Deccan Herald by unkn0wn

recipes/deccan_herald.recipe

@@ -0,0 +1,55 @@
+from calibre.ptempfile import PersistentTemporaryFile
+from calibre.web.feeds.news import BasicNewsRecipe, classes
+
+class herald(BasicNewsRecipe):
+    title = 'Deccan Herald'
+    __author__ = 'unkn0wn'
+    description = 'Deccan Herald is an Indian English language daily newspaper published from the Indian state of Karnataka.'
+    language = 'en_IN'
+    no_stylesheets = True
+    remove_attributes = ['height', 'width', 'style']
+    ignore_duplicate_articles = {'url'}
+    encoding = 'utf-8'
+
+    articles_are_obfuscated = True
+
+    def get_obfuscated_article(self, url):
+        br = self.get_browser()
+        try:
+            br.open(url)
+        except Exception as e:
+            url = e.hdrs.get('location')
+        soup = self.index_to_soup(url)
+        link = soup.find('a', href=True)
+        skip_sections =[ # add sections you want to skip
+            '/sports/', '/video/', '/bengaluru-crime/', '/metrolife/',
+            '/karnataka-districts/', '/brandspot/', '/entertainment/',
+        ]
+        if any(x in link['href'] for x in skip_sections):
+            self.log('Aborting Article ', link['href'])
+            self.abort_article('skipping section')
+
+        self.log('Downloading ', link['href'])
+        html = br.open(link['href']).read()
+        pt = PersistentTemporaryFile('.html')
+        pt.write(html)
+        pt.close()
+        return pt.name
+
+    keep_only_tags = [
+        classes('article-title article-author__name'),
+        dict(name='div', attrs={'id':'main-content'})
+
+    ]
+
+    remove_tags = [
+        classes(
+            'storyShare social-media-icons in_article_video static_text'
+            ' nl-optin-mobile dk_only article-banner-adver-wrapper wb_holder'
+            ' field-name-field-tags section-full strip--business'
+        )
+    ]
+
+    feeds = [
+        ('DH', 'https://news.google.com/rss/search?q=when:27h+allinurl:deccanherald.com&hl=en-IN&gl=IN&ceid=IN:en')
+    ]