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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     compat_urllib_parse,
   8     determine_ext,
   9     ExtractorError,
  10 )
  11
  12
  13 class AUEngineIE(InfoExtractor):
  14     _TEST = {
  15         'url': 'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
  16         'file': 'lfvlytY6.mp4',
  17         'md5': '48972bdbcf1a3a2f5533e62425b41d4f',
  18         'info_dict': {
  19             'title': '[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]'
  20         }
  21     }
  22     _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed\.php\?.*?file=([^&]+).*?'
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26         video_id = mobj.group(1)
  27         webpage = self._download_webpage(url, video_id)
  28         title = self._html_search_regex(r'<title>(?P<title>.+?)</title>',
  29                 webpage, 'title')
  30         title = title.strip()
  31         links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage)
  32         links = map(compat_urllib_parse.unquote, links)
  33
  34         thumbnail = None
  35         video_url = None
  36         for link in links:
  37             if link.endswith('.png'):
  38                 thumbnail = link
  39             elif '/videos/' in link:
  40                 video_url = link
  41         if not video_url:
  42             raise ExtractorError(u'Could not find video URL')
  43         ext = '.' + determine_ext(video_url)
  44         if ext == title[-len(ext):]:
  45             title = title[:-len(ext)]
  46
  47         return {
  48             'id':        video_id,
  49             'url':       video_url,
  50             'title':     title,
  51             'thumbnail': thumbnail,
  52         }