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

recipes/livemint.recipe

@@ -103,7 +103,7 @@ class LiveMint(BasicNewsRecipe):
             dict(name=['meta', 'link', 'svg', 'button', 'iframe']),
             classes(
                 'trendingSimilarHeight moreNews mobAppDownload label msgError msgOk taboolaHeight gadgetSlider'
-                ' socialHolder imgbig disclamerText disqus-comment-count openinApp2 lastAdSlot bs_logo'
+                ' socialHolder imgbig disclamerText disqus-comment-count openinApp2 lastAdSlot bs_logo manualbacklink'
                 ' datePublish sepStory premiumSlider moreStory Joinus moreAbout milestone benefitText'
             )
         ]
@@ -132,7 +132,9 @@ class LiveMint(BasicNewsRecipe):
             # remove empty p tags
             raw = re.sub(
                 r'(<p>\s*)(<[^(\/|a|i|b|em|strong)])', '\g<2>', re.sub(
-                    r'(<p>\s*&nbsp;\s*<\/p>)|(<p>\s*<\/p>)|(<p\s*\S+>&nbsp;\s*<\/p>)', '', raw
+                    r'(<p>\s*&nbsp;\s*<\/p>)|(<p>\s*<\/p>)|(<p\s*\S+>&nbsp;\s*<\/p>)', '', re.sub(
+                        r'(?=<h2>\s*Also\s*Read).*?(?<=</h2>)', '', raw
+                    )
                 )
             )
             if '<script>var wsjFlag=true;</script>' in raw:

recipes/natgeo.recipe

@@ -35,7 +35,8 @@ def parse_lead_image(media):
         yield '<p>'
         if 'dsc' in media['image']:
             yield '<div><img src="{}" alt="{}"></div>'.format(
-                escape(media['image']['src'], True), escape(media['image']['dsc'], True))
+                escape(media['image']['src'], True), escape(media['image']['dsc'], True)
+            )
         else:
             yield '<div><img src="{}"></div>'.format(escape(media['image']['src'], True))
         if 'caption' in media and 'credit' in media:
@@ -84,7 +85,7 @@ def parse_body(x):
             if tag == 'inline':
                 yield ''.join(parse_inline(x))
             elif 'attrs' in x and 'href' in x.get('attrs', ''):
-                yield '<' + tag + ' href = "{}">'.format(x['attrs']['href'])
+                yield '<' + tag + ' href="{}">'.format(x['attrs']['href'])
                 for yld in parse_cont(x):
                     yield yld
                 yield '</' + tag + '>'
@@ -120,8 +121,7 @@ def parse_article(edg):
             for item in main['props']['body']:
                 if isinstance(item, dict):
                     if item.get('type', '') == 'inline':
-                        for inl in parse_inline(item):
+                        yield ''.join(parse_inline(item))
-                            yield inl
                 elif isinstance(item, list):
                     for line in item:
                         yield ''.join(parse_body(line))

recipes/natgeohis.recipe

@@ -34,7 +34,8 @@ def parse_lead_image(media):
         yield '<p>'
         if 'dsc' in media['image']:
             yield '<div><img src="{}" alt="{}"></div>'.format(
-                escape(media['image']['src'], True), escape(media['image']['dsc'], True))
+                escape(media['image']['src'], True), escape(media['image']['dsc'], True)
+            )
         else:
             yield '<div><img src="{}"></div>'.format(escape(media['image']['src'], True))
         if 'caption' in media and 'credit' in media:
@@ -83,7 +84,7 @@ def parse_body(x):
             if tag == 'inline':
                 yield ''.join(parse_inline(x))
             elif 'attrs' in x and 'href' in x.get('attrs', ''):
-                yield '<' + tag + ' href = "{}">'.format(x['attrs']['href'])
+                yield '<' + tag + ' href="{}">'.format(x['attrs']['href'])
                 for yld in parse_cont(x):
                     yield yld
                 yield '</' + tag + '>'
@@ -119,8 +120,7 @@ def parse_article(edg):
             for item in main['props']['body']:
                 if isinstance(item, dict):
                     if item.get('type', '') == 'inline':
-                        for inl in parse_inline(item):
+                        yield ''.join(parse_inline(item))
-                            yield inl
                 elif isinstance(item, list):
                     for line in item:
                         yield ''.join(parse_body(line))

recipes/natgeomag.recipe

@@ -39,7 +39,8 @@ def parse_lead_image(media):
         yield '<p>'
         if 'dsc' in media['image']:
             yield '<div><img src="{}" alt="{}"></div>'.format(
-                escape(media['image']['src'], True), escape(media['image']['dsc'], True))
+                escape(media['image']['src'], True), escape(media['image']['dsc'], True)
+            )
         else:
             yield '<div><img src="{}"></div>'.format(escape(media['image']['src'], True))
         if 'caption' in media and 'credit' in media:
@@ -88,7 +89,7 @@ def parse_body(x):
             if tag == 'inline':
                 yield ''.join(parse_inline(x))
             elif 'attrs' in x and 'href' in x.get('attrs', ''):
-                yield '<' + tag + ' href = "{}">'.format(x['attrs']['href'])
+                yield '<' + tag + ' href="{}">'.format(x['attrs']['href'])
                 for yld in parse_cont(x):
                     yield yld
                 yield '</' + tag + '>'
@@ -124,8 +125,7 @@ def parse_article(edg):
             for item in main['props']['body']:
                 if isinstance(item, dict):
                     if item.get('type', '') == 'inline':
-                        for inl in parse_inline(item):
+                        yield ''.join(parse_inline(item))
-                            yield inl
                 elif isinstance(item, list):
                     for line in item:
                         yield ''.join(parse_body(line))

