mirror of
https://github.com/kovidgoyal/calibre.git
synced 2026-05-08 10:32:28 +00:00
Kovid Goyal
237 lines
8.6 KiB
Python
237 lines
8.6 KiB
Python
#!/usr/bin/env python
|
|
# vim:fileencoding=utf-8
|
|
import json
|
|
import time
|
|
from urllib.parse import quote, urlencode
|
|
|
|
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class WSJ(BasicNewsRecipe):
|
|
title = 'The Wall Street Journal'
|
|
__author__ = 'unkn0wn'
|
|
description = (
|
|
'The Print Edition of WSJ. The Wall Street Journal is your source '
|
|
'for breaking news, analysis and insights from the U.S. and '
|
|
"around the world, the world's leading business and finance publication."
|
|
)
|
|
language = 'en_US'
|
|
masthead_url = 'https://s.wsj.net/media/wsj_amp_masthead_lg.png'
|
|
encoding = 'utf-8'
|
|
no_javascript = True
|
|
no_stylesheets = True
|
|
remove_attributes = ['style', 'height', 'width']
|
|
resolve_internal_links = True
|
|
|
|
recipe_specific_options = {
|
|
'date': {
|
|
'short': 'The date of the edition to download (YYYY-MM-DD format)\nOnly the past 6 editions will be available ',
|
|
'long': 'For example, 2024-05-13',
|
|
},
|
|
'res': {
|
|
'short': 'For hi-res images, select a resolution from the\nfollowing options: 800, 1000, 1200 or 1500',
|
|
'long': 'This is useful for non e-ink devices, and for a lower file size\nthan the default, use 400 or 300.',
|
|
'default': '600',
|
|
},
|
|
}
|
|
|
|
extra_css = '''
|
|
#big-top-caption { font-size:small; text-align:center; }
|
|
[data-type:"tagline"] { font-style:italic; color:#202020; }
|
|
.auth, time { font-size:small; }
|
|
.sub, em, i { color: #202020; }
|
|
'''
|
|
|
|
keep_only_tags = [
|
|
dict(name=['h1', 'h2']),
|
|
dict(attrs={'aria-describedby': 'big-top-caption'}),
|
|
dict(attrs={'id': 'big-top-caption'}),
|
|
dict(name='article', attrs={'style': lambda x: x and 'article-body' in x}),
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(attrs={'data-type': ['inset', 'video']}),
|
|
dict(attrs={'data-testid': 'ad-container'}),
|
|
dict(attrs={'data-spotim-app': 'conversation'}),
|
|
dict(name=['button', 'svg', 'old-script', 'video']),
|
|
dict(
|
|
attrs={
|
|
'aria-label': [
|
|
'Sponsored Offers',
|
|
'Listen To Article',
|
|
'What to Read Next',
|
|
'Utility Bar',
|
|
'Conversation',
|
|
'List of Comments',
|
|
'Comment',
|
|
'JR More Articles',
|
|
]
|
|
}
|
|
),
|
|
dict(
|
|
attrs={
|
|
'data-spot-im-class': [
|
|
'message-text',
|
|
'messages-list',
|
|
'message-view',
|
|
'conversation-root',
|
|
]
|
|
}
|
|
),
|
|
dict(
|
|
attrs={
|
|
'id': lambda x: x
|
|
and x.startswith((
|
|
'comments_sector',
|
|
'wrapper-INLINE',
|
|
'audio-tag-inner-audio-',
|
|
'article-comments-tool',
|
|
))
|
|
}
|
|
),
|
|
dict(name='div', attrs={'data-message-depth': True}),
|
|
]
|
|
|
|
articles_are_obfuscated = True
|
|
|
|
def get_obfuscated_article(self, url):
|
|
from calibre.scraper.simple import read_url
|
|
raw = read_url([], 'https://archive.is/latest/' + url)
|
|
return {'data': raw, 'url': url}
|
|
|
|
def preprocess_html(self, soup):
|
|
res = '?width=600'
|
|
w = self.recipe_specific_options.get('res')
|
|
if w and isinstance(w, str):
|
|
res = '?width=' + w
|
|
for img in soup.findAll('img', attrs={'currentsourceurl': True}):
|
|
img['src'] = img['currentsourceurl'].split('?')[0] + res
|
|
for p in soup.findAll('div', attrs={'data-type': ['paragraph', 'image']}):
|
|
p.name = 'p'
|
|
for a in soup.findAll('a', href=True):
|
|
a['href'] = 'http' + a['href'].split('http')[-1]
|
|
for figc in soup.findAll('figcaption'):
|
|
figc['id'] = 'big-top-caption'
|
|
if name := soup.find('h2', attrs={'itemprop': 'name'}):
|
|
name.extract()
|
|
for h2 in soup.findAll('h2'):
|
|
if self.tag_to_string(h2).startswith(('What to Read Next', 'Conversation')):
|
|
