'ell', 'eng', 'fin', 'fra', 'hun', 'ita', 'jpn', 'kor', 'nld', 'pol', 'por',
'ron', 'rus', 'spa', 'swe', 'tur', 'ukr', 'zho'
]}
SEARCH_THROTTLE = 8
hash_verifiable = True
# batantly based on kodi's bsplayer plugin
# also took from BSPlayer-Subtitles-Downloader
def __init__(self):
self.initialize()
def initialize(self):
self.session = Session()
self.search_url = self.get_sub_domain()
self.token = None
self.login()
def terminate(self):
self.session.close()
self.logout()
def api_request(self, func_name='logIn', params='', tries=5):
headers = {
'User-Agent': 'BSPlayer/2.x (1022.12360)',
'Content-Type': 'text/xml; charset=utf-8',
'Connection': 'close',
'SOAPAction': '"http://api.bsplayer-subtitles.com/v1.php#{func_name}"'.format(func_name=func_name)
}
data = (
'<?xml version="1.0" encoding="UTF-8"?>\n'
'<SOAP-ENV:Envelope xmlns:SOAP-ENV="http://schemas.xmlsoap.org/soap/envelope/" '
'xmlns:SOAP-ENC="http://schemas.xmlsoap.org/soap/encoding/" '
'xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" '
'xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:ns1="{search_url}">'
'<SOAP-ENV:Body SOAP-ENV:encodingStyle="http://schemas.xmlsoap.org/soap/encoding/">'
'<ns1:{func_name}>{params}</ns1:{func_name}></SOAP-ENV:Body></SOAP-ENV:Envelope>'
).format(search_url=self.search_url, func_name=func_name, params=params)
logger.info('Sending request: %s.' % func_name)
for i in iter(range(tries)):
try:
self.session.headers.update(headers.items())
res = self.session.post(self.search_url, data)
return ElementTree.fromstring(res.text)
except Exception as ex:
logger.info("ERROR: %s." % ex)
if func_name == 'logIn':
self.search_url = self.get_sub_domain()
sleep(1)
logger.info('ERROR: Too many tries (%d)...' % tries)
raise Exception('Too many tries...')
def login(self):
# If already logged in
if self.token:
return True
root = self.api_request(
func_name='logIn',
params=('<username></username>'
'<password></password>'
'<AppID>BSPlayer v2.67</AppID>')
)
res = root.find('.//return')
if res.find('status').text == 'OK':
self.token = res.find('data').text
logger.info("Logged In Successfully.")
return True
return False
def logout(self):
# If already logged out / not logged in
if not self.token:
return True
root = self.api_request(
func_name='logOut',
params='<handle>{token}</handle>'.format(token=self.token)
)
res = root.find('.//return')
self.token = None
if res.find('status').text == 'OK':
logger.info("Logged Out Successfully.")
return True
return False
def query(self, video, video_hash, language):
if not self.login():
return []
if isinstance(language, (tuple, list, set)):
# language_ids = ",".join(language)
# language_ids = 'spa'
language_ids = ','.join(sorted(l.opensubtitles for l in language))
if video.imdb_id is None:
imdbId = '*'
else:
imdbId = video.imdb_id
sleep(self.SEARCH_THROTTLE)
root = self.api_request(
func_name='searchSubtitles',
params=(
'<handle>{token}</handle>'
'<movieHash>{movie_hash}</movieHash>'
'<movieSize>{movie_size}</movieSize>'
'<languageId>{language_ids}</languageId>'
'<imdbId>{imdbId}</imdbId>'
).format(token=self.token, movie_hash=video_hash,
movie_size=video.size, language_ids=language_ids, imdbId=imdbId)
)
res = root.find('.//return/result')
if res.find('status').text != 'OK':
return []
items = root.findall('.//return/data/item')
subtitles = []
if items:
logger.info("Subtitles Found.")
for item in items:
subID = item.find('subID').text
subDownloadLink = item.find('subDownloadLink').text
subLang = Language.fromopensubtitles(item.find('subLang').text)
subName = item.find('subName').text
subFormat = item.find('subFormat').text
subtitles.append(
BSPlayerSubtitle(subLang, subName, subFormat, video, subDownloadLink)
)
return subtitles
def list_subtitles(self, video, languages):
return self.query(video, video.hashes['bsplayer'], languages)
def get_sub_domain(self):
# s1-9, s101-109
SUB_DOMAINS = ['s1', 's2', 's3', 's4', 's5', 's6', 's7', 's8', 's9',
's101', 's102', 's103', 's104', 's105', 's106', 's107', 's108', 's109']
API_URL_TEMPLATE = "http://{sub_domain}.api.bsplayer-subtitles.com/v1.php"
sub_domains_end = len(SUB_DOMAINS) - 1
return API_URL_TEMPLATE.format(sub_domain=SUB_DOMAINS[random.randint(0, sub_domains_end)])
def download_subtitle(self, subtitle):
session = Session()
_addheaders = {
'User-Agent': 'Mozilla/4.0 (compatible; Synapse)'
}
session.headers.update(_addheaders)
res = session.get(subtitle.page_link)
if res:
if res.text == '500':
raise ValueError('Error 500 on server')
with gzip.GzipFile(fileobj=io.BytesIO(res.content)) as gf:
subtitle.content = gf.read()
subtitle.normalize()
return subtitle
raise ValueError('Problems conecting to the server')
@@ -0,0 +1,124 @@
import logging
import os
from io import BytesIO
from zipfile import ZipFile
from requests import Session
from subliminal_patch.subtitle import Subtitle
from subliminal_patch.providers import Provider
from subliminal import __short_version__
from subliminal.exceptions import AuthenticationError, ConfigurationError
from subliminal.subtitle import fix_line_ending
from subzero.language import Language
logger = logging.getLogger(__name__)
class Napisy24Subtitle(Subtitle):
'''Napisy24 Subtitle.'''
provider_name = 'napisy24'
def __init__(self, language, hash, imdb_id, napis_id):
super(Napisy24Subtitle, self).__init__(language)
self.hash = hash
self.imdb_id = imdb_id
self.napis_id = napis_id
@property
def id(self):
return self.hash
def get_matches(self, video):
matches = set()
# hash
if 'napisy24' in video.hashes and video.hashes['napisy24'] == self.hash:
matches.add('hash')
# imdb_id
if video.imdb_id and self.imdb_id == video.imdb_id:
matches.add('imdb_id')
return matches
class Napisy24Provider(Provider):
'''Napisy24 Provider.'''
languages = {Language(l) for l in ['pol']}
required_hash = 'napisy24'
api_url = 'http://napisy24.pl/run/CheckSubAgent.php'
def __init__(self, username=None, password=None):
if all((username, password)):
self.username = username
self.password = password
else:
self.username = 'subliminal'
self.password = 'lanimilbus'
self.session = None
def initialize(self):
self.session = Session()
self.session.headers['User-Agent'] = 'Subliminal/%s' % __short_version__
self.session.headers['Content-Type'] = 'application/x-www-form-urlencoded'
def terminate(self):
self.session.close()
def query(self, language, size, name, hash):
params = {
'postAction': 'CheckSub',
'ua': self.username,
'ap': self.password,
'fs': size,
'fh': hash,
'fn': os.path.basename(name),
'n24pref': 1
}
response = self.session.post(self.api_url, data=params, timeout=10)
response.raise_for_status()
response_content = response.content.split(b'||', 1)
n24_data = response_content[0].decode()
if n24_data[:2] != 'OK':
if n24_data[:11] == 'login error':
raise AuthenticationError('Login failed')
logger.error('Unknown response: %s', response.content)
return None
n24_status = n24_data[:4]
if n24_status == 'OK-0':
logger.info('No subtitles found')
return None
subtitle_info = dict(p.split(':', 1) for p in n24_data.split('|')[1:])
logger.debug('Subtitle info: %s', subtitle_info)
if n24_status == 'OK-1':
logger.info('No subtitles found but got video info')
return None
elif n24_status == 'OK-2':
logger.info('Found subtitles')
elif n24_status == 'OK-3':
logger.info('Found subtitles but not from Napisy24 database')
return None
subtitle_content = response_content[1]
subtitle = Napisy24Subtitle(language, hash, 'tt%s' % subtitle_info['imdb'].zfill(7), subtitle_info['napisId'])
with ZipFile(BytesIO(subtitle_content)) as zf:
subtitle.content = fix_line_ending(zf.open(zf.namelist()[0]).read())
return subtitle
def list_subtitles(self, video, languages):
subtitles = [self.query(l, video.size, video.name, video.hashes['napisy24']) for l in languages]
return [s for s in subtitles if s is not None]
def download_subtitle(self, subtitle):
# there is no download step, content is already filled from listing subtitles
pass
@@ -105,7 +105,7 @@ class OpenSubtitlesProvider(ProviderRetryMixin, _OpenSubtitlesProvider):
def __init__(self, username=None, password=None, use_tag_search=False, only_foreign=False, also_foreign=False,
skip_wrong_fps=True, is_vip=False, use_ssl=True, timeout=15):
if any((username, password)) and not all((username, password)):
if not all((username, password)):
raise ConfigurationError('Username and password must be specified')
self.username = username or ''
@@ -154,6 +154,7 @@ class OpenSubtitlesProvider(ProviderRetryMixin, _OpenSubtitlesProvider):
logger.debug('Logged in with token %r', self.token[:10]+"X"*(len(self.token)-10))
region.set("os_token", self.token)
time.sleep(1)
def use_token_or_login(self, func):
if not self.token:
@@ -162,6 +163,7 @@ class OpenSubtitlesProvider(ProviderRetryMixin, _OpenSubtitlesProvider):
try:
return func()
except Unauthorized:
logger.debug("Token not valid, logging in again")
self.log_in()
return func()
@@ -197,16 +199,11 @@ class OpenSubtitlesProvider(ProviderRetryMixin, _OpenSubtitlesProvider):
return
logger.error("Login failed, please check your credentials")
raise
def terminate(self):
if self.token:
try:
checked(lambda: self.server.LogOut(self.token))
except:
logger.error("Logout failed: %s", traceback.format_exc())
self.server = None
self.token = None
#self.token = None
def list_subtitles(self, video, languages):
