Merge branch 'master' of https://github.com/unkn0w7n/calibre

recipes/bloomberg-business-week.recipe

@@ -68,10 +68,10 @@ class Bloomberg(BasicNewsRecipe):
     }
 
     remove_tags = [
-        dict(name=['button', 'svg', 'meta']),
+        dict(name=['button', 'svg', 'meta', 'iframe']),
         dict(name='div', attrs={'id':['bb-that', 'bb-nav']}),
         dict(attrs={'data-image-type':'audio'}),
-        classes('twitter-logo bb-global-footer __sticky__audio__bar__portal__ css--social-wrapper-outer')
+        classes('twitter-logo bb-global-footer __sticky__audio__bar__portal__ css--social-wrapper-outer bplayer-container')
     ]
 
     extra_css = '''

recipes/bloomberg.recipe

@@ -1,3 +1,6 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
+
 import json
 import time
 from datetime import datetime, timedelta
@@ -61,10 +64,10 @@ class Bloomberg(BasicNewsRecipe):
     cover_url = 'https://assets.bwbx.io/images/users/iqjWHBFdfxIU/ivUxvlPidC3M/v0/600x-1.jpg'
 
     remove_tags = [
-        dict(name=['button', 'svg', 'meta']),
+        dict(name=['button', 'svg', 'meta', 'iframe']),
         dict(name='div', attrs={'id':['bb-that', 'bb-nav']}),
         dict(attrs={'data-image-type':'audio'}),
-        classes('twitter-logo bb-global-footer __sticky__audio__bar__portal__ css--social-wrapper-outer')
+        classes('twitter-logo bb-global-footer __sticky__audio__bar__portal__ css--social-wrapper-outer bplayer-container')
     ]
 
     extra_css = '''

recipes/hindu.recipe

@@ -34,7 +34,7 @@ class TheHindu(BasicNewsRecipe):
     recipe_specific_options = {
         'location': {
             'short': 'The name of the local edition',
-            'long': ('If The Hindu is available in your local town/city,\n'
+            'long': ('If The Hindu is available in your local town/city, '
                      'set this to your location, for example, hyderabad\n'
                      'Available Editions: bengaluru, chennai, coimbatore, delhi, '
                      'erode, hyderabad, international, kochi, kolkata,\n'

recipes/hindustan_times_print.recipe

@@ -26,7 +26,7 @@ class ht(BasicNewsRecipe):
     recipe_specific_options = {
         'location': {
             'short': 'The name of the local edition',
-            'long': ('If The Hindustan Times is available in your local town/city,\n'
+            'long': ('If The Hindustan Times is available in your local town/city, '
                      'set this to your location, for example, Delhi\nAvailable Editions:'
                      'Delhi, Mumbai, Chandigarh, Lucknow, Patna, Bengaluru, Pune, Gurgaon,'
                      'Ludhiana, Rajasthan, Amritsar,\nEast UP, Haryana, Jammu, Navi Mumbai,'

recipes/indian_express.recipe

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+# vim:fileencoding=utf-8
 from datetime import datetime, timedelta
 
 from calibre.utils.date import parse_date
@@ -116,10 +118,10 @@ class IndianExpress(BasicNewsRecipe):
 
     def get_cover_url(self):
         soup = self.index_to_soup(
-            'https://www.magzter.com/IN/The-Indian-Express-Ltd./The-Indian-Express-Mumbai/Newspaper/'
+            'https://www.readwhere.com/newspaper/indian-express/Nagpur/38726'
         )
-        for citem in soup.findAll('meta', content=lambda s: s and s.endswith('view/3.jpg')):
+        citem = soup.find('meta', attrs={'property':'og:image'})
-            return citem['content']
+        return citem['content'].replace('300', '600')
 
     def preprocess_html(self, soup):
         if h2 := soup.find('h2'):

recipes/liberation.recipe

@@ -21,9 +21,9 @@ def resize(x):
             return v
 
 m_fr = {
-    1: 'janvier', 2: 'février', 3: 'mars', 4: 'avril',
+    1: 'Janvier', 2: 'Février', 3: 'Mars', 4: 'Avril',
-    5: 'mai', 6: 'juin', 7: 'juillet', 8: 'août',
+    5: 'Mai', 6: 'Juin', 7: 'Juillet', 8: 'Août',
-    9: 'septembre', 10: 'octobre', 11: 'novembre', 12: 'décembre'
+    9: 'Septembre', 10: 'Octobre', 11: 'Novembre', 12: 'Décembre'
 }
 
