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