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

recipes/scroll.recipe

@@ -0,0 +1,63 @@
+from calibre.web.feeds.news import BasicNewsRecipe, classes
+from calibre.ptempfile import PersistentTemporaryFile
+
+class scroll(BasicNewsRecipe):
+    title = 'Scroll.in'
+    __author__ = 'unkn0wn'
+    description = (
+        'The leading destination for original reporting on news, politics, and culture in India. '
+        'Our award-winning team of journalists brings readers insightful analysis and opinion on the day’s '
+        'headlines alongside a fresh mix of features on music, books, and cinema.'
+    )
+    language = 'en_IN'
+    masthead_url = 'https://scroll.in/static/assets/scroll-logo.0f68c78dd023e2598248ea107feba562.003.svg'
+
+    no_stylesheets = True
+    remove_javascript = True
+
+    ignore_duplicate_articles = {'title', 'url'}
+    remove_attributes = ['style', 'height', 'width']
+
+    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
+            '/video/', '/videos/', '/announcements/'
+        ]
+        if any(x in link['href'] for x in skip_sections):
+            self.log('Aborting Article ', link['href'])
+            self.abort_article('skipping video links')
+
+        self.log('Downloading ', link['href'])
+        html = br.open(link['href']).read()
+        pt = PersistentTemporaryFile('.html')
+        pt.write(html)
+        pt.close()
+        return pt.name
+
+    extra_css = '''
+        .orange-tag, .article-meta-container { font-size:small; }
+        .featured-image, .cms-block-image { text-align:center; font-size:small; }
+    '''
+
+    keep_only_tags = [
+        dict(name = 'header'),
+        classes('featured-image article-body')
+    ]
+
+    remove_tags = [classes('comments-entry-point-meta')]
+
+    feeds = [('Articles', 'https://news.google.com/rss/search?q=when:27h+allinurl:https%3A%2F%2Fscroll.in&hl=en-IN&gl=IN&ceid=IN:en')]
+
+    def populate_article_metadata(self, article, soup, first):
+        # article.url = ''
+        article.summary = self.tag_to_string(soup.find('h2'))
+        article.text_summary = self.tag_to_string(soup.find('h2'))
+        article.title = article.title.replace(' - Scroll.in', '')

recipes/wash_post.recipe

@@ -15,7 +15,7 @@ class TheWashingtonPost(BasicNewsRecipe):
     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
     publisher = 'The Washington Post Company'
     category = 'news, politics, USA'
-    oldest_article = 2
+    oldest_article = 1.2
     max_articles_per_feed = 200
     no_stylesheets = True
     encoding = 'utf8'