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'info_dict': {
  16             u'upload_date': u'20121110',
  17             u'title': u'“Angry Video Game Nerd: The Movie” – Trailer',
  18             u'description': u'md5:fb87405fcb42a331742a0dce2708560b',
  19         },
  20         u'params': {
  21             # rtmp download
  22             u'skip_download': True,
  23         },
  24     },
  25     {
  26         u'url': u'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
  27         u'file': u'521be8ef82b16.flv',
  28         u'info_dict': {
  29             u'upload_date': u'20131002',
  30             u'title': u'The Mummy’s Hand (1940)',
  31         },
  32         u'params': {
  33             # rtmp download
  34             u'skip_download': True,
  35         },
  36     }]
  37
  38     def _real_extract(self, url):
  39         mobj = re.match(self._VALID_URL, url)
  40
  41         webpage_url = u'http://' + mobj.group('url')
  42         webpage = self._download_webpage(webpage_url, None) # Don't know video id yet
  43         video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
  44         mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
  45         if not mobj:
  46             raise ExtractorError(u'Can\'t extract embed url and video id')
  47         playerdata_url = mobj.group(u'embed_url')
  48         video_id = mobj.group(u'video_id')
  49
  50         video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|',
  51             webpage, u'title')
  52         video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>',
  53             webpage, u'description', flags=re.DOTALL, fatal=False)
  54         if len(video_description) == 0:
  55             video_description = None
  56
  57         playerdata = self._download_webpage(playerdata_url, video_id)
  58         url = self._html_search_regex(r'\'streamer\': \'(?P<url>[^\']+)\'', playerdata, u'url')
  59
  60         sd_file = self._html_search_regex(r'\'file\': \'(?P<sd_file>[^\']+)\'', playerdata, u'sd_file')
  61         hd_file = self._html_search_regex(r'\'?file\'?: "(?P<hd_file>[^"]+)"', playerdata, u'hd_file')
  62         video_thumbnail = self._html_search_regex(r'\'image\': \'(?P<thumbnail>[^\']+)\'', playerdata, u'thumbnail', fatal=False)
  63
  64         formats = [
  65             {
  66                 'url': url,
  67                 'play_path': 'mp4:' + sd_file,
  68                 'rtmp_live': True, # workaround
  69                 'ext': 'flv',
  70                 'format': 'sd',
  71                 'format_id': 'sd',
  72             },
  73             {
  74                 'url': url,
  75                 'play_path': 'mp4:' + hd_file,
  76                 'rtmp_live': True, # workaround
  77                 'ext': 'flv',
  78                 'format': 'hd',
  79                 'format_id': 'hd',
  80             },
  81         ]
  82
  83         return {
  84             'id': video_id,
  85             'title': video_title,
  86             'formats': formats,
  87             'description': video_description,
  88             'upload_date': video_date,
  89             'thumbnail': video_thumbnail,
  90         }