Indian Express Print Edition by unkn0wn

recipes/indian_express_print_edition.recipe

@@ -0,0 +1,113 @@
+from calibre.web.feeds.news import BasicNewsRecipe, classes
+from collections import defaultdict
+
+
+class IndianExpressPrint(BasicNewsRecipe):
+    title = u'Indian Express | Print Edition'
+    language = 'en_IN'
+    __author__ = 'unkn0wn'
+    masthead_url = 'https://indianexpress.com/wp-content/themes/indianexpress/images/indian-express-logo-n.svg'
+    no_stylesheets = True
+    use_embedded_content = False
+    remove_attributes = ['style', 'height', 'width']
+    ignore_duplicate_articles = {'url'}
+    extra_css = '''
+        #storycenterbyline {font-size:small;}
+        #img-cap {font-size:small;}
+        blockquote{text-align:center; color:#404040;}
+        em{font-style:italic; color:#808080;}
+        #sub-d{color:#202020; font-style:italic;}
+        .ie-authorbox{font-size:small;}
+    '''
+    resolve_internal_links = True
+    remove_empty_feeds = True
+
+    keep_only_tags = [classes('heading-part full-details')]
+    remove_tags = [
+        dict(name='div', attrs={'id': 'ie_story_comments'}),
+        dict(name='div', attrs={'class': lambda x: x and 'related-widget' in x}),
+        dict(
+            name='img',
+            attrs={
+                'src':
+                'https://images.indianexpress.com/2021/06/explained-button-300-ie.jpeg'
+            }
+        ),
+        dict(
+            name='a',
+            attrs={
+                'href':
+                'https://indianexpress.com/section/explained/?utm_source=newbanner'
+            }
+        ),
+        dict(
+            name='img',
+            attrs={
+                'src':
+                'https://images.indianexpress.com/2021/06/opinion-button-300-ie.jpeg'
+            }
+        ),
+        dict(
+            name='a',
+            attrs={
+                'href':
+                'https://indianexpress.com/section/opinion/?utm_source=newbanner'
+            }
+        ),
+        classes(
+            'share-social appstext ie-int-campign-ad ie-breadcrumb custom_read_button unitimg copyright'
+            ' storytags pdsc-related-modify news-guard premium-story append_social_share'
+            ' digital-subscriber-only h-text-widget ie-premium ie-first-publish adboxtop adsizes immigrationimg'
+            'next-story-wrap ie-ie-share next-story-box brand-logo quote_section ie-customshare'
+            ' custom-share o-story-paper-quite ie-network-commenting'
+        )
+    ]
+
+    def parse_index(self):
+        soup = self.index_to_soup('https://indianexpress.com/todays-paper/')
+        feeds_dict = defaultdict(list)
+        for div in soup.findAll('div', attrs={'class':['lead-story', 'section']}):
+            for a in div.findAll('a', attrs={'href':lambda x: x and x.startswith('https://indianexpress.com/article/')}):
+                if not a.find('img'):
+                    url = a['href']
+                    title = self.tag_to_string(a)
+                    section = 'Front Page'
+                    str = a.findParent('strong')
+                    if str:
+                        span = str.find_previous_sibling('span')
+                        if span:
+                            section = self.tag_to_string(span)
+                    # if 'City' in section:
+                    #     url = ''
+                    if not url or not title:
+                        continue
+                    self.log(section, '\n\t', title, '\n\t\t', url)
+                    feeds_dict[section].append({"title": title, "url": url})
+        return [(section, articles) for section, articles in feeds_dict.items()]
+
+    def get_cover_url(self):
+        soup = self.index_to_soup(
+            'https://www.magzter.com/IN/The-Indian-Express-Ltd./The-Indian-Express-Mumbai/Newspaper/'
+        )
+        for citem in soup.findAll(
+            'meta', content=lambda s: s and s.endswith('view/3.jpg')
+        ):
+            return citem['content']
+
+    def preprocess_html(self, soup):
+        h2 = soup.find('h2')
+        if h2:
+            h2.name = 'p'
+            h2['id'] = 'sub-d'
+        for span in soup.findAll(
+            'span', attrs={'class': ['ie-custom-caption', 'custom-caption']}
+        ):
+            span['id'] = 'img-cap'
+        for img in soup.findAll('img'):
+            noscript = img.findParent('noscript')
+            if noscript is not None:
+                lazy = noscript.findPreviousSibling('img')
+                if lazy is not None:
+                    lazy.extract()
+                noscript.name = 'div'
+        return soup