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

   1 # encoding: utf-8
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7 )
   8
   9
  10 class CinemassacreIE(InfoExtractor):
  11     _VALID_URL = r'(?:http://)?(?:www\.)?(?P<url>cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/.+?)(?:[/?].*)?'
  12     _TESTS = [{
  13         u'url': u'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
  14         u'file': u'19911.flv',
  15         u'md5': u'f9bb7ede54d1229c9846e197b4737e06',
  16         u'info_dict': {
  17             u'upload_date': u'20121110',
  18             u'title': u'“Angry Video Game Nerd: The Movie” – Trailer',
  19             u'description': u'md5:fb87405fcb42a331742a0dce2708560b',
  20         },
  21         u'params': {
  22             # rtmp download
  23             u'skip_download': True,
  24         },
  25     },
  26     {
  27         u'url': u'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
  28         u'file': u'521be8ef82b16.flv',
  29         u'md5': u'91b248e1e2473d5bff55d6010518111f',
  30         u'info_dict': {
  31             u'upload_date': u'20131002',
  32             u'title': u'The Mummy’s Hand (1940)',
  33         },
  34         u'params': {
  35             # rtmp download
  36             u'skip_download': True,
  37         },
  38     }]
  39
  40     def _real_extract(self, url):
  41         mobj = re.match(self._VALID_URL, url)
  42
  43         webpage_url = u'http://' + mobj.group('url')
  44         webpage = self._download_webpage(webpage_url, None) # Don't know video id yet
  45         video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
  46         mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/(?:embed|player)\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
  47         if not mobj:
  48             raise ExtractorError(u'Can\'t extract embed url and video id')
  49         playerdata_url = mobj.group(u'embed_url')
  50         video_id = mobj.group(u'video_id')
  51
  52         video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|',
  53             webpage, u'title')
  54         video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>',
  55             webpage, u'description', flags=re.DOTALL, fatal=False)
  56         if len(video_description) == 0:
  57             video_description = None
  58
  59         playerdata = self._download_webpage(playerdata_url, video_id)
  60         url = self._html_search_regex(r'\'streamer\': \'(?P<url>[^\']+)\'', playerdata, u'url')
  61         player_url = self._html_search_regex(r'\'flashplayer\': \'(?P<player_url>[^\']+)\'', playerdata, u'player_url')
  62         page_url = re.split(r'(?<=[^/])/([^/]|$)', player_url)[0]
  63
  64         sd_file = self._html_search_regex(r'\'file\': \'(?P<sd_file>[^\']+)\'', playerdata, u'sd_file')
  65         hd_file = self._html_search_regex(r'\'?file\'?: "(?P<hd_file>[^"]+)"', playerdata, u'hd_file')
  66         video_thumbnail = self._html_search_regex(r'\'image\': \'(?P<thumbnail>[^\']+)\'', playerdata, u'thumbnail', fatal=False)
  67
  68         formats = [
  69             {
  70                 'url': url,
  71                 'player_url': player_url,
  72                 'page_url': page_url,
  73                 'play_path': 'mp4:' + sd_file,
  74                 'ext': 'flv',
  75                 'format': 'sd',
  76                 'format_id': 'sd',
  77             },
  78             {
  79                 'url': url,
  80                 'player_url': player_url,
  81                 'page_url': page_url,
  82                 'play_path': 'mp4:' + hd_file,
  83                 'ext': 'flv',
  84                 'format': 'hd',
  85                 'format_id': 'hd',
  86             },
  87         ]
  88
  89         info = {
  90             'id': video_id,
  91             'title': video_title,
  92             'formats': formats,
  93             'description': video_description,
  94             'upload_date': video_date,
  95             'thumbnail': video_thumbnail,
  96         }
  97         # TODO: Remove when #980 has been merged
  98         info.update(formats[-1])
  99         return info