Raphaël G. Git Repositories - youtubedl/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 ..utils import (
   8     ExtractorError,
   9     compat_urllib_request,
  10     compat_urllib_parse,
  11 )
  12
  13
  14 class MooshareIE(InfoExtractor):
  15     IE_NAME = 'mooshare'
  16     IE_DESC = 'Mooshare.biz'
  17     _VALID_URL = r'http://mooshare\.biz/(?P<id>[\da-z]{12})'
  18
  19     _TESTS = [
  20         {
  21             'url': 'http://mooshare.biz/8dqtk4bjbp8g',
  22             'md5': '4e14f9562928aecd2e42c6f341c8feba',
  23             'info_dict': {
  24                 'id': '8dqtk4bjbp8g',
  25                 'ext': 'mp4',
  26                 'title': 'Comedy Football 2011 - (part 1-2)',
  27                 'duration': 893,
  28             },
  29         },
  30         {
  31             'url': 'http://mooshare.biz/aipjtoc4g95j',
  32             'info_dict': {
  33                 'id': 'aipjtoc4g95j',
  34                 'ext': 'mp4',
  35                 'title': 'Orange Caramel  Dashing Through the Snow',
  36                 'duration': 212,
  37             },
  38             'params': {
  39                 # rtmp download
  40                 'skip_download': True,
  41             }
  42         }
  43     ]
  44
  45     def _real_extract(self, url):
  46         mobj = re.match(self._VALID_URL, url)
  47         video_id = mobj.group('id')
  48
  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(u'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.to_screen('%s: Waiting for timeout' % video_id)
  68         time.sleep(5)
  69
  70         video_page = self._download_webpage(request, video_id, 'Downloading video page')
  71
  72         thumbnail = self._html_search_regex(r'image:\s*"([^"]+)",', video_page, 'thumbnail', fatal=False)
  73         duration_str = self._html_search_regex(r'duration:\s*"(\d+)",', video_page, 'duration', fatal=False)
  74         duration = int(duration_str) if duration_str is not None else None
  75
  76         formats = []
  77
  78         # SD video
  79         mobj = re.search(r'(?m)file:\s*"(?P<url>[^"]+)",\s*provider:', video_page)
  80         if mobj is not None:
  81             formats.append({
  82                 'url': mobj.group('url'),
  83                 'format_id': 'sd',
  84                 'format': 'SD',
  85             })
  86
  87         # HD video
  88         mobj = re.search(r'\'hd-2\': { file: \'(?P<url>[^\']+)\' },', video_page)
  89         if mobj is not None:
  90             formats.append({
  91                 'url': mobj.group('url'),
  92                 'format_id': 'hd',
  93                 'format': 'HD',
  94             })
  95
  96         # rtmp video
  97         mobj = re.search(r'(?m)file: "(?P<playpath>[^"]+)",\s*streamer: "(?P<rtmpurl>rtmp://[^"]+)",', video_page)
  98         if mobj is not None:
  99             formats.append({
 100                 'url': mobj.group('rtmpurl'),
 101                 'play_path': mobj.group('playpath'),
 102                 'rtmp_live': False,
 103                 'ext': 'mp4',
 104                 'format_id': 'rtmp',
 105                 'format': 'HD',
 106             })
 107
 108         return {
 109             'id': video_id,
 110             'title': title,
 111             'thumbnail': thumbnail,
 112             'duration': duration,
 113             'formats': formats,
 114         }