mirror of
https://github.com/kovidgoyal/calibre.git
synced 2026-05-08 10:32:28 +00:00
Kovid Goyal
68 lines
3.1 KiB
Python
68 lines
3.1 KiB
Python
import re
|
|
|
|
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
|
|
|
|
class aktualneRecipe(BasicNewsRecipe):
|
|
__author__ = 'bubak'
|
|
title = u'aktualne.cz'
|
|
publisher = u'Centrum holdings'
|
|
description = 'aktuálně.cz'
|
|
oldest_article = 1
|
|
max_articles_per_feed = 20
|
|
|
|
feeds = [
|
|
(u'Domácí', u'https://zpravy.aktualne.cz/rss/domaci/'),
|
|
(u'Zprávy', u'https://zpravy.aktualne.cz/rss/'),
|
|
(u'Zahraniční zprávy', u'https://zpravy.aktualne.cz/rss/zahranici/'),
|
|
(u'Ekonomika', u'https://zpravy.aktualne.cz/rss/ekonomika/'),
|
|
(u'Blogy a názory', u'https://nazory.aktualne.cz/rss/')
|
|
]
|
|
|
|
language = 'cs'
|
|
cover_url = 'http://img.aktualne.centrum.cz/design/akt4/o/l/logo-akt-ciste.png'
|
|
remove_javascript = True
|
|
no_stylesheets = True
|
|
|
|
remove_attributes = []
|
|
remove_tags_before = dict(name='h1', attrs={'class':['titulek-clanku']})
|
|
remove_tags_after = dict(name='div', attrs={'class':['e-articles-show-body-bottom__share']})
|
|
filter_regexps = [r'img.aktualne.centrum.cz']
|
|
remove_tags = [dict(name='div', attrs={'id':['social-bookmark']}),
|
|
dict(name='div', attrs={'class':['box1', 'svazane-tagy']}),
|
|
dict(name='div', attrs={'class':'itemcomment id0'}),
|
|
dict(name='div', attrs={'class':'hlavicka'}),
|
|
dict(name='div', attrs={'class':'hlavni-menu'}),
|
|
dict(name='div', attrs={'class':'top-standard-brand-obal'}),
|
|
dict(name='div', attrs={'class':['breadcrumb', 'hlavicka clearfix', 'e-ui-sub-menu',
|
|
'e-web-aktualne-articles-show-header__authors-and-share', 'f-tiptap-node',
|
|
'e-web-aktualne-articles-show__recommended']}),
|
|
dict(name='div', attrs={'id':'start-standard'}),
|
|
dict(name='div', attrs={'id':'forum'}),
|
|
dict(name='ul', attrs={'id':'nav-breadcrumb'}),
|
|
dict(name='header'),
|
|
dict(name='footer'),
|
|
dict(name='aside'),
|
|
dict(name='span', attrs={'class':'akce'}),
|
|
dict(name='span', attrs={'class':'odrazka vetsi'}),
|
|
dict(name='div', attrs={'class':'boxP'}),
|
|
dict(name='div', attrs={'class':'box2'})]
|
|
preprocess_regexps = [
|
|
(re.compile(r'<div class="(contenttitle"|socialni-site|wiki|facebook-promo|facebook-like-button"|meta-akce).*',
|
|
re.DOTALL|re.IGNORECASE), lambda match: '</body>'),
|
|
(re.compile(r'<div class="[^"]*poutak-clanek-trojka".*', re.DOTALL|re.IGNORECASE), lambda match: '</body>'),
|
|
(re.compile(r'<[aA]\s[^>]*>', re.DOTALL|re.IGNORECASE), lambda match: '')]
|
|
|
|
keep_only_tags = []
|
|
|
|
visited_urls = {}
|
|
def get_article_url(self, article):
|
|
url = BasicNewsRecipe.get_article_url(self, article)
|
|
if url in self.visited_urls:
|
|
self.log.debug('Ignoring duplicate: ' + url)
|
|
return None
|
|
else:
|
|
self.visited_urls[url] = True
|
|
self.log.debug('Accepting: ' + url)
|
|
return url
|