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

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import time
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_urllib_request,
   9     compat_urllib_parse,
  10 )
  11 from ..utils import (
  12     ExtractorError,
  13 )
  14
  15
  16 class MooshareIE(InfoExtractor):
  17     IE_NAME = 'mooshare'
  18     IE_DESC = 'Mooshare.biz'
  19     _VALID_URL = r'http://(?:www\.)?mooshare\.biz/(?P<id>[\da-z]{12})'
  20
  21     _TESTS = [
  22         {
  23             'url': 'http://mooshare.biz/8dqtk4bjbp8g',
  24             'md5': '4e14f9562928aecd2e42c6f341c8feba',
  25             'info_dict': {
  26                 'id': '8dqtk4bjbp8g',
  27                 'ext': 'mp4',
  28                 'title': 'Comedy Football 2011 - (part 1-2)',
  29                 'duration': 893,
  30             },
  31         },
  32         {
  33             'url': 'http://mooshare.biz/aipjtoc4g95j',
  34             'info_dict': {
  35                 'id': 'aipjtoc4g95j',
  36                 'ext': 'mp4',
  37                 'title': 'Orange Caramel  Dashing Through the Snow',
  38                 'duration': 212,
  39             },
  40             'params': {
  41                 # rtmp download
  42                 'skip_download': True,
  43             }
  44         }
  45     ]
  46
  47     def _real_extract(self, url):
  48         video_id = self._match_id(url)
  49         page = self._download_webpage(url, video_id, 'Downloading page')
  50
  51         if re.search(r'>Video Not Found or Deleted<', page) is not None:
  52             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  53
  54         hash_key = self._html_search_regex(r'<input type="hidden" name="hash" value="([^"]+)">', page, 'hash')
  55         title = self._html_search_regex(r'(?m)<div class="blockTitle">\s*<h2>Watch ([^<]+)</h2>', page, 'title')
  56
  57         download_form = {
  58             'op': 'download1',
  59             'id': video_id,
  60             'hash': hash_key,
  61         }
  62
  63         request = compat_urllib_request.Request(
  64             'http://mooshare.biz/%s' % video_id, compat_urllib_parse.urlencode(download_form))
  65         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  66
  67         self._sleep(5, video_id)
  68
  69         video_page = self._download_webpage(request, video_id, 'Downloading video page')
  70
  71         thumbnail = self._html_search_regex(r'image:\s*"([^"]+)",', video_page, 'thumbnail', fatal=False)
  72         duration_str = self._html_search_regex(r'duration:\s*"(\d+)",', video_page, 'duration', fatal=False)
  73         duration = int(duration_str) if duration_str is not None else None
  74
  75         formats = []
  76
  77         # SD video
  78         mobj = re.search(r'(?m)file:\s*"(?P<url>[^"]+)",\s*provider:', video_page)
  79         if mobj is not None:
  80             formats.append({
  81                 'url': mobj.group('url'),
  82                 'format_id': 'sd',
  83                 'format': 'SD',
  84             })
  85
  86         # HD video
  87         mobj = re.search(r'\'hd-2\': { file: \'(?P<url>[^\']+)\' },', video_page)
  88         if mobj is not None:
  89             formats.append({
  90                 'url': mobj.group('url'),
  91                 'format_id': 'hd',
  92                 'format': 'HD',
  93             })
  94
  95         # rtmp video
  96         mobj = re.search(r'(?m)file: "(?P<playpath>[^"]+)",\s*streamer: "(?P<rtmpurl>rtmp://[^"]+)",', video_page)
  97         if mobj is not None:
  98             formats.append({
  99                 'url': mobj.group('rtmpurl'),
 100                 'play_path': mobj.group('playpath'),
 101                 'rtmp_live': False,
 102                 'ext': 'mp4',
 103                 'format_id': 'rtmp',
 104                 'format': 'HD',
 105             })
 106
 107         return {
 108             'id': video_id,
 109             'title': title,
 110             'thumbnail': thumbnail,
 111             'duration': duration,
 112             'formats': formats,
 113         }