Update Bloomberg Business Week

recipes/bloomberg-business-week.recipe

@@ -14,7 +14,7 @@ class Bloomberg(BasicNewsRecipe):
  ignore_duplicate_articles = {'url'}
  resolve_internal_links = True
  masthead_url = 'https://assets.bwbx.io/s3/javelin/public/hub/images/BW-Logo-Black-cc9035fbb3.svg'
- delay = 1.5
+ delay = 2
  extra_css = '''
  #auth {font-size:small; font-weight:bold;}
  #time {font-size:small;}
@@ -23,6 +23,11 @@ class Bloomberg(BasicNewsRecipe):
  .news-figure-credit {font-size:small; text-align:center; color:#202020;}
  '''
 
+ remove_tags = [
+ dict(name='div', attrs={'id':['bb-that', 'bb-nav']}),
+ classes('twitter-logo bb-global-footer')
+ ]
+
  def get_browser(self):
  br = browser()
  br.set_handle_redirect(False)
@@ -47,7 +52,9 @@ class Bloomberg(BasicNewsRecipe):
  articles = []
  for art in div.findAll('article'):
  a = art.find('a', **classes('story-list-story__info__headline-link'))
- url = 'https://www.bloomberg.com' + a['href']
+ url = a['href']
+ if url.startswith('http') is False:
+ url = 'https://www.bloomberg.com' + a['href']
  title = self.tag_to_string(a)
  desc = ''
  sum = art.find(**classes('story-list-story__info__summary'))
@@ -66,7 +73,8 @@ class Bloomberg(BasicNewsRecipe):
  m = re.search('data-component-props="ArticleBody">', raw)
  if not m:
  m = re.search('data-component-props="FeatureBody">', raw)
-
+ if not m:
+ return raw
  raw = raw[m.start():]
  raw = raw.split('>', 1)[1]
  data = json.JSONDecoder().raw_decode(raw)[0]