h2.extract()
|
|
h2.name = 'h3'
|
|
h2['class'] = 'sub'
|
|
for ph in soup.findAll('a', attrs={'data-type': ['phrase', 'link']}):
|
|
if div := ph.findParent('div'):
|
|
div.name = 'span'
|
|
for auth in soup.findAll(
|
|
'a', attrs={'aria-label': lambda x: x and x.startswith('Author page')}
|
|
):
|
|
if div := auth.find_previous_sibling('div'):
|
|
div.name = 'span'
|
|
if parent := auth.findParent('div'):
|
|
parent['class'] = 'auth'
|
|
for x in soup.findAll('ufc-follow-author-widget'):
|
|
if y := x.findParent('div'):
|
|
y.extract()
|
|
return soup
|
|
|
|
def get_browser(self, *args, **kw):
|
|
br = BasicNewsRecipe.get_browser(self, *args, **kw)
|
|
br.addheaders += [
|
|
('apollographql-client-name', 'wsj-mobile-android-release'),
|
|
]
|
|
return br
|
|
|
|
def _download_cover(self):
|
|
import os
|
|
from contextlib import closing
|
|
|
|
from calibre import browser
|
|
from calibre.utils.img import save_cover_data_to
|
|
|
|
br = browser()
|
|
raw = br.open(
|
|
'https://frontpages.freedomforum.org/newspapers/wsj-The_Wall_Street_Journal'
|
|
)
|
|
soup = BeautifulSoup(raw.read())
|
|
cu = soup.find(
|
|
'img',
|
|
attrs={
|
|
'alt': 'Front Page Image',
|
|
'src': lambda x: x and x.endswith('front-page-large.jpg'),
|
|
},
|
|
)['src'].replace('-large', '-medium')
|
|
self.report_progress(1, _('Downloading cover from %s') % cu)
|
|
with closing(br.open(cu, timeout=self.timeout)) as r:
|
|
cdata = r.read()
|
|
cpath = os.path.join(self.output_dir, 'cover.jpg')
|
|
save_cover_data_to(cdata, cpath)
|
|
self.cover_path = cpath
|
|
|
|
def parse_index(self):
|
|
query = {
|
|
'operationName': 'IssueQuery',
|
|
'variables': '{"publication":"WSJ","region":"US","masthead":"ITPNEXTGEN"}',
|
|
'extensions': '{"persistedQuery":{"version":1,"sha256Hash":"d938226e7d1c1fff050e7d084c72179e2713dcf4736d3a442c618c55b896f847"}}',
|
|
}
|
|
url = 'https://shared-data.dowjones.io/gateway/graphql?' + urlencode(
|
|
query, safe='()!', quote_via=quote
|
|
)
|
|
raw = self.index_to_soup(url, raw=True)
|
|
|
|
cat_data = json.loads(raw)['data']['mobileIssuesByMasthead']
|
|
edit = [x['datedLabel'] for x in cat_data][1:]
|
|
self.log('**Past Editions available : ' + ' | '.join(edit))
|
|
|
|
past_edition = self.recipe_specific_options.get('date')
|
|
|
|
for itm in cat_data:
|
|
if past_edition and isinstance(past_edition, str):
|
|
if past_edition in itm['publishedDateUtc']:
|
|
self.timefmt = ' [' + itm['datedLabel']
|
|
sections_ = itm['sections']
|
|
break
|
|
self.timefmt = f' [{itm["datedLabel"]}]'
|
|
sections_ = itm['sections']
|
|
break
|
|
|
|
self.log('Downloading ', self.timefmt)
|
|
|
|
feeds = []
|
|
|
|
for sec in sections_[:-1]:
|
|
time.sleep(3)
|
|
section = sec['label']
|
|
self.log(section)
|
|
cont_id = sec['key']
|
|
|
|
query = {
|
|
'operationName': 'SectionQuery',
|
|
'variables': '{{"id":"{}"}}'.format(cont_id),
|
|
'extensions': '{"persistedQuery":{"version":1,"sha256Hash":"207fe93376f379bf223ed2734cf9313a28291293366a803db923666fa6b45026"}}',
|
|
}
|
|
sec_url = 'https://shared-data.dowjones.io/gateway/graphql?' + urlencode(
|
|
query, safe='()!', quote_via=quote
|
|
)
|
|
sec_raw = self.index_to_soup(sec_url, raw=True)
|
|
|
|
sec_data = json.loads(sec_raw)['data']['summaryCollectionContent'][
|
|
'collectionItems'
|
|
]
|
|
|
|
articles = []
|
|
|
|
for art in sec_data:
|
|
for arts in art['collectionItems']:
|
|
mobi = arts['content']['mobileSummary']
|
|
title = mobi['headline']['text']
|
|
try:
|
|
desc = mobi['description']['content']['text']
|
|
except TypeError:
|
|
desc = ''
|
|
url = arts['content']['sourceUrl']
|
|
self.log(' ', title, '\n\t', desc, '\n\t', url)
|
|
articles.append({'title': title, 'description': desc, 'url': url})
|
|
feeds.append((section, articles))
|
|
return feeds
|