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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_urllib_request,
   8     compat_urllib_parse,
   9 )
  10 from ..utils import (
  11     ExtractorError,
  12 )
  13
  14
  15 class MooshareIE(InfoExtractor):
  16     IE_NAME = 'mooshare'
  17     IE_DESC = 'Mooshare.biz'
  18     _VALID_URL = r'http://(?:www\.)?mooshare\.biz/(?P<id>[\da-z]{12})'
  19
  20     _TESTS = [
  21         {
  22             'url': 'http://mooshare.biz/8dqtk4bjbp8g',
  23             'md5': '4e14f9562928aecd2e42c6f341c8feba',
  24             'info_dict': {
  25                 'id': '8dqtk4bjbp8g',
  26                 'ext': 'mp4',
  27                 'title': 'Comedy Football 2011 - (part 1-2)',
  28                 'duration': 893,
  29             },
  30         },
  31         {
  32             'url': 'http://mooshare.biz/aipjtoc4g95j',
  33             'info_dict': {
  34                 'id': 'aipjtoc4g95j',
  35                 'ext': 'mp4',
  36                 'title': 'Orange Caramel  Dashing Through the Snow',
  37                 'duration': 212,
  38             },
  39             'params': {
  40                 # rtmp download
  41                 'skip_download': True,
  42             }
  43         }
  44     ]
  45
  46     def _real_extract(self, url):
  47         video_id = self._match_id(url)
  48         page = self._download_webpage(url, video_id, 'Downloading page')
  49
  50         if re.search(r'>Video Not Found or Deleted<', page) is not None:
  51             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  52
  53         hash_key = self._html_search_regex(r'<input type="hidden" name="hash" value="([^"]+)">', page, 'hash')
  54         title = self._html_search_regex(r'(?m)<div class="blockTitle">\s*<h2>Watch ([^<]+)</h2>', page, 'title')
  55
  56         download_form = {
  57             'op': 'download1',
  58             'id': video_id,
  59             'hash': hash_key,
  60         }
  61
  62         request = compat_urllib_request.Request(
  63             'http://mooshare.biz/%s' % video_id, compat_urllib_parse.urlencode(download_form))
  64         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  65
  66         self._sleep(5, video_id)
  67
  68         video_page = self._download_webpage(request, video_id, 'Downloading video page')
  69
  70         thumbnail = self._html_search_regex(r'image:\s*"([^"]+)",', video_page, 'thumbnail', fatal=False)
  71         duration_str = self._html_search_regex(r'duration:\s*"(\d+)",', video_page, 'duration', fatal=False)
  72         duration = int(duration_str) if duration_str is not None else None
  73
  74         formats = []
  75
  76         # SD video
  77         mobj = re.search(r'(?m)file:\s*"(?P<url>[^"]+)",\s*provider:', video_page)
  78         if mobj is not None:
  79             formats.append({
  80                 'url': mobj.group('url'),
  81                 'format_id': 'sd',
  82                 'format': 'SD',
  83             })
  84
  85         # HD video
  86         mobj = re.search(r'\'hd-2\': { file: \'(?P<url>[^\']+)\' },', video_page)
  87         if mobj is not None:
  88             formats.append({
  89                 'url': mobj.group('url'),
  90                 'format_id': 'hd',
  91                 'format': 'HD',
  92             })
  93
  94         # rtmp video
  95         mobj = re.search(r'(?m)file: "(?P<playpath>[^"]+)",\s*streamer: "(?P<rtmpurl>rtmp://[^"]+)",', video_page)
  96         if mobj is not None:
  97             formats.append({
  98                 'url': mobj.group('rtmpurl'),
  99                 'play_path': mobj.group('playpath'),
 100                 'rtmp_live': False,
 101                 'ext': 'mp4',
 102                 'format_id': 'rtmp',
 103                 'format': 'HD',
 104             })
 105
 106         return {
 107             'id': video_id,
 108             'title': title,
 109             'thumbnail': thumbnail,
 110             'duration': duration,
 111             'formats': formats,
 112         }