"""
@@ -0,0 +1,241 @@
# -*- coding: utf-8 -*-
from requests import Session
import json
import logging
from subzero.language import Language
from bs4 import BeautifulSoup
from guessit import guessit
from subliminal_patch.providers import Provider
from subliminal.providers import Episode, Movie
from subliminal_patch.utils import sanitize
from subliminal_patch.subtitle import Subtitle, guess_matches
from subliminal.subtitle import fix_line_ending
__author__ = "Dor Nizar"
logger = logging.getLogger(__name__)
class ScrewZiraSubtitle(Subtitle):
provider_name = 'screwzira'
def __init__(self, language, title_id, subtitle_id, series, season, episode, release, year):
super(ScrewZiraSubtitle, self).__init__(language, subtitle_id)
self.title_id = title_id
self.subtitle_id = subtitle_id
self.series = series
self.season = season
self.episode = episode
self.release = release
self.year = year
def get_matches(self, video):
matches = set()
logger.debug("--ScrewZiraSubtitle--\n{}".format(self.__dict__))
# episode
if isinstance(video, Episode):
# series
if video.series and sanitize(self.series) == sanitize(video.series):
matches.add('series')
# season
if video.season and self.season == video.season:
matches.add('season')
# episode
if video.episode and self.episode == video.episode:
matches.add('episode')
# guess
matches |= guess_matches(video, guessit(self.release, {'type': 'episode'}))
# movie
elif isinstance(video, Movie):
# title
if video.title and (sanitize(self.series) in (
sanitize(name) for name in [video.title] + video.alternative_titles)):
matches.add('title')
# year
if video.year and self.year == video.year:
matches.add('year')
# guess
matches |= guess_matches(video, guessit(self.release, {'type': 'movie'}))
logger.debug("ScrewZira subtitle criteria match:\n{}".format(matches))
return matches
@property
def id(self):
return self.subtitle_id
class ScrewZiraProvider(Provider):
subtitle_class = ScrewZiraSubtitle
languages = {Language.fromalpha2(l) for l in ['he']}
URL_SERVER = 'https://www.screwzira.com/'
URI_SEARCH_TITLE = 'Services/ContentProvider.svc/GetSearchForecast'
URI_SEARCH_SERIES_SUBTITLE = 'Services/GetModuleAjax.ashx'
URI_SEARCH_MOVIE_SUBTITLE = "MovieInfo.aspx"
URI_REQ_SUBTITLE_ID = "Services/ContentProvider.svc/RequestSubtitleDownload"
URI_DOWNLOAD_SUBTITLE = "Services/DownloadFile.ashx"
def initialize(self):
logger.debug("ScrewZira initialize")
self.session = Session()
self.session.headers[
'User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; ' \
'Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36'
def terminate(self):
logger.debug("ScrewZira terminate")
self.session.close()
def __init__(self):
self.session = None
def _search_series(self, title):
logger.debug("Searching '{}'".format(title))
title_request = {
"request": {
"SearchString": title,
"SearchType": "Film"
}
}
r = self.session.post(self.URL_SERVER + self.URI_SEARCH_TITLE, json=title_request, allow_redirects=False,
timeout=10)
r.raise_for_status()
series_found = r.json()
if 'd' in series_found:
try:
series_found = json.loads(series_found['d'])
except ValueError:
series_found = None
if 'Items' in series_found:
return series_found['Items']
return []
def _search_subtitles(self, title_id, season=None, episode=None):
if season and episode:
params = {
'moduleName': 'SubtitlesList',
'SeriesID': title_id,
'Season': season,
'Episode': episode
}
r = self.session.get(url=self.URL_SERVER + self.URI_SEARCH_SERIES_SUBTITLE, params=params)
else:
params = {
'ID': title_id,
}
r = self.session.get(url=self.URL_SERVER + self.URI_SEARCH_MOVIE_SUBTITLE, params=params)
r.raise_for_status()
results = r.content
if not results:
return []
subtitles = BeautifulSoup(results, 'html.parser').select('a.fa')
logger.debug("[BS4] Elements found:\n{}".format(subtitles))
subtitle_list = []
for i in subtitles:
subtitle_id = i.attrs['data-subtitle-id']
release = i.findParent().findParent().text.strip().split('\n')[0]
subtitle_list.append((subtitle_id, release))
return subtitle_list # [(Subtitle ID, name), (....)]
def _req_download_identifier(self, title_id, subtitle_id):
logger.debug("Request subtitle identifier for: title id: {}, subtitle id: {}".format(title_id, subtitle_id))
data = {
'request': {
'FilmID': title_id,
'SubtitleID': subtitle_id,
'FontSize': 0,
'FontColor': "",
'PredefinedLayout': -1
}
}
r = self.session.post(self.URL_SERVER + self.URI_REQ_SUBTITLE_ID, json=data, allow_redirects=False,
timeout=10)
r.raise_for_status()
try:
r = json.loads(r.json()['d'])
except ValueError:
r = {}
if 'DownloadIdentifier' not in r:
logger.error("Download Identifier not found")
return None
return r['DownloadIdentifier']
def _download_subtitles(self, download_id):
logger.debug("Downloading subtitles by download identifier - {}".format(download_id))
data = {'DownloadIdentifier': download_id}
r = self.session.get(self.URL_SERVER + self.URI_DOWNLOAD_SUBTITLE, params=data,
timeout=10)
r.raise_for_status()
if not r.content:
logger.debug("Download subtitle failed")
return None
logger.debug("Download subtitle success")
return r.content
def query(self, title, season=None, episode=None, year=None):
subtitles = []
titles = self._search_series(title)
if season and episode:
logger.debug("Searching for:\nTitle: {}\nSeason: {}\nEpisode: {}\nYear: {}".format(title, season,
episode, year))
else:
logger.debug("Searching for:\nTitle: {}\nYear: {}\n".format(title, year))
for title in titles:
logger.debug("Title Candidate: {}".format(title))
title_id = title['ID']
if season and episode:
result = self._search_subtitles(title_id, season, episode)
else:
result = self._search_subtitles(title_id)
if not result:
continue
for subtitle_id, release in result:
subtitles.append(self.subtitle_class(next(iter(self.languages)), title_id, subtitle_id,
title['EngName'], season, episode, release, year))
if subtitles:
logger.debug("Found Subtitle Candidates: {}".format(subtitles))
return subtitles
def list_subtitles(self, video, languages):
season = episode = year = title = None
if isinstance(video, Episode):
logger.info("list_subtitles Series: {}, season: {}, episode: {}".format(video.series,
video.season,
video.episode))
title = video.series
season = video.season
episode = video.episode
elif isinstance(video, Movie):
logger.info("list_subtitles Movie: {}, year: {}".format(video.title, video.year))
title = video.title
year = video.year
return [s for s in self.query(title, season, episode, year) if s.language in languages]
def download_subtitle(self, subtitle):
# type: (ScrewZiraSubtitle) -> None
logger.info('Downloading subtitle from ScrewZira: %r', subtitle)
downloadID = self._req_download_identifier(subtitle.title_id, subtitle.subtitle_id)
if not downloadID:
logger.debug('Unable to retrieve download identifier')
return None
content = self._download_subtitles(downloadID)
if not content:
logger.debug('Unable to download subtitle')
return None
subtitle.content = fix_line_ending(content)
@@ -4,29 +4,34 @@ import io
import logging
import os
import time
import traceback
import requests
import inflect
import cfscrape
import re
import json
import HTMLParser
import urlparse
from random import randint
from zipfile import ZipFile
from babelfish import language_converters
from guessit import guessit
from dogpile.cache.api import NO_VALUE
from subliminal import Episode, ProviderError
from subliminal.cache import region
from subliminal.exceptions import ConfigurationError, ServiceUnavailable
from subliminal.utils import sanitize_release_group
from subliminal.cache import region
from subliminal_patch.http import RetryingCFSession
from subliminal_patch.providers import Provider
from subliminal_patch.providers.mixins import ProviderSubtitleArchiveMixin
from subliminal_patch.subtitle import Subtitle, guess_matches
from subliminal_patch.converters.subscene import language_ids, supported_languages
from subscene_api.subscene import search, Subtitle as APISubtitle
from subscene_api.subscene import search, Subtitle as APISubtitle, SITE_DOMAIN
from subzero.language import Language
p = inflect.engine()
language_converters.register('subscene = subliminal_patch.converters.subscene:SubsceneConverter')
logger = logging.getLogger(__name__)
@@ -117,28 +122,106 @@ class SubsceneProvider(Provider, ProviderSubtitleArchiveMixin):
skip_wrong_fps = False
hearing_impaired_verifiable = True
only_foreign = False
username = None
password = None
search_throttle = 2 # seconds
search_throttle = 8 # seconds
def __init__(self, only_foreign=False, username=None, password=None):
if not all((username, password)):
raise ConfigurationError('Username and password must be specified')
def __init__(self, only_foreign=False):
self.only_foreign = only_foreign
self.username = username
self.password = password
def initialize(self):
logger.info("Creating session")
self.session = RetryingCFSession()
prev_cookies = region.get("subscene_cookies2")
if prev_cookies != NO_VALUE:
logger.debug("Re-using old subscene cookies: %r", prev_cookies)
self.session.cookies.update(prev_cookies)
else:
logger.debug("Logging in")
self.login()
def login(self):
r = self.session.get("https://subscene.com/account/login")
if "Server Error" in r.content:
logger.error("Login unavailable; Maintenance?")
raise ServiceUnavailable("Login unavailable; Maintenance?")
