Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/auengine.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     compat_urllib_parse,
   6     determine_ext,
   7     ExtractorError,
   8 )
   9
  10 class AUEngineIE(InfoExtractor):
  11     _TEST = {
  12         u'url': u'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
  13         u'file': u'lfvlytY6.mp4',
  14         u'md5': u'48972bdbcf1a3a2f5533e62425b41d4f',
  15         u'info_dict': {
  16             u"title": u"[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]"
  17         }
  18     }
  19     _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed\.php\?.*?file=([^&]+).*?'
  20
  21     def _real_extract(self, url):
  22         mobj = re.match(self._VALID_URL, url)
  23         video_id = mobj.group(1)
  24         webpage = self._download_webpage(url, video_id)
  25         title = self._html_search_regex(r'<title>(?P<title>.+?)</title>',
  26                 webpage, u'title')
  27         title = title.strip()
  28         links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage)
  29         links = map(compat_urllib_parse.unquote, links)
  30
  31         thumbnail = None
  32         video_url = None
  33         for link in links:
  34             if link.endswith('.png'):
  35                 thumbnail = link
  36             elif '/videos/' in link:
  37                 video_url = link
  38         if not video_url:
  39             raise ExtractorError(u'Could not find video URL')
  40         ext = u'.' + determine_ext(video_url)
  41         if ext == title[-len(ext):]:
  42             title = title[:-len(ext)]
  43
  44         return {
  45             'id':        video_id,
  46             'url':       video_url,
  47             'title':     title,
  48             'thumbnail': thumbnail,
  49         }