 def json_to_html(raw):
@@ -34,7 +34,7 @@ def json_to_html(raw):
 
     auth = '<p class="auth">{}</p>\n'
     dt = datetime.fromisoformat(data['last_updated_date'][:-1]) + timedelta(seconds=time.timezone)
-    dt = dt.strftime('%d ' + m_fr[dt.month] + ' %Y')
+    dt = dt.strftime(m_fr[dt.month] + '%d, %Y')
     a = [x['name'] for x in data['credits']['by']]
     if a:
         auth = auth.format(', '.join(a) + ' | ' + dt)
@@ -86,6 +86,7 @@ class Liberation(BasicNewsRecipe):
     oldest_article = 1.15
     remove_empty_feeds = True
     articles_are_obfuscated = True
+    timefmt = '[ %s]' % datetime.now().strftime(m_fr[datetime.now().month] '%d, %Y')
     ignore_duplicate_articles = {'title', 'url'}
     key = 'ZWplZVBlaW5nZWl0YWVnaG8zd2VlbmdlZXlvaHB1'
     masthead_url = 'https://journal.liberation.fr/img/logo.svg'

recipes/the_athletic.recipe

@@ -1,52 +0,0 @@
-from calibre.web.feeds.news import BasicNewsRecipe
-
-
-class Athletic(BasicNewsRecipe):
-    title = u'The Athletic'
-    __author__ = 'unkn0wn'
-    description = 'The Athletic delivers powerful stories and smart analysis that bring sports fans closer to the heart of the game. From breaking news and live commentary, to deeply-reported long reads and exclusive interviews, subscribers rely on The Athletic for every sports story that matters.'  # noqa
-    masthead_url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/9/95/The_Athletic_wordmark_black_2020.svg/640px-The_Athletic_wordmark_black_2020.svg.png'  # noqa
-    language = 'en'
-    oldest_article = 1.15  # days
-    max_articles_per_feed = 50
-    encoding = 'utf-8'
-    use_embedded_content = False
-    no_stylesheets = True
-    remove_attributes = ['style', 'height', 'width']
-    ignore_duplicate_articles = {'url'}
-    remove_empty_feeds = True
-    extra_css = '''
-        #articleByLineString{font-size:small;}
-        .inline-credits{font-size:small; text-align:center;}
-    '''
-    keep_only_tags = [
-        dict(name='amp-img', attrs={'class': 'i-amphtml-layout-fill'}),
-        dict(name='div', attrs={'class': ['the-lead-article', 'article-container']})
-    ]
-    remove_tags = [
-        dict(name='i-amphtml-sizer')
-    ]
-
-    feeds = [
-        ('The Athletic Ink', 'https://theathletic.com/ink/?rss'),
-        ('Football', 'https://theathletic.com/football/?rss'),
-        ('Boxing', 'https://theathletic.com/boxing/?rss'),
-        ('MMA', 'https://theathletic.com/mma/?rss'),
-        ('Motorsports', 'https://theathletic.com/motorsports/?rss'),
-        ('NBA', 'https://theathletic.com/nba/?rss'),
-        ('NHL', 'https://theathletic.com/nhl/?rss'),
-        ('Olympics', 'https://theathletic.com/olympics/?rss'),
-        ('Culture', 'https://theathletic.com/culture/?rss'),
-        ('Others', 'https://theathletic.com/rss-feed/'),  # All Articles
-        # just add '/?rss' to the sections you'd like to get.. there's too many
-    ]
-
-    def preprocess_html(self, soup):
-        for img in soup.findAll('amp-img'):
-            if not img.find('img'):
-                img.name = 'img'
-        return soup
-
-    def print_version(self, url):
-        reset = url.split('?')[0] + '?amp=1'
-        return reset

recipes/wsj.recipe

@@ -28,7 +28,7 @@ class WSJ(BasicNewsRecipe):
     title = 'The Wall Street Journal'
     __author__ = 'unkn0wn'
     description = (
-        'The Wall Street Journal is your source for breaking news, analysis and insights from the U.S. and '
+        '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'