match = re.search(r"<script id='modelJson' type='application/json'>\s*(.+)\s*</script>", r.content)
if match:
h = HTMLParser.HTMLParser()
data = json.loads(h.unescape(match.group(1)))
login_url = urlparse.urljoin(data["siteUrl"], data["loginUrl"])
time.sleep(1.0)
r = self.session.post(login_url,
{
"username": self.username,
"password": self.password,
data["antiForgery"]["name"]: data["antiForgery"]["value"]
})
pep_content = re.search(r"<form method=\"post\" action=\"https://subscene\.com/\">"
r".+name=\"id_token\".+?value=\"(?P<id_token>.+?)\".*?"
r"access_token\".+?value=\"(?P<access_token>.+?)\".+?"
r"token_type.+?value=\"(?P<token_type>.+?)\".+?"
r"expires_in.+?value=\"(?P<expires_in>.+?)\".+?"
r"scope.+?value=\"(?P<scope>.+?)\".+?"
r"state.+?value=\"(?P<state>.+?)\".+?"
r"session_state.+?value=\"(?P<session_state>.+?)\"",
r.content, re.MULTILINE | re.DOTALL)
if pep_content:
r = self.session.post(SITE_DOMAIN, pep_content.groupdict())
try:
r.raise_for_status()
except Exception:
raise ProviderError("Something went wrong when trying to log in: %s", traceback.format_exc())
else:
cj = self.session.cookies.copy()
store_cks = ("scene", "idsrv", "idsrv.xsrf", "idsvr.clients", "idsvr.session", "idsvr.username")
for cn in self.session.cookies.iterkeys():
if cn not in store_cks:
del cj[cn]
logger.debug("Storing cookies: %r", cj)
region.set("subscene_cookies2", cj)
return
raise ProviderError("Something went wrong when trying to log in #1")
def terminate(self):
logger.info("Closing session")
self.session.close()
def _create_filters(self, languages):
self.filters = dict(HearingImpaired="2")
acc_filters = self.filters.copy()
if self.only_foreign:
self.filters["ForeignOnly"] = "True"
acc_filters["ForeignOnly"] = self.filters["ForeignOnly"].lower()
logger.info("Only searching for foreign/forced subtitles")
self.filters["LanguageFilter"] = ",".join((str(language_ids[l.alpha3]) for l in languages
if l.alpha3 in language_ids))
selected_ids = []
for l in languages:
lid = language_ids.get(l.basename, language_ids.get(l.alpha3, None))
if lid:
selected_ids.append(str(lid))
acc_filters["SelectedIds"] = selected_ids
self.filters["LanguageFilter"] = ",".join(acc_filters["SelectedIds"])
last_filters = region.get("subscene_filters")
if last_filters != acc_filters:
region.set("subscene_filters", acc_filters)
logger.debug("Setting account filters to %r", acc_filters)
self.session.post("https://u.subscene.com/filter", acc_filters, allow_redirects=False)
logger.debug("Filter created: '%s'" % self.filters)
@@ -181,7 +264,11 @@ class SubsceneProvider(Provider, ProviderSubtitleArchiveMixin):
def parse_results(self, video, film):
subtitles = []
for s in film.subtitles:
subtitle = SubsceneSubtitle.from_api(s)
try:
subtitle = SubsceneSubtitle.from_api(s)
except NotImplementedError, e:
logger.info(e)
continue
subtitle.asked_for_release_group = video.release_group
if isinstance(video, Episode):
subtitle.asked_for_episode = video.episode
@@ -194,10 +281,16 @@ class SubsceneProvider(Provider, ProviderSubtitleArchiveMixin):
return subtitles
def do_search(self, *args, **kwargs):
try:
return search(*args, **kwargs)
except requests.HTTPError:
region.delete("subscene_cookies2")
def query(self, video):
vfn = get_video_filename(video)
# vfn = get_video_filename(video)
subtitles = []
#logger.debug(u"Searching for: %s", vfn)
# logger.debug(u"Searching for: %s", vfn)
# film = search(vfn, session=self.session)
#
# if film and film.subtitles:
@@ -206,16 +299,17 @@ class SubsceneProvider(Provider, ProviderSubtitleArchiveMixin):
# else:
# logger.debug('No release results found')
#time.sleep(self.search_throttle)
# time.sleep(self.search_throttle)
# re-search for episodes without explicit release name
if isinstance(video, Episode):
#term = u"%s S%02iE%02i" % (video.series, video.season, video.episode)
more_than_one = len([video.series] + video.alternative_series) > 1
for series in [video.series] + video.alternative_series:
titles = list(set([video.series] + video.alternative_series))[:2]
# term = u"%s S%02iE%02i" % (video.series, video.season, video.episode)
more_than_one = len(titles) > 1
for series in titles:
term = u"%s - %s Season" % (series, p.number_to_words("%sth" % video.season).capitalize())
logger.debug('Searching for alternative results: %s', term)
film = search(term, session=self.session, release=False)
film = self.do_search(term, session=self.session, release=False, throttle=self.search_throttle)
if film and film.subtitles:
logger.debug('Alternative results found: %s', len(film.subtitles))
subtitles += self.parse_results(video, film)
@@ -223,25 +317,27 @@ class SubsceneProvider(Provider, ProviderSubtitleArchiveMixin):
logger.debug('No alternative results found')
# packs
if video.season_fully_aired:
term = u"%s S%02i" % (series, video.season)
logger.debug('Searching for packs: %s', term)
time.sleep(self.search_throttle)
film = search(term, session=self.session)
if film and film.subtitles:
logger.debug('Pack results found: %s', len(film.subtitles))
subtitles += self.parse_results(video, film)
else:
logger.debug('No pack results found')
else:
logger.debug("Not searching for packs, because the season hasn't fully aired")
# if video.season_fully_aired:
# term = u"%s S%02i" % (series, video.season)
# logger.debug('Searching for packs: %s', term)
# time.sleep(self.search_throttle)
# film = search(term, session=self.session, throttle=self.search_throttle)
# if film and film.subtitles:
# logger.debug('Pack results found: %s', len(film.subtitles))
# subtitles += self.parse_results(video, film)
# else:
# logger.debug('No pack results found')
# else:
# logger.debug("Not searching for packs, because the season hasn't fully aired")
if more_than_one:
time.sleep(self.search_throttle)
else:
more_than_one = len([video.title] + video.alternative_titles) > 1
for title in [video.title] + video.alternative_titles:
logger.debug('Searching for movie results: %s', title)
film = search(title, year=video.year, session=self.session, limit_to=None, release=False)
titles = list(set([video.title] + video.alternative_titles))[:2]
more_than_one = len(titles) > 1
for title in titles:
logger.debug('Searching for movie results: %r', title)
film = self.do_search(title, year=video.year, session=self.session, limit_to=None, release=False,
throttle=self.search_throttle)
if film and film.subtitles:
subtitles += self.parse_results(video, film)
if more_than_one:
@@ -2,42 +2,35 @@
import io
import logging
import math
import re
import time
from datetime import datetime
import dateutil.parser
import rarfile
from bs4 import BeautifulSoup
from zipfile import ZipFile, is_zipfile
from rarfile import RarFile, is_rarfile
from babelfish import language_converters, Script
from requests import RequestException
from requests import RequestException, codes as request_codes
from guessit import guessit
from subliminal_patch.http import RetryingCFSession
from subliminal_patch.providers import Provider
from subliminal_patch.providers.mixins import ProviderSubtitleArchiveMixin
from subliminal_patch.subtitle import Subtitle
from subliminal_patch.utils import sanitize, fix_inconsistent_naming as _fix_inconsistent_naming
from subliminal.exceptions import ProviderError
from subliminal.exceptions import ProviderError, AuthenticationError, ConfigurationError
from subliminal.score import get_equivalent_release_groups
from subliminal.utils import sanitize_release_group
from subliminal.subtitle import guess_matches
from subliminal.video import Episode, Movie
from subliminal.subtitle import fix_line_ending
from subliminal_patch.pitcher import pitchers, load_verification, store_verification
from subzero.language import Language
from random import randint
from .utils import FIRST_THOUSAND_OR_SO_USER_AGENTS as AGENT_LIST
from subzero.language import Language
from dogpile.cache.api import NO_VALUE
from subliminal.cache import region
# parsing regex definitions
title_re = re.compile(r'(?P<title>(?:.+(?= [Aa][Kk][Aa] ))|.+)(?:(?:.+)(?P<altitle>(?<= [Aa][Kk][Aa] ).+))?')
lang_re = re.compile(r'(?<=flags/)(?P<lang>.{2})(?:.)(?P<script>c?)(?:.+)')
season_re = re.compile(r'Sezona (?P<season>\d+)')
episode_re = re.compile(r'Epizoda (?P<episode>\d+)')
year_re = re.compile(r'(?P<year>\d+)')
fps_re = re.compile(r'fps: (?P<fps>.+)')
def fix_inconsistent_naming(title):
@@ -51,6 +44,7 @@ def fix_inconsistent_naming(title):
return _fix_inconsistent_naming(title, {"DC's Legends of Tomorrow": "Legends of Tomorrow",
"Marvel's Jessica Jones": "Jessica Jones"})
logger = logging.getLogger(__name__)
# Configure :mod:`rarfile` to use the same path separator as :mod:`zipfile`
@@ -62,9 +56,9 @@ language_converters.register('titlovi = subliminal_patch.converters.titlovi:Titl
class TitloviSubtitle(Subtitle):
provider_name = 'titlovi'
def __init__(self, language, page_link, download_link, sid, releases, title, alt_title=None, season=None,
episode=None, year=None, fps=None, asked_for_release_group=None, asked_for_episode=None):
super(TitloviSubtitle, self).__init__(language, page_link=page_link)
def __init__(self, language, download_link, sid, releases, title, alt_title=None, season=None,
episode=None, year=None, rating=None, download_count=None, asked_for_release_group=None, asked_for_episode=None):
super(TitloviSubtitle, self).__init__(language)
self.sid = sid
self.releases = self.release_info = releases
self.title = title
@@ -73,11 +67,21 @@ class TitloviSubtitle(Subtitle):
self.episode = episode
self.year = year
self.download_link = download_link
self.fps = fps
self.rating = rating
self.download_count = download_count
self.matches = None
self.asked_for_release_group = asked_for_release_group
self.asked_for_episode = asked_for_episode
def __repr__(self):
if self.season and self.episode:
return '<%s "%s (%r)" s%.2de%.2d [%s:%s] ID:%r R:%.2f D:%r>' % (
self.__class__.__name__, self.title, self.year, self.season, self.episode, self.language, self._guessed_encoding, self.sid,
self.rating, self.download_count)
else:
return '<%s "%s (%r)" [%s:%s] ID:%r R:%.2f D:%r>' % (
self.__class__.__name__, self.title, self.year, self.language, self._guessed_encoding, self.sid, self.rating, self.download_count)
@property
def id(self):
return self.sid
@@ -134,20 +138,62 @@ class TitloviSubtitle(Subtitle):
class TitloviProvider(Provider, ProviderSubtitleArchiveMixin):
subtitle_class = TitloviSubtitle
languages = {Language.fromtitlovi(l) for l in language_converters['titlovi'].codes} | {Language.fromietf('sr-Latn')}
server_url = 'https://titlovi.com'
search_url = server_url + '/titlovi/?'
