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

recipes/wash_post.recipe

@@ -16,7 +16,14 @@ from calibre.web.feeds.news import BasicNewsRecipe
 class TheWashingtonPost(BasicNewsRecipe):
     title = 'The Washington Post'
     __author__ = 'Darko Miletic, unkn0wn'
-    description = 'Leading source for news, video and opinion on politics, business, world and national news, science, travel, entertainment and more. Our local coverage includes reporting on education, crime, weather, traffic, real estate, jobs and cars for DC, Maryland and Virginia. Offering award-winning opinion writing, entertainment information and restaurant reviews.'  # noqa: E501
+    description = (
+        'Leading source for news, video and opinion on politics, business, '
+        'world and national news, science, travel, entertainment and more. '
+        'Our local coverage includes reporting on education, crime, weather, '
+        'traffic, real estate, jobs and cars for DC, Maryland and Virginia. '
+        'Offering award-winning opinion writing, entertainment information '
+        'and restaurant reviews.'
+    )
     publisher = 'The Washington Post Company'
     category = 'news, politics, USA'
     oldest_article = 1.2
@@ -27,7 +34,7 @@ class TheWashingtonPost(BasicNewsRecipe):
     language = 'en_US'
     remove_empty_feeds = True
     ignore_duplicate_articles = {'url'}
-    masthead_url = 'https://www.washingtonpost.com/pb/resources/img/twp-masthead-415x57.svg'
+    masthead_url = 'https://upload.wikimedia.org/wikipedia/commons/9/93/The_Logo_of_The_Washington_Post_Newspaper.svg'
     publication_type = 'newspaper'
     remove_attributes = ['style', 'width', 'height']
 
@@ -35,7 +42,7 @@ class TheWashingtonPost(BasicNewsRecipe):
         'days': {
             'short': 'Oldest article to download from this news source. In days ',
             'long': 'For example, 0.5, gives you articles from the past 12 hours',
-            'default': str(oldest_article)
+            'default': str(oldest_article),
         }
     }
 
@@ -51,28 +58,39 @@ class TheWashingtonPost(BasicNewsRecipe):
         .time { font-size:small; color: #202020; }
     '''
 
-    def get_browser(self):
+    def get_cover_url(self):
-        return BasicNewsRecipe.get_browser(
+        soup = self.index_to_soup('https://www.washingtonpost.com/todays_paper/updates/')
-            self, verify_ssl_certificates=False, user_agent='Mozilla/5.0 (Windows NT 10.0; rv:128.0) Gecko/20100101 Firefox/128.0')
+        if img := soup.find(
+            'img', attrs={'src': lambda x: x and x.endswith('_FrontPage.png')}
+        ):
+            return img['src']
+
+    def get_browser(self, *args, **kwargs):
+        kwargs['user_agent'] = (
+            'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)'
+        )
+        br = BasicNewsRecipe.get_browser(self, *args, **kwargs)
+        br.addheaders += [
+            ('Referer', 'https://www.google.com/'),
+            ('X-Forwarded-For', '66.249.66.1'),
+        ]
+        return br
 
