Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/shared.py

   1 from __future__ import unicode_literals
   2
   3 import base64
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_urllib_parse
   7 from ..utils import (
   8     ExtractorError,
   9     int_or_none,
  10     sanitized_Request,
  11 )
  12
  13
  14 class SharedIE(InfoExtractor):
  15     IE_DESC = 'shared.sx and vivo.sx'
  16     _VALID_URL = r'http://(?:shared|vivo)\.sx/(?P<id>[\da-z]{10})'
  17
  18     _TESTS = [{
  19         'url': 'http://shared.sx/0060718775',
  20         'md5': '106fefed92a8a2adb8c98e6a0652f49b',
  21         'info_dict': {
  22             'id': '0060718775',
  23             'ext': 'mp4',
  24             'title': 'Bmp4',
  25             'filesize': 1720110,
  26         },
  27     }, {
  28         'url': 'http://vivo.sx/d7ddda0e78',
  29         'md5': '15b3af41be0b4fe01f4df075c2678b2c',
  30         'info_dict': {
  31             'id': 'd7ddda0e78',
  32             'ext': 'mp4',
  33             'title': 'Chicken',
  34             'filesize': 528031,
  35         },
  36     }]
  37
  38     def _real_extract(self, url):
  39         video_id = self._match_id(url)
  40         webpage = self._download_webpage(url, video_id)
  41
  42         if '>File does not exist<' in webpage:
  43             raise ExtractorError(
  44                 'Video %s does not exist' % video_id, expected=True)
  45
  46         download_form = self._hidden_inputs(webpage)
  47         request = sanitized_Request(
  48             url, compat_urllib_parse.urlencode(download_form))
  49         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  50
  51         video_page = self._download_webpage(
  52             request, video_id, 'Downloading video page')
  53
  54         video_url = self._html_search_regex(
  55             r'data-url="([^"]+)"', video_page, 'video URL')
  56         title = base64.b64decode(self._html_search_meta(
  57             'full:title', webpage, 'title').encode('utf-8')).decode('utf-8')
  58         filesize = int_or_none(self._html_search_meta(
  59             'full:size', webpage, 'file size', fatal=False))
  60         thumbnail = self._html_search_regex(
  61             r'data-poster="([^"]+)"', video_page, 'thumbnail', default=None)
  62
  63         return {
  64             'id': video_id,
  65             'url': video_url,
  66             'ext': 'mp4',
  67             'filesize': filesize,
  68             'title': title,
  69             'thumbnail': thumbnail,
  70         }