Update The Guardian and The Observer

recipes/guardian.recipe

@@ -6,10 +6,8 @@ __docformat__ = 'restructuredtext en'
 '''
 www.guardian.co.uk
 '''
-from calibre import strftime
 from calibre.web.feeds.news import BasicNewsRecipe
 from datetime import date
-from calibre.ebooks.BeautifulSoup import BeautifulSoup, Tag
 
 class Guardian(BasicNewsRecipe):
 
@@ -23,15 +21,16 @@ class Guardian(BasicNewsRecipe):
         cover_pic = 'Guardian digital edition'
         masthead_url = 'http://static.guim.co.uk/static/f76b43f9dcfd761f0ecf7099a127b603b2922118/common/images/logos/the-guardian/titlepiece.gif'
 
-    __author__ = 'Seabound and Sujata Raman'
+    __author__ = 'Kovid Goyal'
     language = 'en_GB'
 
     oldest_article              = 7
     max_articles_per_feed       = 100
     remove_javascript           = True
     encoding                    = 'utf-8'
-    compress_news_images = True
+    remove_empty_feeds = True
-    compress_news_images_auto_size = 8
+    no_stylesheets = True
+    remove_attributes = ['style']
 
     # List of section titles to ignore
     # For example: ['Sport']
@@ -40,129 +39,37 @@ class Guardian(BasicNewsRecipe):
     timefmt = ' [%a, %d %b %Y]'
 
     keep_only_tags = [
-        dict(name='div', attrs={'id':["content","article_header","main-article-info",]}),
+        dict(attrs={'class': lambda x: x and 'content__main-column' in x.split()}),
-        dict(attrs={'class':lambda x: x and set(x.split()).intersection({'content__head', 'content__main'})}),
     ]
     remove_tags = [
-        dict(name='div', attrs={'class':[
+        dict(attrs={'class': lambda x:x and '--twitter' in x}),
-            "video-content","videos-third-column", 'meta__extras', 'submeta-container  submeta-container--break-at-leftcol ']}),
+        dict(attrs={'data-component': ['share', 'social']}),
-        dict(name='div', attrs={'id':["article-toolbox","subscribe-feeds",]}),
+        dict(attrs={'data-link-name': 'block share'}),
-        dict(name='div', attrs={'class':["guardian-tickets promo-component",]}),
+        dict(attrs={'class': lambda x:x and 'inline-expand-image' in x}),
-        dict(name='ul', attrs={'class':["pagination"]}),
+        dict(attrs={'class': lambda x:x and 'modern-visible' in x.split()}),
-        dict(name='ul', attrs={'id':["content-actions"]}),
+    ]
-        # article history link
+    remove_tags_after = [
-        dict(name='a', attrs={'class':["rollover history-link"]}),
+        dict(attrs={'class': lambda x: x and 'content__article-body' in x.split()}),
-        # "a version of this article ..." speil
-        dict(name='div' , attrs={'class' : ['section']}),
-        # "about this article" js dialog
-        dict(name='div', attrs={'class':["share-top",]}),
-        # author picture
-        dict(name='img', attrs={'class':["contributor-pic-small"]}),
-        # embedded videos/captions
-        dict(name='span',attrs={'class' : ['inline embed embed-media']}),
     ]
-    use_embedded_content    = False
-
-    no_stylesheets = True
-    extra_css = '''
-                    .article-attributes{font-size: x-small; font-family:Arial,Helvetica,sans-serif;}
-                    .h1{font-size: large ;font-family:georgia,serif; font-weight:bold;}
-                    .stand-first-alone{color:#666666; font-size:small; font-family:Arial,Helvetica,sans-serif;}
-                    .caption{color:#666666; font-size:x-small; font-family:Arial,Helvetica,sans-serif;}
-                    #article-wrapper{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}
-                    .main-article-info{font-family:Arial,Helvetica,sans-serif;}
-                    #full-contents{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}
-                    #match-stats-summary{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}
-                '''
-
-    def get_article_url(self, article):
-        url = article.get('guid', None)
-        if '/video/' in url or '/flyer/' in url or '/quiz/' in url or \
-            '/gallery/' in url or 'ivebeenthere' in url or \
-            'pickthescore' in url or 'audioslideshow' in url :
-            url = None
-        return url
-
-    def populate_article_metadata(self, article, soup, first):
-        if first and hasattr(self, 'add_toc_thumbnail'):
-            picdiv = soup.find('img')
-            if picdiv is not None:
-                self.add_toc_thumbnail(article,picdiv['src'])
 
