_ 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 class CinemassacreIE(InfoExtractor):
  10     _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})/.+?)(?:[/?].*)?'
  11     _TESTS = [{
  12         u'url': u'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
  13         u'file': u'19911.mp4',
  14         u'info_dict': {
  15             u'upload_date': u'20121110',
  16             u'title': u'“Angry Video Game Nerd: The Movie” – Trailer',
  17             u'description': u'md5:fb87405fcb42a331742a0dce2708560b',
  18         },
  19         u'params': {
  20             u'skip_download': True,
  21         },
  22     },
  23     {
  24         u'url': u'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
  25         u'file': u'521be8ef82b16.mp4',
  26         u'info_dict': {
  27             u'upload_date': u'20131002',
  28             u'title': u'The Mummy’s Hand (1940)',
  29         },
  30         u'params': {
  31             u'skip_download': True,
  32         },
  33     }]
  34
  35     def _real_extract(self,url):
  36         mobj = re.match(self._VALID_URL, url)
  37
  38         webpage_url = u'http://' + mobj.group('url')
  39         webpage = self._download_webpage(webpage_url, None) # Don't know video id yet
  40         video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
  41         mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/(?:embed|player)\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
  42         if not mobj:
  43             raise ExtractorError(u'Can\'t extract embed url and video id')
  44         playerdata_url = mobj.group(u'embed_url')
  45         video_id = mobj.group(u'video_id')
  46
  47         video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|',
  48             webpage, u'title')
  49         video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>',
  50             webpage, u'description', flags=re.DOTALL, fatal=False)
  51         if len(video_description) == 0:
  52             video_description = None
  53
  54         playerdata = self._download_webpage(playerdata_url, video_id)
  55         base_url = self._html_search_regex(r'\'streamer\': \'(?P<base_url>rtmp://[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3})/(?:vod|Cinemassacre)\'',
  56             playerdata, u'base_url')
  57         base_url += '/Cinemassacre/'
  58          # Important: The file names in playerdata are not used by the player and even wrong for some videos
  59         sd_file = 'Cinemassacre-%s_high.mp4' % video_id
  60         hd_file = 'Cinemassacre-%s.mp4' % video_id
  61         video_thumbnail = 'http://image.screenwavemedia.com/Cinemassacre/Cinemassacre-%s_thumb_640x360.jpg' % video_id
  62
  63         formats = [{
  64             'id':          video_id,
  65             'url':         base_url + hd_file,
  66             'format':      'hd',
  67             'ext':         'mp4',
  68             'title':       video_title,
  69             'description': video_description,
  70             'upload_date': video_date,
  71             'thumbnail':   video_thumbnail,
  72         },
  73         {
  74             'id':          video_id,
  75             'url':         base_url + sd_file,
  76             'ext':         'mp4',
  77             'format':      'sd',
  78             'title':       video_title,
  79             'description': video_description,
  80             'upload_date': video_date,
  81             'thumbnail':   video_thumbnail,
  82         }]
  83
  84         if self._downloader.params.get('listformats', None):
  85             self._print_formats(formats)
  86             return
  87
  88         req_format = self._downloader.params.get('format', 'best')
  89         self.to_screen(u'Format: %s' % req_format)
  90
  91         if req_format is None or req_format == 'best':
  92             return [formats[0]]
  93         elif req_format == 'worst':
  94             return [formats[-1]]
  95         elif req_format in ('-1', 'all'):
  96             return formats
  97         else:
  98             format = self._specific( req_format, formats )
  99             if format is None:
 100                 raise ExtractorError(u'Requested format not available')
 101             return [format]
 102
 103     def _print_formats(self, formats):
 104         """Print all available formats"""
 105         print(u'Available formats:')
 106         print(u'ext\t\tformat')
 107         print(u'---------------------------------')
 108         for format in formats:
 109             print(u'%s\t\t%s'  % (format['ext'], format['format']))
 110
 111     def _specific(self, req_format, formats):
 112         for x in formats:
 113             if x["format"] == req_format:
 114                 return x
 115         return None