     # Official feeds: https://www.washingtonpost.com/discussions/2018/10/12/washington-post-rss-feeds/
     feeds = [
-        (u'Politics', u'http://feeds.washingtonpost.com/rss/politics'),
+        ('Politics', 'http://feeds.washingtonpost.com/rss/politics'),
-        (u'Opinions', u'http://feeds.washingtonpost.com/rss/opinions'),
+        ('Opinions', 'http://feeds.washingtonpost.com/rss/opinions'),
-        (u'Local', u'http://feeds.washingtonpost.com/rss/local'),
+        ('Local', 'http://feeds.washingtonpost.com/rss/local'),
-        (u'Sports', u'http://feeds.washingtonpost.com/rss/sports'),
+        ('Sports', 'http://feeds.washingtonpost.com/rss/sports'),
-        (u'Technology', u'http://feeds.washingtonpost.com/rss/business/technology'),
+        ('Technology', 'http://feeds.washingtonpost.com/rss/business/technology'),
-        (u'National', u'http://feeds.washingtonpost.com/rss/national'),
+        ('National', 'http://feeds.washingtonpost.com/rss/national'),
-        (u'World', u'http://feeds.washingtonpost.com/rss/world'),
+        ('World', 'http://feeds.washingtonpost.com/rss/world'),
-        (u'Business', u'http://feeds.washingtonpost.com/rss/business'),
+        ('Business', 'http://feeds.washingtonpost.com/rss/business'),
-        (u'Lifestyle', u'http://feeds.washingtonpost.com/rss/lifestyle'),
+        ('Lifestyle', 'http://feeds.washingtonpost.com/rss/lifestyle'),
-        (u'Entertainment',
+        ('Entertainment', 'http://feeds.washingtonpost.com/rss/entertainment'),
-         u'http://feeds.washingtonpost.com/rss/entertainment'),
-
         # Undocumented feeds.
-        (u'White House',
+        ('White House', 'http://feeds.washingtonpost.com/rss/politics/whitehouse'),
-         u'http://feeds.washingtonpost.com/rss/politics/whitehouse'),
+        ('Commanders', 'http://feeds.washingtonpost.com/rss/sports/redskins'),
-        (u'Commanders', u'http://feeds.washingtonpost.com/rss/sports/redskins'),
     ]
 
     def preprocess_raw_html(self, raw, *a):
@@ -87,8 +105,14 @@ class TheWashingtonPost(BasicNewsRecipe):
 
         author = ''
         if 'credits' in data:
-            author = ('<div><span class="auth">' + 'By ' + ', '.join(x['name'] for x in data['credits']['by']) +
+            author = (
-                      '</span> | <span class="time">' + data['publish_date'][:-14] + '</span></div>')
+                '<div><span class="auth">'
+                + 'By '
+                + ', '.join(x['name'] for x in data['credits']['by'])
+                + '</span> | <span class="time">'
+                + data['publish_date'][:-14]
+                + '</span></div>'
+            )
 
         body = ''
         for x in data['content_elements']:
@@ -100,11 +124,21 @@ class TheWashingtonPost(BasicNewsRecipe):
                         x['promo_image']['url'], x['description'].get('basic', '')
                     )
             elif x['type'] == 'image':
-                body += '<p><div class="img"><img src="{}"><div>{}</div></div></p>'.format(x['url'], x['credits_caption_display'])
+                body += (
+                    '<p><div class="img"><img src="{}"><div>{}</div></div></p>'.format(
+                        x['url'], x['credits_caption_display']
+                    )
+                )
 
-        return '<html><body><div>' + title + subhead + author + body + '</div></body></html>'
+        return (
+            '<html><body><div>' + title + subhead + author + body + '</div></body></html>'
+        )
 
     def preprocess_html(self, soup):
-        for img in soup.findAll('img', attrs={'src':True}):
+        for img in soup.findAll('img', attrs={'src': True}):
-            img['src'] = 'https://www.washingtonpost.com/wp-apps/imrs.php?src=' + img['src'] + '&w=916'
+            img['src'] = (
+                'https://www.washingtonpost.com/wp-apps/imrs.php?src='
+                + img['src']
+                + '&w=916'
+            )
         return soup

recipes/wash_post_print.recipe

@@ -15,10 +15,12 @@ class wapoprint(BasicNewsRecipe):
     title = 'The Washington Post | Print Edition'
     __author__ = 'unkn0wn'
     description = (
-        'Leading source for news, video and opinion on politics, business, world and national news, science,'
+        'Leading source for news, video and opinion on politics, business, '
-        ' travel, entertainment and more. Our local coverage includes reporting on education, crime, weather,'
+        'world and national news, science, travel, entertainment and more. '
-        ' traffic, real estate, jobs and cars for DC, Maryland and Virginia. Offering award-winning opinion writing,'
+        'Our local coverage includes reporting on education, crime, weather, '
-        ' entertainment information and restaurant reviews.'
+        'traffic, real estate, jobs and cars for DC, Maryland and Virginia. '
+        'Offering award-winning opinion writing, entertainment information '
+        'and restaurant reviews.'
     )
     publisher = 'The Washington Post Company'
     category = 'news, politics, USA'
@@ -29,22 +31,33 @@ class wapoprint(BasicNewsRecipe):
     remove_attributes = ['style', 'height', 'width']
     publication_type = 'newspaper'
     ignore_duplicate_articles = {'title', 'url'}
-    masthead_url = 'https://www.washingtonpost.com/pb/resources/img/twp-masthead-415x57.svg'
+    masthead_url = 'https://upload.wikimedia.org/wikipedia/commons/9/93/The_Logo_of_The_Washington_Post_Newspaper.svg'
     extra_css = '''
         .img { text-align:center; font-size:small; }
         .auth { font-weight:bold; font-size:small; }
         .time { font-size:small; color: #202020; }
     '''
 
