youtube_dl/extractor/addanime.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     compat_HTTPError,
   6     compat_str,
   7     compat_urllib_parse,
   8     compat_urllib_parse_urlparse,
   9
  10     ExtractorError,
  11 )
  12
  13
  14 class AddAnimeIE(InfoExtractor):
  15
  16     _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
  17     IE_NAME = u'AddAnime'
  18     _TEST = {
  19         u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
  20         u'file': u'24MR3YO5SAS9.mp4',
  21         u'md5': u'72954ea10bc979ab5e2eb288b21425a0',
  22         u'info_dict': {
  23             u"description": u"One Piece 606",
  24             u"title": u"One Piece 606"
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         try:
  30             mobj = re.match(self._VALID_URL, url)
  31             video_id = mobj.group('video_id')
  32             webpage = self._download_webpage(url, video_id)
  33         except ExtractorError as ee:
  34             if not isinstance(ee.cause, compat_HTTPError) or \
  35                ee.cause.code != 503:
  36                 raise
  37
  38             redir_webpage = ee.cause.read().decode('utf-8')
  39             action = self._search_regex(
  40                 r'<form id="challenge-form" action="([^"]+)"',
  41                 redir_webpage, u'Redirect form')
  42             vc = self._search_regex(
  43                 r'<input type="hidden" name="jschl_vc" value="([^"]+)"/>',
  44                 redir_webpage, u'redirect vc value')
  45             av = re.search(
  46                 r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);',
  47                 redir_webpage)
  48             if av is None:
  49                 raise ExtractorError(u'Cannot find redirect math task')
  50             av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3))
  51
  52             parsed_url = compat_urllib_parse_urlparse(url)
  53             av_val = av_res + len(parsed_url.netloc)
  54             confirm_url = (
  55                 parsed_url.scheme + u'://' + parsed_url.netloc +
  56                 action + '?' +
  57                 compat_urllib_parse.urlencode({
  58                     'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
  59             self._download_webpage(
  60                 confirm_url, video_id,
  61                 note=u'Confirming after redirect')
  62             webpage = self._download_webpage(url, video_id)
  63
  64         formats = []
  65         for format_id in ('normal', 'hq'):
  66             rex = r"var %s_video_file = '(.*?)';" % re.escape(format_id)
  67             video_url = self._search_regex(rex, webpage, u'video file URLx',
  68                                            fatal=False)
  69             if not video_url:
  70                 continue
  71             formats.append({
  72                 'format_id': format_id,
  73                 'url': video_url,
  74             })
  75         if not formats:
  76             raise ExtractorError(u'Cannot find any video format!')
  77         video_title = self._og_search_title(webpage)
  78         video_description = self._og_search_description(webpage)
  79
  80         return {
  81             '_type': 'video',
  82             'id':  video_id,
  83             'formats': formats,
  84             'title': video_title,
  85             'description': video_description
  86         }