download_url = server_url + '/download/?type=1&mediaid='
api_url = 'https://kodi.titlovi.com/api/subtitles'
api_gettoken_url = api_url + '/gettoken'
api_search_url = api_url + '/search'
def __init__(self, username=None, password=None):
if not all((username, password)):
raise ConfigurationError('Username and password must be specified')
self.username = username
self.password = password
self.session = None
self.user_id = None
self.login_token = None
self.token_exp = None
def initialize(self):
self.session = RetryingCFSession()
load_verification("titlovi", self.session)
#load_verification("titlovi", self.session)
token = region.get("titlovi_token")
if token is not NO_VALUE:
self.user_id, self.login_token, self.token_exp = token
if datetime.now() > self.token_exp:
logger.debug('Token expired')
self.log_in()
else:
logger.debug('Use cached token')
else:
logger.debug('Token not found in cache')
self.log_in()
def log_in(self):
login_params = dict(username=self.username, password=self.password, json=True)
try:
response = self.session.post(self.api_gettoken_url, params=login_params)
if response.status_code == request_codes.ok:
resp_json = response.json()
self.login_token = resp_json.get('Token')
self.user_id = resp_json.get('UserId')
self.token_exp = dateutil.parser.parse(resp_json.get('ExpirationDate'))
region.set("titlovi_token", [self.user_id, self.login_token, self.token_exp])
logger.debug('New token obtained')
elif response.status_code == request_codes.unauthorized:
raise AuthenticationError('Login failed')
except RequestException as e:
logger.error(e)
def terminate(self):
self.session.close()
def query(self, languages, title, season=None, episode=None, year=None, video=None):
items_per_page = 10
current_page = 1
def query(self, languages, title, season=None, episode=None, year=None, imdb_id=None, video=None):
search_params = dict()
used_languages = languages
lang_strings = [str(lang) for lang in used_languages]
@@ -162,168 +208,73 @@ class TitloviProvider(Provider, ProviderSubtitleArchiveMixin):
langs = '|'.join(map(str, [l.titlovi for l in used_languages]))
# set query params
params = {'prijevod': title, 'jezik': langs}
search_params['query'] = title
search_params['lang'] = langs
is_episode = False
if season and episode:
is_episode = True
params['s'] = season
params['e'] = episode
if year:
params['g'] = year
search_params['season'] = season
search_params['episode'] = episode
#if year:
# search_params['year'] = year
if imdb_id:
search_params['imdbID'] = imdb_id
# loop through paginated results
logger.info('Searching subtitles %r', params)
logger.info('Searching subtitles %r', search_params)
subtitles = []
query_results = []
while True:
# query the server
try:
r = self.session.get(self.search_url, params=params, timeout=10)
r.raise_for_status()
except RequestException as e:
captcha_passed = False
if e.response.status_code == 403 and "data-sitekey" in e.response.content:
logger.info('titlovi: Solving captcha. This might take a couple of minutes, but should only '
'happen once every so often')
try:
search_params['token'] = self.login_token
search_params['userid'] = self.user_id
search_params['json'] = True
site_key = re.search(r'data-sitekey="(.+?)"', e.response.content).group(1)
challenge_s = re.search(r'type="hidden" name="s" value="(.+?)"', e.response.content).group(1)
challenge_ray = re.search(r'data-ray="(.+?)"', e.response.content).group(1)
if not all([site_key, challenge_s, challenge_ray]):
raise Exception("titlovi: Captcha site-key not found!")
response = self.session.get(self.api_search_url, params=search_params)
resp_json = response.json()
if resp_json['SubtitleResults']:
query_results.extend(resp_json['SubtitleResults'])
pitcher = pitchers.get_pitcher()("titlovi", e.request.url, site_key,
user_agent=self.session.headers["User-Agent"],
cookies=self.session.cookies.get_dict(),
is_invisible=True)
result = pitcher.throw()
if not result:
raise Exception("titlovi: Couldn't solve captcha!")
except Exception as e:
logger.error(e)
s_params = {
"s": challenge_s,
"id": challenge_ray,
"g-recaptcha-response": result,
}
r = self.session.get(self.server_url + "/cdn-cgi/l/chk_captcha", params=s_params, timeout=10,
allow_redirects=False)
r.raise_for_status()
r = self.session.get(self.search_url, params=params, timeout=10)
r.raise_for_status()
store_verification("titlovi", self.session)
captcha_passed = True
for sub in query_results:
if not captcha_passed:
logger.exception('RequestException %s', e)
break
# title and alternate title
match = title_re.search(sub.get('Title'))
if match:
_title = match.group('title')
alt_title = match.group('altitle')
else:
try:
soup = BeautifulSoup(r.content, 'lxml')
continue
# number of results
result_count = int(soup.select_one('.results_count b').string)
except:
result_count = None
# handle movies and series separately
if is_episode:
subtitle = self.subtitle_class(Language.fromtitlovi(sub.get('Lang')), sub.get('Link'), sub.get('Id'), sub.get('Release'), _title,
alt_title=alt_title, season=sub.get('Season'), episode=sub.get('Episode'),
year=sub.get('Year'), rating=sub.get('Rating'),
download_count=sub.get('DownloadCount'),
asked_for_release_group=video.release_group,
asked_for_episode=episode)
else:
subtitle = self.subtitle_class(Language.fromtitlovi(sub.get('Lang')), sub.get('Link'), sub.get('Id'), sub.get('Release'), _title,
alt_title=alt_title, year=sub.get('Year'), rating=sub.get('Rating'),
download_count=sub.get('DownloadCount'),
asked_for_release_group=video.release_group)
logger.debug('Found subtitle %r', subtitle)
# exit if no results
if not result_count:
if not subtitles:
logger.debug('No subtitles found')
else:
logger.debug("No more subtitles found")
break
# prime our matches so we can use the values later
subtitle.get_matches(video)
# number of pages with results
pages = int(math.ceil(result_count / float(items_per_page)))
# get current page
if 'pg' in params:
current_page = int(params['pg'])
try:
sublist = soup.select('section.titlovi > ul.titlovi > li.subtitleContainer.canEdit')
for sub in sublist:
# subtitle id
sid = sub.find(attrs={'data-id': True}).attrs['data-id']
# get download link
download_link = self.download_url + sid
# title and alternate title
match = title_re.search(sub.a.string)
if match:
_title = match.group('title')
alt_title = match.group('altitle')
else:
continue
# page link
page_link = self.server_url + sub.a.attrs['href']
# subtitle language
match = lang_re.search(sub.select_one('.lang').attrs['src'])
if match:
try:
# decode language
lang = Language.fromtitlovi(match.group('lang')+match.group('script'))
except ValueError:
continue
# relase year or series start year
match = year_re.search(sub.find(attrs={'data-id': True}).parent.i.string)
if match:
r_year = int(match.group('year'))
# fps
match = fps_re.search(sub.select_one('.fps').string)
if match:
fps = match.group('fps')
# releases
releases = str(sub.select_one('.fps').parent.contents[0].string)
# handle movies and series separately
if is_episode:
# season and episode info
sxe = sub.select_one('.s0xe0y').string
r_season = None
r_episode = None
if sxe:
match = season_re.search(sxe)
if match:
r_season = int(match.group('season'))
match = episode_re.search(sxe)
if match:
r_episode = int(match.group('episode'))
subtitle = self.subtitle_class(lang, page_link, download_link, sid, releases, _title,
alt_title=alt_title, season=r_season, episode=r_episode,
year=r_year, fps=fps,
asked_for_release_group=video.release_group,
asked_for_episode=episode)
else:
subtitle = self.subtitle_class(lang, page_link, download_link, sid, releases, _title,
alt_title=alt_title, year=r_year, fps=fps,
asked_for_release_group=video.release_group)
logger.debug('Found subtitle %r', subtitle)
# prime our matches so we can use the values later
subtitle.get_matches(video)
# add found subtitles
subtitles.append(subtitle)
finally:
soup.decompose()
# stop on last page
if current_page >= pages:
break
# increment current page
params['pg'] = current_page + 1
logger.debug('Getting page %d', params['pg'])
# add found subtitles
subtitles.append(subtitle)
return subtitles
def list_subtitles(self, video, languages):
season = episode = None
if isinstance(video, Episode):
title = video.series
season = video.season
@@ -333,6 +284,7 @@ class TitloviProvider(Provider, ProviderSubtitleArchiveMixin):
return [s for s in
self.query(languages, fix_inconsistent_naming(title), season=season, episode=episode, year=video.year,
