_ 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.mp4',
  15         u'md5': u'fde81fbafaee331785f58cd6c0d46190',
  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     },
  22     {
  23         u'url': u'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
  24         u'file': u'521be8ef82b16.mp4',
  25         u'md5': u'd72f10cd39eac4215048f62ab477a511',
  26         u'info_dict': {
  27             u'upload_date': u'20131002',
  28             u'title': u'The Mummy’s Hand (1940)',
  29         },
  30     }]
  31
  32     def _real_extract(self, url):
  33         mobj = re.match(self._VALID_URL, url)
  34
  35         webpage_url = u'http://' + mobj.group('url')
  36         webpage = self._download_webpage(webpage_url, None) # Don't know video id yet
  37         video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
  38         mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
  39         if not mobj:
  40             raise ExtractorError(u'Can\'t extract embed url and video id')
  41         playerdata_url = mobj.group(u'embed_url')
  42         video_id = mobj.group(u'video_id')
  43
  44         video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|',
  45             webpage, u'title')
  46         video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>',
  47             webpage, u'description', flags=re.DOTALL, fatal=False)
  48         if len(video_description) == 0:
  49             video_description = None
  50
  51         playerdata = self._download_webpage(playerdata_url, video_id)
  52
  53         sd_url = self._html_search_regex(r'file: \'(?P<sd_file>[^\']+)\', label: \'SD\'', playerdata, u'sd_file')
  54         hd_url= self._html_search_regex(r'file: \'(?P<hd_file>[^\']+)\', label: \'HD\'', playerdata, u'hd_file')
  55         video_thumbnail = self._html_search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, u'thumbnail', fatal=False)
  56
  57         formats = [
  58             {
  59                 'url': sd_url,
  60                 'ext': 'mp4',
  61                 'format': 'sd',
  62                 'format_id': 'sd',
  63             },
  64             {
  65                 'url': hd_url,
  66                 'ext': 'mp4',
  67                 'format': 'hd',
  68                 'format_id': 'hd',
  69             },
  70         ]
  71
  72         return {
  73             'id': video_id,
  74             'title': video_title,
  75             'formats': formats,
  76             'description': video_description,
  77             'upload_date': video_date,
  78             'thumbnail': video_thumbnail,
  79         }