-    def get_browser(self):
+    def get_browser(self, *args, **kwargs):
-        return BasicNewsRecipe.get_browser(
+        kwargs['user_agent'] = (
-            self, verify_ssl_certificates=False, user_agent='Mozilla/5.0 (Windows NT 10.0; rv:128.0) Gecko/20100101 Firefox/128.0')
+            'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)'
+        )
+        br = BasicNewsRecipe.get_browser(self, *args, **kwargs)
+        br.addheaders += [
+            ('Referer', 'https://www.google.com/'),
+            ('X-Forwarded-For', '66.249.66.1'),
+        ]
+        return br
 
     def parse_index(self):
         soup = self.index_to_soup('https://www.washingtonpost.com/todays_paper/updates/')
-        if img := soup.find('img', attrs={'src':lambda x: x and x.endswith('_FrontPage.png')}):
+        if img := soup.find(
+            'img', attrs={'src': lambda x: x and x.endswith('_FrontPage.png')}
+        ):
             self.cover_url = img['src']
-        if h2 := soup.find('h2', attrs={'class':lambda x: x and 'font--subhead' in x.split()}):
+        if h2 := soup.find(
+            'h2', attrs={'class': lambda x: x and 'font--subhead' in x.split()}
+        ):
             self.title = 'WaPo Print | ' + self.tag_to_string(h2)
 
         feeds = []
@@ -77,8 +90,14 @@ class wapoprint(BasicNewsRecipe):
 
         author = ''
         if 'credits' in data:
-            author = ('<div><span class="auth">' + 'By ' + ', '.join(x['name'] for x in data['credits']['by']) +
+            author = (
-                      '</span> | <span class="time">' + data['publish_date'][:-14] + '</span></div>')
+                '<div><span class="auth">'
+                + 'By '
+                + ', '.join(x['name'] for x in data['credits']['by'])
+                + '</span> | <span class="time">'
+                + data['publish_date'][:-14]
+                + '</span></div>'
+            )
 
         body = ''
         for x in data['content_elements']:
@@ -90,13 +109,23 @@ class wapoprint(BasicNewsRecipe):
                         x['promo_image']['url'], x['description'].get('basic', '')
                     )
             elif x['type'] == 'image':
-                body += '<p><div class="img"><img src="{}"><div>{}</div></div></p>'.format(x['url'], x['credits_caption_display'])
+                body += (
+                    '<p><div class="img"><img src="{}"><div>{}</div></div></p>'.format(
+                        x['url'], x['credits_caption_display']
+                    )
+                )
 
-        return '<html><body><div>' + title + subhead + author + body + '</div></body></html>'
+        return (
+            '<html><body><div>' + title + subhead + author + body + '</div></body></html>'
+        )
 
     def preprocess_html(self, soup):
-        for img in soup.findAll('img', attrs={'src':True}):
+        for img in soup.findAll('img', attrs={'src': True}):
-            img['src'] = 'https://www.washingtonpost.com/wp-apps/imrs.php?src=' + img['src'] + '&w=916'
+            img['src'] = (
+                'https://www.washingtonpost.com/wp-apps/imrs.php?src='
+                + img['src']
+                + '&w=916'
+            )
         return soup
 
     def populate_article_metadata(self, article, soup, first):