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

   1 import os.path
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     compat_urllib_parse,
   7     compat_urllib_parse_urlparse,
   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'[^A-Za-z0-9]?(?:file|url):\s*["\'](http[^\'"&]*)', webpage)
  29         links = [compat_urllib_parse.unquote(l) for l in links]
  30         for link in links:
  31             root, pathext = os.path.splitext(compat_urllib_parse_urlparse(link).path)
  32             if pathext == '.png':
  33                 thumbnail = link
  34             elif pathext == '.mp4':
  35                 url = link
  36                 ext = pathext
  37         if ext == title[-len(ext):]:
  38             title = title[:-len(ext)]
  39         ext = ext[1:]
  40         return [{
  41             'id':        video_id,
  42             'url':       url,
  43             'ext':       ext,
  44             'title':     title,
  45             'thumbnail': thumbnail,
  46         }]