recipes/poliitico_eu.recipe

@@ -0,0 +1,101 @@
+#!/usr/bin/env  python2
+# -*- coding: cp1252 -*-
+
+__license__ = 'GPL v3'
+__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
+'''
+politico.eu
+'''
+
+from calibre.web.feeds.news import BasicNewsRecipe
+
+class Politico(BasicNewsRecipe):
+
+    title = 'Politico.eu'
+    __author__ = 'unkn0wn, Darko Miletic and Sujata Raman'
+    description = 'We connect and empower professionals through nonpartisan journalism and actionable intelligence about European politics and policy. Download Weekly.'
+    publisher = 'Axel Springer SE.'
+    category = 'news, politics, Europe'
+    oldest_article = 7 # days
+    max_articles_per_feed = 20
+    use_embedded_content = False
+    no_stylesheets = True
+    remove_javascript = True
+    encoding = 'UTF-8'
+    language = 'en'
+
+    remove_empty_feeds = True
+    ignore_duplicate_articles = ['url']
+
+    html2lrf_options = [
+        '--comment', description, '--category', category, '--publisher', publisher, '--ignore-tables'
+    ]
+
+    html2epub_options = 'publisher="' + publisher + '"\ncomments="' + \
+        description + '"\ntags="' + category + '"\nlinearize_tables=True'
+
+    keep_only_tags = [
+        dict(name='div', attrs={'class':['container']}),
+    ]
+
+    remove_tags = [
+        dict(name=['notags', 'embed', 'aside', 'object', 'link']),
+        dict(name='div', attrs={'class':'module-article-inline related-articles'}),
+        dict(name='header', attrs={'class':'summary-header'}),
+        dict(name='div', attrs={'class':'amazon-polly-wrapper'}),
+        dict(name='div', attrs={'class': lambda x: x and 'story-meta' in x.split()}),
+        dict(attrs={'class': lambda x: x and 'story-tools' in x.split()}),
+        dict(attrs={'class': lambda x: x and 'social-sharing' in x.split()}),
+        dict(attrs={'class': lambda x: x and 'story-meta__authors' in x.split()}),
+        dict(attrs={'class': lambda x: x and 'story-meta__timestamp' in x.split()}),
+        dict(attrs={'class': lambda x: x and 'story-continued' in x.split()}),
+        dict(attrs={'class': lambda x: x and 'story-supplement' in x.split()}),
+        dict(attrs={'class': lambda x: x and 'story-share' in x.split()}),
+        dict(attrs={'class': lambda x: x and 'suggested' in x.split()}),
+        dict(attrs={'class': lambda x: x and 'article__sidebar' in x.split()}),
+        dict(name='svg'),
+        dict(name='footer'),
+        dict(name='span', attrs={'class':'ad-label'}),
+        dict(name='div', attrs={'class':'pro-pill'}),
+        dict(name='ol', attrs={'class':'breadcrumbs__list'}),
+    ]
+
+    preprocess_regexps = [(re.compile(r'<a\s[^>]*>([^<]*)</a>', re.DOTALL|re.IGNORECASE), lambda match: match.group(1))]
+
+    remove_tags_after  = dict(attrs={'class': lambda x: x and 'article__more-from' in x.split()})
+
+    extra_css = '''
+                body{font-family:Arial,Sans-serif;}
+                element.style{color:#FF0000;font-family:Arial,Sans-serif;}
+                .author{color:#808080;font-size:x-small;}
+                a{ color:#003399;}
+                .byline{color:#696969 ; font-size:x-small;}
+                .story{color:#000000;}
+                td{color:#000000;}
+                .figcaption__inner, .article-meta, .authors, .datetime {font-size:small; }
+            '''
+
+    def get_article_url(self, article):
+        url = BasicNewsRecipe.get_article_url(self, article)
+        if 'politico.com' not in url:
+            return url.split('?')[0]
+
+    masthead_url = 'https://www.politico.eu/cdn-cgi/image/width=573,quality=80,onerror=redirect,format=auto/wp-content/uploads/2021/02/25/Politico_logo-01.png'
+
+    def get_cover_url(self):
+        soup = self.index_to_soup('https://www.politico.eu/')
+        for cov in soup.findAll(attrs={'class':'cta__image'}):
+            if cov.find('a', attrs={'href':lambda x: x and 'edition.pagesuite-professional' in x}):
+                return cov.a.img['src']
+
+    feeds = [
+        ('Policy', 'https://www.politico.eu/section/policy/feed'),
+        ('Opinion', 'https://www.politico.eu/section/opinion/feed'),
+        ('Newsletter', 'https://www.politico.eu/newsletter/feed'),
+        ('Others', 'https://www.politico.eu/feed')
+    ]
+
+    def postprocess_html(self, soup, first):
+        for tag in soup.findAll(name=['table', 'tr', 'td']):
+            tag.name = 'div'
+        return soup