     def preprocess_html(self, soup):
-
+        for img in soup.findAll('img', srcset=True):
-        # multiple html sections in soup, useful stuff in the first
+            img['src'] = img['srcset'].partition(' ')[0]
-        html = soup.find('html')
+            img['srcset'] = ''
-        soup2 = BeautifulSoup()
-        soup2.insert(0,html)
-
-        soup = soup2
-
-        for item in soup.findAll(style=True):
-            del item['style']
-
-        for item in soup.findAll(face=True):
-            del item['face']
-        for tag in soup.findAll(name=['ul','li']):
-            tag.name = 'div'
-
-        # removes number next to rating stars
-        items_to_remove = []
-        rating_container = soup.find('div', attrs={'class': ['rating-container']})
-        if rating_container:
-            for item in rating_container:
-                if isinstance(item, Tag) and str(item.name) == 'span':
-                    items_to_remove.append(item)
-
-        for item in items_to_remove:
-            item.extract()
-
         return soup
 
-    def find_sections(self):
-        # soup = self.index_to_soup("http://www.guardian.co.uk/theobserver")
-        soup = self.index_to_soup(self.base_url)
-        # find cover pic
-        img = soup.find('img',attrs={'alt':self.cover_pic})
-        if img is not None:
-            self.cover_url = img['src']
-        # end find cover pic
-
-        idx = soup.find('div', id='book-index')
-        for s in idx.findAll('strong', attrs={'class':'book'}):
-            a = s.find('a', href=True)
-            section_title = self.tag_to_string(a)
-            if section_title not in self.ignore_sections:
-                prefix = ''
-                if section_title != 'Main section':
-                    prefix = section_title + ': '
-                for subsection in s.parent.findAll('a', attrs={'class':'book-section'}):
-                    yield (prefix + self.tag_to_string(subsection), subsection['href'])
-
-    def find_articles(self, url):
-        soup = self.index_to_soup(url)
-        div = soup.find('div', attrs={'class':'book-index'})
-        for ul in div.findAll('ul', attrs={'class':'trailblock'}):
-            for li in ul.findAll('li'):
-                a = li.find(href=True)
-                if not a:
-                    continue
-                title = self.tag_to_string(a)
-                url = a['href']
-                if not title or not url:
-                    continue
-                tt = li.find('div', attrs={'class':'trailtext'})
-                if tt is not None:
-                    for da in tt.findAll('a'):
-                        da.extract()
-                    desc = self.tag_to_string(tt).strip()
-                yield {
-                        'title': title, 'url':url, 'description':desc,
-                        'date' : strftime('%a, %d %b'),
-                        }
-
     def parse_index(self):
         feeds = []
-        for title, href in self.find_sections():
+        soup = self.index_to_soup(self.base_url)
-            feeds.append((title, list(self.find_articles(href))))
+        for section in soup.findAll('section'):
+            title = self.tag_to_string(section.find(attrs={'class':'fc-container__header__title'})).strip().capitalize()
+            self.log('\nFound section:', title)
+            feeds.append((title, []))
+            for li in section.findAll('li'):
+                for a in li.findAll('a', attrs={'data-link-name':'article'}, href=True):
+                    title = self.tag_to_string(a).strip()
+                    url = a['href']
+                    self.log(' ', title, url)
+                    feeds[-1][1].append({'title':title, 'url':url})
+                    break
         return feeds