_ 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})/(?P<display_id>[^?#/]+)'
  13     _TESTS = [
  14         {
  15             'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
  16             'file': '19911.mp4',
  17             'md5': '782f8504ca95a0eba8fc9177c373eec7',
  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': 'dec39ee5118f8d9cc067f45f9cbe3a35',
  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         display_id = mobj.group('display_id')
  38
  39         webpage = self._download_webpage(url, display_id)
  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/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
  42         if not mobj:
  43             raise ExtractorError('Can\'t extract embed url and video id')
  44         playerdata_url = mobj.group('embed_url')
  45         video_id = mobj.group('video_id')
  46
  47         video_title = self._html_search_regex(
  48             r'<title>(?P<title>.+?)\|', webpage, 'title')
  49         video_description = self._html_search_regex(
  50             r'<div class="entry-content">(?P<description>.+?)</div>',
  51             webpage, 'description', flags=re.DOTALL, fatal=False)
  52
  53         playerdata = self._download_webpage(playerdata_url, video_id)
  54
  55         sd_url = self._html_search_regex(r'file: \'([^\']+)\', label: \'SD\'', playerdata, 'sd_file')
  56         hd_url = self._html_search_regex(
  57             r'file: \'([^\']+)\', label: \'HD\'', playerdata, 'hd_file',
  58             default=None)
  59         video_thumbnail = self._html_search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False)
  60
  61         formats = [{
  62             'url': sd_url,
  63             'ext': 'mp4',
  64             'format': 'sd',
  65             'format_id': 'sd',
  66             'quality': 1,
  67         }]
  68         if hd_url:
  69             formats.append({
  70                 'url': hd_url,
  71                 'ext': 'mp4',
  72                 'format': 'hd',
  73                 'format_id': 'hd',
  74                 'quality': 2,
  75             })
  76         self._sort_formats(formats)
  77
  78         return {
  79             'id': video_id,
  80             'title': video_title,
  81             'formats': formats,
  82             'description': video_description,
  83             'upload_date': video_date,
  84             'thumbnail': video_thumbnail,
  85         }