_ Git - youtube-dl/blob - youtube_dl/extractor/addanime.py

   1 import ast
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     compat_HTTPError,
   7     compat_str,
   8     compat_urllib_parse,
   9     compat_urllib_parse_urlparse,
  10
  11     ExtractorError,
  12 )
  13
  14
  15 class AddAnimeIE(InfoExtractor):
  16
  17     _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
  18     IE_NAME = u'AddAnime'
  19     _TEST = {
  20         u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
  21         u'file': u'24MR3YO5SAS9.flv',
  22         u'md5': u'1036a0e0cd307b95bd8a8c3a5c8cfaf1',
  23         u'info_dict': {
  24             u"description": u"One Piece 606",
  25             u"title": u"One Piece 606"
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         try:
  31             mobj = re.match(self._VALID_URL, url)
  32             video_id = mobj.group('video_id')
  33             webpage = self._download_webpage(url, video_id)
  34         except ExtractorError as ee:
  35             if not isinstance(ee.cause, compat_HTTPError):
  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         video_url = self._search_regex(r"var normal_video_file = '(.*?)';",
  65                                        webpage, u'video file URL')
  66         video_title = self._og_search_title(webpage)
  67         video_description = self._og_search_description(webpage)
  68
  69         return {
  70             '_type': 'video',
  71             'id':  video_id,
  72             'url': video_url,
  73             'ext': 'flv',
  74             'title': video_title,
  75             'description': video_description
  76         }