Example #1
0
def video_config_url(url):
  soup = _get_soup(url, cache=True)
  player = soup.find("div", class_="player-jv")
  
  if not player:
    return None
  
  # get the config file url
  return utils.get_absolute_url(player.get('data-src'))
Example #2
0
def video_pages(url):
  soup = _get_soup(url)
  
  # articles often contain videos
  articles = soup.find_all("article")
  
  if not articles:
    return []
  
  # list all links found in articles
  links = [_get_video_link(article) for article in articles]
  
  # remove dead entries (articles without valid link)
  links = filter(None, links)
  
  # return a list of absolute URLs from that list
  return [utils.get_absolute_url(link.get('href')) for link in links]
Example #3
0
def _filename_to_url(filename):
  url = urllib.parse.unquote(filename)
  return utils.get_absolute_url(url)
Example #4
0
 def test_get_absolute_url_relative(self):
   expected = 'http://www.jeuxvideo.com/videos/chroniques/434958/speed-game-live-any-majora-s-mask-fini-en-moins-de-1h35.htm'
   actual = get_absolute_url('/videos/chroniques/434958/speed-game-live-any-majora-s-mask-fini-en-moins-de-1h35.htm')
   self.assertEqual(actual, expected)
Example #5
0
 def test_get_relative_url_homepage_noslash(self):
   expected = 'http://www.jeuxvideo.com'
   actual = get_absolute_url('http://www.jeuxvideo.com')
   self.assertEqual(actual, expected)