imdb_id=video.imdb_id,
video=video)]
def download_subtitle(self, subtitle):
@@ -370,10 +322,12 @@ class TitloviProvider(Provider, ProviderSubtitleArchiveMixin):
sub_to_extract = None
for sub_name in subs_in_archive:
if not ('.cyr' in sub_name or '.cir' in sub_name):
_sub_name = sub_name.lower()
if not ('.cyr' in _sub_name or '.cir' in _sub_name or 'cyr)' in _sub_name):
sr_lat_subs.append(sub_name)
if ('.cyr' in sub_name or '.cir' in sub_name) and not '.lat' in sub_name:
if ('.cyr' in sub_name or '.cir' in _sub_name) and not '.lat' in _sub_name.lower():
sr_cyr_subs.append(sub_name)
if subtitle.language == 'sr':
@@ -19,11 +19,11 @@ class DroneAPIClient(object):
_fill_attrs = None
def __init__(self, version=1, session=None, headers=None, timeout=10, base_url=None, api_key=None,
ssl_no_verify=False):
ssl_no_verify=False, pem_file=None):
headers = dict(headers or {}, **{"X-Api-Key": api_key})
#: Session for the requests
self.session = session or CertifiSession()
self.session = session or CertifiSession(verify=pem_file)
if ssl_no_verify:
self.session.verify = False
@@ -87,7 +87,10 @@ def refine(video, **kwargs):
# parse series year
series_year = None
if result['firstAired']:
series_year = datetime.datetime.strptime(result['firstAired'], '%Y-%m-%d').year
try:
series_year = datetime.datetime.strptime(result['firstAired'], '%Y-%m-%d').year
except ValueError:
continue
# discard mismatches on year
if video.year and series_year and video.year != series_year:
@@ -60,6 +60,8 @@ def compute_score(matches, subtitle, video, hearing_impaired=None):
episode_hash_valid_if = {"series", "season", "episode", "format"}
movie_hash_valid_if = {"video_codec", "format"}
orig_matches = matches.copy()
# on hash match, discard everything else
if subtitle.hash_verifiable:
if 'hash' in matches:
@@ -83,41 +85,47 @@ def compute_score(matches, subtitle, video, hearing_impaired=None):
matches &= {'hash'}
# handle equivalent matches
eq_matches = set()
if is_episode:
if 'title' in matches:
logger.debug('Adding title match equivalent')
matches.add('episode')
eq_matches.add('episode')
if 'series_imdb_id' in matches:
logger.debug('Adding series_imdb_id match equivalent')
matches |= {'series', 'year'}
eq_matches |= {'series', 'year'}
if 'imdb_id' in matches:
logger.debug('Adding imdb_id match equivalents')
matches |= {'series', 'year', 'season', 'episode'}
eq_matches |= {'series', 'year', 'season', 'episode'}
if 'tvdb_id' in matches:
logger.debug('Adding tvdb_id match equivalents')
matches |= {'series', 'year', 'season', 'episode', 'title'}
eq_matches |= {'series', 'year', 'season', 'episode', 'title'}
if 'series_tvdb_id' in matches:
logger.debug('Adding series_tvdb_id match equivalents')
matches |= {'series', 'year'}
eq_matches |= {'series', 'year'}
# specials
if video.is_special and 'title' in matches and 'series' in matches \
and 'year' in matches:
logger.debug('Adding special title match equivalent')
matches |= {'season', 'episode'}
eq_matches |= {'season', 'episode'}
elif is_movie:
if 'imdb_id' in matches:
logger.debug('Adding imdb_id match equivalents')
matches |= {'title', 'year'}
eq_matches |= {'title', 'year'}
matches |= eq_matches
# handle hearing impaired
if hearing_impaired is not None and subtitle.hearing_impaired == hearing_impaired:
logger.debug('Matched hearing_impaired')
matches.add('hearing_impaired')
orig_matches.add('hearing_impaired')
# compute the score
score = sum((scores.get(match, 0) for match in matches))
logger.info('%r: Computed score %r with final matches %r', subtitle, score, matches)
return score
score_without_hash = sum((scores.get(match, 0) for match in orig_matches | eq_matches if match != "hash"))
return score, score_without_hash
@@ -19,6 +19,15 @@ from subliminal import Subtitle as Subtitle_
from subliminal.subtitle import Episode, Movie, sanitize_release_group, get_equivalent_release_groups
from subliminal_patch.utils import sanitize
from ftfy import fix_text
from codecs import BOM_UTF8, BOM_UTF16_BE, BOM_UTF16_LE, BOM_UTF32_BE, BOM_UTF32_LE
BOMS = (
(BOM_UTF8, "UTF-8"),
(BOM_UTF32_BE, "UTF-32-BE"),
(BOM_UTF32_LE, "UTF-32-LE"),
(BOM_UTF16_BE, "UTF-16-BE"),
(BOM_UTF16_LE, "UTF-16-LE"),
)
logger = logging.getLogger(__name__)
@@ -105,6 +114,9 @@ class Subtitle(Subtitle_):
# normalize line endings
self.content = self.content.replace("\r\n", "\n").replace('\r', '\n')
def _check_bom(self, data):
return [encoding for bom, encoding in BOMS if data.startswith(bom)]
def guess_encoding(self):
"""Guess encoding using the language, falling back on chardet.
@@ -119,11 +131,17 @@ class Subtitle(Subtitle_):
encodings = ['utf-8']
# check UTF BOMs
bom_encodings = self._check_bom(self.content)
if bom_encodings:
encodings = list(set(enc.lower() for enc in bom_encodings + encodings))
# add language-specific encodings
# http://scratchpad.wikia.com/wiki/Character_Encoding_Recommendation_for_Languages
if self.language.alpha3 == 'zho':
encodings.extend(['cp936', 'gb2312', 'cp950', 'gb18030', 'big5', 'big5hkscs'])
encodings.extend(['cp936', 'gb2312', 'gbk', 'gb18030', 'hz', 'iso2022_jp_2', 'cp950', 'gb18030', 'big5',
'big5hkscs', 'utf-16'])
elif self.language.alpha3 == 'jpn':
encodings.extend(['shift-jis', 'cp932', 'euc_jp', 'iso2022_jp', 'iso2022_jp_1', 'iso2022_jp_2',
'iso2022_jp_2004', 'iso2022_jp_3', 'iso2022_jp_ext', ])
@@ -132,7 +150,7 @@ class Subtitle(Subtitle_):
# arabian/farsi
elif self.language.alpha3 in ('ara', 'fas', 'per'):
encodings.append('windows-1256')
encodings.extend(['windows-1256', 'utf-16'])
elif self.language.alpha3 == 'heb':
encodings.extend(['windows-1255', 'iso-8859-8'])
elif self.language.alpha3 == 'tur':
@@ -250,8 +268,7 @@ class Subtitle(Subtitle_):
subs = pysubs2.SSAFile.from_string(text, fps=self.plex_media_fps)
unicontent = self.pysubs2_to_unicode(subs)
self.content = unicontent.encode("utf-8")
self._guessed_encoding = "utf-8"
self.content = unicontent.encode(self._guessed_encoding)
except:
logger.exception("Couldn't convert subtitle %s to .srt format: %s", self, traceback.format_exc())
return False
@@ -261,6 +278,12 @@ class Subtitle(Subtitle_):
@classmethod
def pysubs2_to_unicode(cls, sub, format="srt"):
"""
this is a modified version of pysubs2.SubripFormat.to_file with special handling for drawing tags in ASS
:param sub:
:param format:
:return:
"""
def ms_to_timestamp(ms, mssep=","):
"""Convert ms to 'HH:MM:SS,mmm'"""
# XXX throw on overflow/underflow?
@@ -272,9 +295,12 @@ class Subtitle(Subtitle_):
def prepare_text(text, style):
body = []
for fragment, sty in parse_tags(text, style, sub.styles):
fragment = fragment.replace(ur"\h", u" ")
fragment = fragment.replace(ur"\n", u"\n")
fragment = fragment.replace(ur"\N", u"\n")
fragment = fragment.replace(r"\h", u" ")
fragment = fragment.replace(r"\n", u"\n")
fragment = fragment.replace(r"\N", u"\n")
if sty.drawing:
raise pysubs2.ContentNotUsable
if format == "srt":
if sty.italic:
fragment = u"<i>%s</i>" % fragment
@@ -306,7 +332,10 @@ class Subtitle(Subtitle_):
for i, line in enumerate(visible_lines, 1):
start = ms_to_timestamp(line.start, mssep=mssep)
end = ms_to_timestamp(line.end, mssep=mssep)
text = prepare_text(line.text, sub.styles.get(line.style, SSAStyle.DEFAULT_STYLE))
try:
text = prepare_text(line.text, sub.styles.get(line.style, SSAStyle.DEFAULT_STYLE))
except pysubs2.ContentNotUsable:
continue
out.append(u"%d\n" % i)
out.append(u"%s --> %s\n" % (start, end))
@@ -319,7 +348,8 @@ class Subtitle(Subtitle_):
:return: string
"""
if not self.mods:
return fix_text(self.content.decode("utf-8"), **ftfy_defaults).encode(encoding="utf-8")
return fix_text(self.content.decode(encoding=self._guessed_encoding), **ftfy_defaults).encode(
encoding=self._guessed_encoding)
submods = SubtitleModifications(debug=debug)
if submods.load(content=self.text, language=self.language):
@@ -328,7 +358,7 @@ class Subtitle(Subtitle_):
self.mods = submods.mods_used
content = fix_text(self.pysubs2_to_unicode(submods.f, format=format), **ftfy_defaults)\
.encode(encoding="utf-8")
.encode(encoding=self._guessed_encoding)
submods.f = None
del submods
return content
@@ -339,6 +369,15 @@ class ModifiedSubtitle(Subtitle):
id = None
MERGED_FORMATS = {
"TV": ("HDTV", "SDTV", "AHDTV", "UHDTV"),
"Air": ("SATRip", "DVB", "PPV"),
"Disk": ("DVD", "HD-DVD", "BluRay")
}
MERGED_FORMATS_REV = dict((v.lower(), k.lower()) for k in MERGED_FORMATS for v in MERGED_FORMATS[k])
def guess_matches(video, guess, partial=False):
"""Get matches between a `video` and a `guess`.
