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

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6 )
   7 from bs4 import BeautifulSoup
   8
   9
  10 class AddAnimeIE(InfoExtractor):
  11
  12     _VALID_URL = r'^(?:http?://)?(?:\w+\.)?add-anime\.net/watch_video.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
  13     IE_NAME = u'AddAnime'
  14     _TEST = {
  15         u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
  16         u'file': u'137499050692ced.flv',
  17         u'md5': u'0813c2430bea7a46bf13acf3406992f4',
  18         u'info_dict': {
  19             u"description": u"One Piece 606",
  20             u"uploader": u"mugiwaraQ8",
  21             u"title": u"One Piece 606"
  22         }
  23     }
  24
  25     def _real_extract(self, url):
  26         mobj = re.match(self._VALID_URL, url)
  27         if mobj is None:
  28             raise ExtractorError(u'Invalid URL: %s' % url)
  29
  30         video_id = mobj.group('video_id')
  31
  32         webpage = self._download_webpage(url, video_id)
  33
  34         video_url = self._search_regex(r'var normal_video_file = "(.*?)",',
  35             webpage, u'video URL')
  36
  37         video_title = self._og_search_title(webpage)
  38
  39         video_description = self._og_search_description(webpage)
  40
  41         soup = BeautifulSoup(webpage)
  42
  43         video_uploader= soup.find("meta", {"author":""})['content']
  44
  45         info = {
  46             'id':  video_id,
  47             'url': video_url,
  48             'ext': 'flv',
  49             'title': video_title,
  50             'description': video_description,
  51             'uploader': video_uploader
  52         }
  53
  54         return [info]