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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8 )
   9
  10
  11 class CinemassacreIE(InfoExtractor):
  12     _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})/.+?'
  13     _TESTS = [
  14         {
  15             'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
  16             'file': '19911.mp4',
  17             'md5': 'fde81fbafaee331785f58cd6c0d46190',
  18             'info_dict': {
  19                 'upload_date': '20121110',
  20                 'title': '“Angry Video Game Nerd: The Movie” – Trailer',
  21                 'description': 'md5:fb87405fcb42a331742a0dce2708560b',
  22             },
  23         },
  24         {
  25             'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
  26             'file': '521be8ef82b16.mp4',
  27             'md5': 'd72f10cd39eac4215048f62ab477a511',
  28             'info_dict': {
  29                 'upload_date': '20131002',
  30                 'title': 'The Mummy’s Hand (1940)',
  31             },
  32         }
  33     ]
  34
  35     def _real_extract(self, url):
  36         mobj = re.match(self._VALID_URL, url)
  37
  38         webpage = self._download_webpage(url, None)  # Don't know video id yet
  39         video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
  40         mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
  41         if not mobj:
  42             raise ExtractorError('Can\'t extract embed url and video id')
  43         playerdata_url = mobj.group('embed_url')
  44         video_id = mobj.group('video_id')
  45
  46         video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|',
  47             webpage, 'title')
  48         video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>',
  49             webpage, 'description', flags=re.DOTALL, fatal=False)
  50         if len(video_description) == 0:
  51             video_description = None
  52
  53         playerdata = self._download_webpage(playerdata_url, video_id)
  54
  55         sd_url = self._html_search_regex(r'file: \'(?P<sd_file>[^\']+)\', label: \'SD\'', playerdata, 'sd_file')
  56         hd_url = self._html_search_regex(r'file: \'(?P<hd_file>[^\']+)\', label: \'HD\'', playerdata, 'hd_file')
  57         video_thumbnail = self._html_search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False)
  58
  59         formats = [
  60             {
  61                 'url': sd_url,
  62                 'ext': 'mp4',
  63                 'format': 'sd',
  64                 'format_id': 'sd',
  65             },
  66             {
  67                 'url': hd_url,
  68                 'ext': 'mp4',
  69                 'format': 'hd',
  70                 'format_id': 'hd',
  71             },
  72         ]
  73
  74         return {
  75             'id': video_id,
  76             'title': video_title,
  77             'formats': formats,
  78             'description': video_description,
  79             'upload_date': video_date,
  80             'thumbnail': video_thumbnail,
  81         }