@@ -359,11 +398,11 @@ def guess_matches(video, guess, partial=False):
matches = set()
if isinstance(video, Episode):
# series
titles = guess["title"]
if not isinstance(titles, types.ListType):
titles = [titles]
if video.series and 'title' in guess:
titles = guess["title"]
if not isinstance(titles, types.ListType):
titles = [titles]
for title in titles:
if sanitize(title) in (sanitize(name) for name in [video.series] + video.alternative_series):
matches.add('series')
@@ -421,21 +460,25 @@ def guess_matches(video, guess, partial=False):
formats = [formats]
if video.format:
video_format = video.format
if video_format in ("HDTV", "SDTV", "TV"):
video_format = "TV"
logger.debug("Treating HDTV/SDTV the same")
video_format = video.format.lower()
_video_gen_format = MERGED_FORMATS_REV.get(video_format)
if _video_gen_format:
logger.debug("Treating %s as %s the same", video_format, _video_gen_format)
for frmt in formats:
if frmt in ("HDTV", "SDTV"):
frmt = "TV"
_guess_gen_frmt = MERGED_FORMATS_REV.get(frmt.lower())
if frmt.lower() == video_format.lower():
if _guess_gen_frmt == _video_gen_format:
matches.add('format')
break
if "release_group" in matches and "format" not in matches:
logger.info("Release group matched but format didn't. Remnoving release group match.")
matches.remove("release_group")
# video_codec
if video.video_codec and 'video_codec' in guess and guess['video_codec'] == video.video_codec:
matches.add('video_codec')
# audio_codec
if video.audio_codec and 'audio_codec' in guess and guess['audio_codec'] == video.audio_codec:
matches.add('audio_codec')
+2 -1
View File
@@ -21,9 +21,10 @@ if debug:
logging.basicConfig(level=logging.DEBUG)
#sub = Subtitle(Language.fromietf("eng:forced"), mods=["common", "remove_HI", "OCR_fixes", "fix_uppercase", "shift_offset(ms=-500)", "shift_offset(ms=500)", "shift_offset(s=2,ms=800)"])
sub = Subtitle(Language.fromietf("eng:forced"), mods=["common", "remove_HI", "OCR_fixes", "fix_uppercase", "shift_offset(ms=0,s=1)"])
sub = Subtitle(Language.fromietf("eng"), mods=["common", "remove_HI", "OCR_fixes", "fix_uppercase", "shift_offset(ms=0,s=1)", "fix_incremental", "fix_short"])
sub.content = open(fn).read()
sub.normalize()
sub.is_valid()
content = sub.get_modified_content(debug=True)
#submod = SubMod(debug=debug)
@@ -28,6 +28,9 @@ import re
import enum
import sys
import requests
import time
import logging
is_PY2 = sys.version_info[0] < 3
if is_PY2:
@@ -37,8 +40,13 @@ else:
from contextlib import suppress
from urllib2.request import Request, urlopen
from dogpile.cache.api import NO_VALUE
from subliminal.cache import region
from bs4 import BeautifulSoup, NavigableString
logger = logging.getLogger(__name__)
# constants
HEADERS = {
}
@@ -48,14 +56,23 @@ DEFAULT_USER_AGENT = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_3) AppleWeb"\
"Kit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.47 Safari/537.36"
ENDPOINT_RE = re.compile(ur'(?uis)<form.+?action="/subtitles/(.+)">.*?<input type="text"')
class NewEndpoint(Exception):
pass
# utils
def soup_for(url, session=None, user_agent=DEFAULT_USER_AGENT):
def soup_for(url, data=None, session=None, user_agent=DEFAULT_USER_AGENT):
url = re.sub("\s", "+", url)
if not session:
r = Request(url, data=None, headers=dict(HEADERS, **{"User-Agent": user_agent}))
html = urlopen(r).read().decode("utf-8")
else:
html = session.get(url).text
ret = session.post(url, data=data)
ret.raise_for_status()
html = ret.text
return BeautifulSoup(html, "html.parser")
@@ -108,7 +125,7 @@ class Subtitle(object):
subtitles = []
for row in rows:
if row.td.a is not None:
if row.td.a is not None and row.td.get("class", ["lazy"])[0] != "empty":
subtitles.append(cls.from_row(row))
return subtitles
@@ -238,22 +255,52 @@ def get_first_film(soup, section, year=None, session=None):
url = SITE_DOMAIN + t.div.a.get("href")
break
if not url:
return
# fallback to non-year results
logger.info("Falling back to non-year results as year wasn't found (%s)", year)
url = SITE_DOMAIN + tag.findNext("ul").find("li").div.a.get("href")
return Film.from_url(url, session=session)
def search(term, release=True, session=None, year=None, limit_to=SearchTypes.Exact):
soup = soup_for("%s/subtitles/%s?q=%s" % (SITE_DOMAIN, "release" if release else "title", term), session=session)
def find_endpoint(session, content=None):
endpoint = region.get("subscene_endpoint2")
if endpoint is NO_VALUE:
if not content:
content = session.get(SITE_DOMAIN).text
if "Subtitle search by" in str(soup):
rows = soup.find("table").tbody.find_all("tr")
subtitles = Subtitle.from_rows(rows)
return Film(term, subtitles=subtitles)
m = ENDPOINT_RE.search(content)
if m:
endpoint = m.group(1).strip()
logger.debug("Switching main endpoint to %s", endpoint)
region.set("subscene_endpoint2", endpoint)
return endpoint
for junk, search_type in SearchTypes.__members__.items():
if section_exists(soup, search_type):
return get_first_film(soup, search_type, year=year, session=session)
if limit_to == search_type:
return
def search(term, release=True, session=None, year=None, limit_to=SearchTypes.Exact, throttle=0):
# note to subscene: if you actually start to randomize the endpoint, we'll have to query your server even more
if release:
endpoint = "release"
else:
endpoint = find_endpoint(session)
time.sleep(throttle)
if not endpoint:
logger.error("Couldn't find endpoint, exiting")
return
soup = soup_for("%s/subtitles/%s" % (SITE_DOMAIN, endpoint), data={"query": term},
session=session)
if soup:
if "Subtitle search by" in str(soup):
rows = soup.find("table").tbody.find_all("tr")
subtitles = Subtitle.from_rows(rows)
return Film(term, subtitles=subtitles)
for junk, search_type in SearchTypes.__members__.items():
if section_exists(soup, search_type):
return get_first_film(soup, search_type, year=year, session=session)
if limit_to == search_type:
return
@@ -2,7 +2,8 @@
OS_PLEX_USERAGENT = 'plexapp.com v9.0'
DEPENDENCY_MODULE_NAMES = ['subliminal', 'subliminal_patch', 'enzyme', 'guessit', 'subzero', 'libfilebot', 'cfscrape']
DEPENDENCY_MODULE_NAMES = ['subliminal', 'subliminal_patch', 'enzyme', 'guessit', 'subzero', 'libfilebot',
'cloudscraper']
PERSONAL_MEDIA_IDENTIFIER = "com.plexapp.agents.none"
PLUGIN_IDENTIFIER_SHORT = "subzero"
PLUGIN_IDENTIFIER = "com.plexapp.agents.%s" % PLUGIN_IDENTIFIER_SHORT
+40 -1
View File
@@ -1,16 +1,42 @@
# coding=utf-8
import types
import re
from babelfish.exceptions import LanguageError
from babelfish import Language as Language_, basestr
from babelfish import Language as Language_, basestr, LANGUAGE_MATRIX
repl_map = {
"dk": "da",
"nld": "nl",
"english": "en",
"alb": "sq",
"arm": "hy",
"baq": "eu",
"bur": "my",
"chi": "zh",
"cze": "cs",
"dut": "nl",
"fre": "fr",
"geo": "ka",
"ger": "de",
"gre": "el",
"ice": "is",
"mac": "mk",
"mao": "mi",
"may": "ms",
"per": "fa",
"rum": "ro",
"slo": "sk",
"tib": "bo",
}
ALPHA2_LIST = list(set(filter(lambda x: x, map(lambda x: x.alpha2, LANGUAGE_MATRIX)))) + list(repl_map.values())
ALPHA3b_LIST = list(set(filter(lambda x: x, map(lambda x: x.alpha3, LANGUAGE_MATRIX)))) + \
list(set(filter(lambda x: len(x) == 3, list(repl_map.keys()))))
FULL_LANGUAGE_LIST = ALPHA2_LIST + ALPHA3b_LIST
def language_from_stream(l):
if not l:
raise LanguageError()
@@ -115,3 +141,16 @@ class Language(Language_):
return Language(*Language_.fromietf(s).__getstate__())
return Language(*Language_.fromalpha3b(s).__getstate__())
IETF_MATCH = ".+\.([^-.]+)(?:-[A-Za-z]+)?$"
ENDSWITH_LANGUAGECODE_RE = re.compile("\.([^-.]{2,3})(?:-[A-Za-z]{2,})?$")
def match_ietf_language(s, ietf=False):
language_match = re.match(".+\.([^\.]+)$" if not ietf
else IETF_MATCH, s)
if language_match and len(language_match.groups()) == 1:
language = language_match.groups()[0]
return language
return s
@@ -107,6 +107,12 @@ class Dicked(object):
for key, value in entries.iteritems():
self.__dict__[key] = (Dicked(**value) if isinstance(value, dict) else value)
def has(self, key):
return self._entries is not None and key in self._entries
def get(self, key, default=None):
return self._entries.get(key, default) if self._entries else default
def __repr__(self):
return str(self)
File diff suppressed because one or more lines are too long
@@ -36,6 +36,7 @@ SZ_FIX_DATA = {
u" l ": u" I ",
u"'sjust": u"'s just",
u"'tjust": u"'t just",
u"\";": u"'s",
},
"WholeWords": {
u"I'11": u"I'll",
@@ -0,0 +1,7 @@
# coding=utf-8
class EmptyEntryError(Exception):
pass
