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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     int_or_none,
  10 )
  11
  12
  13 class CinemassacreIE(InfoExtractor):
  14     _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)'
  15     _TESTS = [
  16         {
  17             'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
  18             'md5': 'fde81fbafaee331785f58cd6c0d46190',
  19             'info_dict': {
  20                 'id': '19911',
  21                 'ext': 'mp4',
  22                 'upload_date': '20121110',
  23                 'title': '“Angry Video Game Nerd: The Movie” – Trailer',
  24                 'description': 'md5:fb87405fcb42a331742a0dce2708560b',
  25             },
  26         },
  27         {
  28             'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
  29             'md5': 'd72f10cd39eac4215048f62ab477a511',
  30             'info_dict': {
  31                 'id': '521be8ef82b16',
  32                 'ext': 'mp4',
  33                 'upload_date': '20131002',
  34                 'title': 'The Mummy’s Hand (1940)',
  35             },
  36         }
  37     ]
  38
  39     def _real_extract(self, url):
  40         mobj = re.match(self._VALID_URL, url)
  41         display_id = mobj.group('display_id')
  42
  43         webpage = self._download_webpage(url, display_id)
  44         video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
  45         mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P<full_video_id>(?:Cinemassacre-)?(?P<video_id>.+?)))"', webpage)
  46         if not mobj:
  47             raise ExtractorError('Can\'t extract embed url and video id')
  48         playerdata_url = mobj.group('embed_url')
  49         video_id = mobj.group('video_id')
  50         full_video_id = mobj.group('full_video_id')
  51
  52         video_title = self._html_search_regex(
  53             r'<title>(?P<title>.+?)\|', webpage, 'title')
  54         video_description = self._html_search_regex(
  55             r'<div class="entry-content">(?P<description>.+?)</div>',
  56             webpage, 'description', flags=re.DOTALL, fatal=False)
  57         video_thumbnail = self._og_search_thumbnail(webpage)
  58
  59         playerdata = self._download_webpage(playerdata_url, video_id, 'Downloading player webpage')
  60
  61         vidurl = self._search_regex(
  62             r'\'vidurl\'\s*:\s*"([^\']+)"', playerdata, 'vidurl').replace('\\/', '/')
  63
  64         videolist_url = None
  65
  66         mobj = re.search(r"'videoserver'\s*:\s*'(?P<videoserver>[^']+)'", playerdata)
  67         if mobj:
  68             videoserver = mobj.group('videoserver')
  69             mobj = re.search(r'\'vidid\'\s*:\s*"(?P<vidid>[^\']+)"', playerdata)
  70             vidid = mobj.group('vidid') if mobj else full_video_id
  71             videolist_url = 'http://%s/vod/smil:%s.smil/jwplayer.smil' % (videoserver, vidid)
  72         else:
  73             mobj = re.search(r"file\s*:\s*'(?P<smil>http.+?/jwplayer\.smil)'", playerdata)
  74             if mobj:
  75                 videolist_url = mobj.group('smil')
  76
  77         if videolist_url:
  78             videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML')
  79             formats = []
  80             baseurl = vidurl[:vidurl.rfind('/')+1]
  81             for video in videolist.findall('.//video'):
  82                 src = video.get('src')
  83                 if not src:
  84                     continue
  85                 file_ = src.partition(':')[-1]
  86                 width = int_or_none(video.get('width'))
  87                 height = int_or_none(video.get('height'))
  88                 bitrate = int_or_none(video.get('system-bitrate'))
  89                 format = {
  90                     'url': baseurl + file_,
  91                     'format_id': src.rpartition('.')[0].rpartition('_')[-1],
  92                 }
  93                 if width or height:
  94                     format.update({
  95                         'tbr': bitrate // 1000 if bitrate else None,
  96                         'width': width,
  97                         'height': height,
  98                     })
  99                 else:
 100                     format.update({
 101                         'abr': bitrate // 1000 if bitrate else None,
 102                         'vcodec': 'none',
 103                     })
 104                 formats.append(format)
 105             self._sort_formats(formats)
 106         else:
 107             formats = [{
 108                 'url': vidurl,
 109             }]
 110
 111         return {
 112             'id': video_id,
 113             'title': video_title,
 114             'formats': formats,
 115             'description': video_description,
 116             'upload_date': video_date,
 117             'thumbnail': video_thumbnail,
 118         }