class EmptyLineError(Exception):
pass
@@ -6,7 +6,8 @@ import pysubs2
import logging
import time
from mods import EMPTY_TAG_PROCESSOR, EmptyEntryError
from mods import EMPTY_TAG_PROCESSOR
from exc import EmptyEntryError
from registry import registry
from subzero.language import Language
@@ -293,15 +294,18 @@ class SubtitleModifications(object):
end_tag = line[-5:]
line = line[:-5]
last_procs_mods = []
# fixme: this double loop is ugly
for order, identifier, args in mods:
mod = self.initialized_mods[identifier]
try:
line = mod.modify(line.strip(), entry=entry.text, debug=self.debug, parent=self, index=index,
line = mod.modify(line.strip(), entry=t, debug=self.debug, parent=self, index=index,
**args)
except EmptyEntryError:
if self.debug:
logger.debug(u"%d: %s: %r -> ''", index, identifier, entry.text)
logger.debug(u"%d: %s: %r -> ''", index, identifier, t)
skip_entry = True
break
@@ -312,6 +316,33 @@ class SubtitleModifications(object):
break
applied_mods.append(identifier)
if mod.last_processors:
last_procs_mods.append([identifier, args])
if skip_entry:
lines = []
break
if skip_line:
continue
for identifier, args in last_procs_mods:
mod = self.initialized_mods[identifier]
try:
line = mod.modify(line.strip(), entry=t, debug=self.debug, parent=self, index=index,
procs=["last_process"], **args)
except EmptyEntryError:
if self.debug:
logger.debug(u"%d: %s: %r -> ''", index, identifier, t)
skip_entry = True
break
if not line:
if self.debug:
logger.debug(u"%d: %s: %r -> ''", index, identifier, old_line)
skip_line = True
break
if skip_entry:
lines = []
@@ -21,6 +21,7 @@ class SubtitleModification(object):
pre_processors = []
processors = []
post_processors = []
last_processors = []
languages = []
def __init__(self, parent):
@@ -67,15 +68,16 @@ class SubtitleModification(object):
def post_process(self, content, debug=False, parent=None, **kwargs):
return self._process(content, self.post_processors, debug=debug, parent=parent, **kwargs)
def modify(self, content, debug=False, parent=None, **kwargs):
def modify(self, content, debug=False, parent=None, procs=None, **kwargs):
if not content:
return
new_content = content
for method in ("pre_process", "process", "post_process"):
for method in procs or ("pre_process", "process", "post_process"):
if not new_content:
return
new_content = getattr(self, method)(new_content, debug=debug, parent=parent, **kwargs)
new_content = self._process(new_content, getattr(self, "%sors" % method),
debug=debug, parent=parent, **kwargs)
return new_content
@@ -105,5 +107,3 @@ empty_line_post_processors = [
]
class EmptyEntryError(Exception):
pass
@@ -1,14 +1,17 @@
# coding=utf-8
import re
import logging
from collections import OrderedDict
from subzero.language import Language
from subzero.modification.mods import SubtitleTextModification, empty_line_post_processors, SubtitleModification
from subzero.modification.processors import FuncProcessor
from subzero.modification.processors.re_processor import NReProcessor
from subzero.modification import registry
from tld import get_tld
logger = logging.getLogger(__name__)
ENGLISH = Language("eng")
@@ -28,7 +31,7 @@ class CommonFixes(SubtitleTextModification):
NReProcessor(re.compile(r'(?u)(\w|\b|\s|^)(-\s?-{1,2})'), ur"\1", name="CM_multidash"),
# line = _/-/\s
NReProcessor(re.compile(r'(?u)(^\W*[-_.:>~]+\W*$)'), "", name="CM_non_word_only"),
NReProcessor(re.compile(r'(?u)(^\W*[-_.:<>~"\']+\W*$)'), "", name="CM_non_word_only"),
# remove >>
NReProcessor(re.compile(r'(?u)^\s?>>\s*'), "", name="CM_leading_crocodiles"),
@@ -37,7 +40,7 @@ class CommonFixes(SubtitleTextModification):
NReProcessor(re.compile(r'(?u)(^\W*:\s*(?=\w+))'), "", name="CM_empty_colon_start"),
# fix music symbols
NReProcessor(re.compile(ur'(?u)(^[-\s>~]*[*#¶]+\s*)|(\s*[*#¶]+\s*$)'),
NReProcessor(re.compile(ur'(?u)(^[-\s>~]*[*#¶]+\s+)|(\s*[*#¶]+\s*$)'),
lambda x: u"" if x.group(1) else u"",
name="CM_music_symbols"),
@@ -113,7 +116,9 @@ class CommonFixes(SubtitleTextModification):
NReProcessor(re.compile(r'(?u)(?:(?<=^)|(?<=\w)) +([!?.,](?![!?.,]| \.))'), r"\1", name="CM_punctuation_space"),
# add space after punctuation
NReProcessor(re.compile(r'(?u)([!?.,:])([A-zÀ-ž]{2,})'), r"\1 \2", name="CM_punctuation_space2"),
NReProcessor(re.compile(r'(?u)(([^\s]*)([!?.,:])([A-zÀ-ž]{2,}))'),
lambda match: u"%s%s %s" % (match.group(2), match.group(3), match.group(4)) if not get_tld(match.group(1), fail_silently=True, fix_protocol=True) else match.group(1),
name="CM_punctuation_space2"),
# fix lowercase I in english
NReProcessor(re.compile(r'(?u)(\b)i(\b)'), r"\1I\2", name="CM_EN_lowercase_i",
@@ -178,7 +183,104 @@ class FixUppercase(SubtitleModification):
entry.plaintext = self.capitalize(entry.plaintext)
class FixIncremental(SubtitleModification):
identifier = "fix_incremental"
description = "Fixes inremental-repeating subtitles"
modifies_whole_file = True
exclusive = True
long_description = "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"
def modify(self, content, debug=False, parent=None, **kwargs):
prev_entry = None
for entry in parent.f:
subs = []
for sub in entry.text.split("\N"):
if prev_entry and prev_entry.text and prev_entry.text.lower().endswith(sub.lower()):
if debug:
logger.debug(u"Skipping incremental/dup: %s" % sub)
continue
subs.append(sub)
if subs:
entry.text = "\N".join(subs)
prev_entry = entry
class FixShort(SubtitleModification):
identifier = "fix_short"
description = "ASDasdasdasdasdd"
modifies_whole_file = True
exclusive = True
long_description = "adsadsdasdsadsa"
def modify(self, content, debug=False, parent=None, **kwargs):
prev_entry = None
prev_entry_dur = None
max_duration = 500
max_line_len = 200
max_lines = 3
entries = []
last_lines = []
for index, entry in enumerate(parent.f):
current_new_lines = []
if not last_lines and parent.f[index-1]:
print "YOO"
# find last lines
last_lines = parent.f[index-1].text.split("\N")
has_space = len(last_lines) < max_lines
last_line = ""
# go through each line and pack them
for line in entry.text.split("\N"):
new_line = ""
if line:
if last_line != line and last_line and len(last_line + line) <= max_line_len:
# new line plus line fits
if re.match(".+\W$", line):
if last_line.endswith(" "):
new_line = last_line + line
else:
new_line = last_line + " " + line
logger.debug("MERGING '%s' with '%s' to '%s'", last_line, line, new_line)
else:
new_line = line
last_line = new_line
current_new_lines.append(new_line)
# merge entries
if prev_entry:
#print prev_entry.duration, max_duration, len(new_lines), max_lines
if prev_entry.duration < max_duration and len(current_new_lines) < max_lines:
#len(prev_entry.text) < max_len
print "HIT", prev_entry.text, " + ", entry.text
entry_text = prev_entry.text + "\N" + "\N".join(current_new_lines)
else:
entry_text = "\N".join(current_new_lines)
else:
entry_text = "\N".join(current_new_lines)
#prev_entry = entry.copy()
if not prev_entry:
prev_entry = entry.copy()
continue
new_entry = prev_entry.copy()
new_entry.text = entry_text
prev_entry = new_entry.copy()
entries.append(new_entry)
#new_entries.append(entry.copy())
parent.f.entries = entries
registry.register(CommonFixes)
registry.register(RemoveTags)
registry.register(ReverseRTL)
registry.register(FixUppercase)
registry.register(FixIncremental)
registry.register(FixShort)
@@ -1,7 +1,8 @@
# coding=utf-8
import re
from subzero.modification.mods import SubtitleTextModification, empty_line_post_processors, EmptyEntryError, TAG
from subzero.modification.mods import SubtitleTextModification, empty_line_post_processors, TAG
from subzero.modification.exc import EmptyEntryError
from subzero.modification.processors.re_processor import NReProcessor
from subzero.modification import registry
@@ -46,14 +47,14 @@ class HearingImpaired(SubtitleTextModification):
name="HI_before_colon_noncaps"),
# brackets (only remove if at least 3 chars in brackets)
NReProcessor(re.compile(ur'(?sux)-?%(t)s[([][^([)\]]+?(?=[A-zÀ-ž"\'.]{3,})[^([)\]]+[)\]][\s:]*%(t)s' %
NReProcessor(re.compile(ur'(?sux)-?%(t)s["\']*[([][^([)\]]+?(?=[A-zÀ-ž"\'.]{3,})[^([)\]]+[)\]]["\']*[\s:]*%(t)s' %
{"t": TAG}), "", name="HI_brackets"),
NReProcessor(re.compile(ur'(?sux)-?%(t)s[([]%(t)s(?=[A-zÀ-ž"\'.]{3,})[^([)\]]+%(t)s$' % {"t": TAG}),
"", name="HI_bracket_open_start"),
#NReProcessor(re.compile(ur'(?sux)-?%(t)s[([]%(t)s(?=[A-zÀ-ž"\'.]{3,})[^([)\]]+%(t)s$' % {"t": TAG}),
# "", name="HI_bracket_open_start"),
NReProcessor(re.compile(ur'(?sux)-?%(t)s(?=[A-zÀ-ž"\'.]{3,})[^([)\]]+[)\]][\s:]*%(t)s' % {"t": TAG}), "",
name="HI_bracket_open_end"),
#NReProcessor(re.compile(ur'(?sux)-?%(t)s(?=[A-zÀ-ž"\'.]{3,})[^([)\]]+[)\]][\s:]*%(t)s' % {"t": TAG}), "",
# name="HI_bracket_open_end"),
# text before colon (and possible dash in front), max 11 chars after the first whitespace (if any)
# NReProcessor(re.compile(r'(?u)(^[A-z\-\'"_]+[\w\s]{0,11}:[^0-9{2}][\s]*)'), "", name="HI_before_colon"),
@@ -73,7 +74,7 @@ class HearingImpaired(SubtitleTextModification):
supported=lambda p: not p.only_uppercase),
# remove MAN:
NReProcessor(re.compile(ur'(?suxi)(.*MAN:\s*)'), "", name="HI_remove_man"),
NReProcessor(re.compile(ur'(?suxi)(\b(?:WO)MAN:\s*)'), "", name="HI_remove_man"),
# dash in front
# NReProcessor(re.compile(r'(?u)^\s*-\s*'), "", name="HI_starting_dash"),
@@ -81,13 +82,18 @@ class HearingImpaired(SubtitleTextModification):
# all caps at start before new sentence
NReProcessor(re.compile(ur'(?u)^(?=[A-ZÀ-Ž]{4,})[A-ZÀ-Ž-_\s]+\s([A-ZÀ-Ž][a-zà-ž].+)'), r"\1",
name="HI_starting_upper_then_sentence", supported=lambda p: not p.only_uppercase),
# remove music symbols
NReProcessor(re.compile(ur'(?u)(^%(t)s[*#¶♫♪\s]*%(t)s[*#¶♫♪\s]+%(t)s[*#¶♫♪\s]*%(t)s$)' % {"t": TAG}),
"", name="HI_music_symbols_only"),
]
post_processors = empty_line_post_processors
last_processors = [
# remove music symbols
NReProcessor(re.compile(ur'(?u)(^%(t)s[*#¶♫♪\s]*%(t)s[*#¶♫♪\s]+%(t)s[*#¶♫♪\s]*%(t)s$)' % {"t": TAG}),
"", name="HI_music_symbols_only"),
# remove music entries
NReProcessor(re.compile(ur'(?ums)(^[-\s>~]*[*#¶♫♪]+\s*.+|.+\s*[*#¶♫♪]+\s*$)'),
"", name="HI_music", entry=True),
]
registry.register(HearingImpaired)
@@ -10,7 +10,7 @@ class Processor(object):
supported = None
enabled = True
def __init__(self, name=None, parent=None, supported=None):
def __init__(self, name=None, parent=None, supported=None, **kwargs):
self.name = name
self.parent = parent
self.supported = supported if supported else lambda parent: True
@@ -35,7 +35,7 @@ class Processor(object):
class FuncProcessor(Processor):
func = None
def __init__(self, func, name=None, parent=None, supported=None):
def __init__(self, func, name=None, parent=None, supported=None, **kwargs):
super(FuncProcessor, self).__init__(name=name, supported=supported)
self.func = func
@@ -2,6 +2,7 @@
import re
import logging
from subzero.modification.exc import EmptyEntryError
from subzero.modification.processors import Processor
logger = logging.getLogger(__name__)
@@ -14,13 +15,22 @@ class ReProcessor(Processor):
pattern = None
replace_with = None
def __init__(self, pattern, replace_with, name=None, supported=None):
def __init__(self, pattern, replace_with, name=None, supported=None, entry=False, **kwargs):
super(ReProcessor, self).__init__(name=name, supported=supported)
self.pattern = pattern
self.replace_with = replace_with
self.use_entry = entry
def process(self, content, debug=False, **kwargs):
return self.pattern.sub(self.replace_with, content)
def process(self, content, debug=False, entry=None, **kwargs):
if not self.use_entry:
return self.pattern.sub(self.replace_with, content)
ret = self.pattern.sub(self.replace_with, entry)
if not ret:
raise EmptyEntryError()
elif ret != entry:
return ret
return content
class NReProcessor(ReProcessor):
@@ -36,7 +46,7 @@ class MultipleWordReProcessor(ReProcessor):
}
replaces found key in pattern with the corresponding value in data
"""
def __init__(self, snr_dict, name=None, parent=None, supported=None):
def __init__(self, snr_dict, name=None, parent=None, supported=None, **kwargs):
super(ReProcessor, self).__init__(name=name, supported=supported)
self.snr_dict = snr_dict
@@ -12,7 +12,7 @@ class StringProcessor(Processor):
String replacement processor base
"""
def __init__(self, search, replace, name=None, parent=None, supported=None):
def __init__(self, search, replace, name=None, parent=None, supported=None, **kwargs):
super(StringProcessor, self).__init__(name=name, supported=supported)
self.search = search
self.replace = replace
@@ -31,7 +31,7 @@ class MultipleLineProcessor(Processor):
"data": {"old_value": "new_value"}
}
"""
def __init__(self, snr_dict, name=None, parent=None, supported=None):
def __init__(self, snr_dict, name=None, parent=None, supported=None, **kwargs):
super(MultipleLineProcessor, self).__init__(name=name, supported=supported)
self.snr_dict = snr_dict
+6 -4
View File
@@ -17,7 +17,8 @@ def has_external_subtitle(part_id, stored_subs, language):
def set_existing_languages(video, video_info, external_subtitles=False, embedded_subtitles=False, known_embedded=None,
stored_subs=None, languages=None, only_one=False, known_metadata_subs=None):
stored_subs=None, languages=None, only_one=False, known_metadata_subs=None,
match_strictness="strict"):
logger.debug(u"Determining existing subtitles for %s", video.name)
external_langs_found = set()
@@ -27,7 +28,8 @@ def set_existing_languages(video, video_info, external_subtitles=False, embedded
external_langs_found = known_metadata_subs
external_langs_found.update(set(search_external_subtitles(video.name, languages=languages,
only_one=only_one).values()))
only_one=only_one,
match_strictness=match_strictness).values()))
# found external subtitles should be considered?
if external_subtitles:
@@ -52,10 +54,10 @@ def set_existing_languages(video, video_info, external_subtitles=False, embedded
video.subtitle_languages.add(language)
def parse_video(fn, hints, skip_hashing=False, dry_run=False, providers=None):
def parse_video(fn, hints, skip_hashing=False, dry_run=False, providers=None, hash_from=None):
logger.debug("Parsing video: %s, hints: %s", os.path.basename(fn), hints)
return scan_video(fn, hints=hints, dont_use_actual_file=dry_run, providers=providers,
skip_hashing=skip_hashing)
skip_hashing=skip_hashing, hash_from=hash_from)
def refine_video(video, no_refining=False, refiner_settings=None):
+2
View File
@@ -19,6 +19,8 @@ I can't keep running. L can't!
<b>i don't know. Some kind of wrong "1 00" number---
of signal, drawing the Tardis off.... course.</b>
# I'm singing in the rain
www.website.com
www.nowebsite.badlol
4
00:00:16,099 --> 00:00:17,224
+14
View File
@@ -0,0 +1,14 @@
# -*- coding: utf-8 -*-
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals
from .utils import get_fld, get_tld, get_tld_names, is_tld, parse_tld, Result, update_tld_names
__title__ = u'tld'
__version__ = u'0.11.10'
__author__ = u'Artur Barseghyan'
__copyright__ = u'2013-2019 Artur Barseghyan'
__license__ = u'MPL-1.1 OR GPL-2.0-only OR LGPL-2.1-or-later'
__all__ = (u'get_fld', u'get_tld', u'get_tld_names', u'is_tld',
u'parse_tld', u'Result', u'update_tld_names')
+57
View File
@@ -0,0 +1,57 @@
# -*- coding: utf-8 -*-
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals
from six import with_metaclass as _py_backwards_six_withmetaclass
from codecs import open as codecs_open
try:
from urllib.request import urlopen
except ImportError:
from six.moves.urllib.request import urlopen as urlopen
from .exceptions import TldIOError, TldImproperlyConfigured
from .helpers import project_dir
from .registry import Registry
__author__ = u'Artur Barseghyan'
__copyright__ = u'2013-2019 Artur Barseghyan'
__license__ = u'MPL-1.1 OR GPL-2.0-only OR LGPL-2.1-or-later'
__all__ = (u'BaseTLDSourceParser',)
class BaseTLDSourceParser(
_py_backwards_six_withmetaclass(Registry, *[object])):
u'Base TLD source parser.'
uid = None
source_url = None
local_path = None
@classmethod
def validate(cls):
u'Constructor.'
if (not cls.uid):
raise TldImproperlyConfigured(
u'The `uid` property of the TLD source parser shall be defined.')
@classmethod
def get_tld_names(cls, fail_silently=False, retry_count=0):
u'Get tld names.\n\n :param fail_silently:\n :param retry_count:\n :return:\n '
cls.validate()
raise NotImplementedError(
u'Your TLD source parser shall implement `get_tld_names` method.')
@classmethod
def update_tld_names(cls, fail_silently=False):
u'Update the local copy of the TLD file.\n\n :param fail_silently:\n :return:\n '
try:
remote_file = urlopen(cls.source_url)
local_file = codecs_open(project_dir(
cls.local_path), u'wb', encoding='utf8')
local_file.write(remote_file.read().decode(u'utf8'))
local_file.close()
remote_file.close()
except Exception as err:
if fail_silently:
return False
raise TldIOError(err)
return True

Some files were not shown because too many files have changed in this diff Show More