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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_b64decode
   5 from ..utils import (
   6     ExtractorError,
   7     int_or_none,
   8     urlencode_postdata,
   9 )
  10
  11
  12 class SharedBaseIE(InfoExtractor):
  13     def _real_extract(self, url):
  14         video_id = self._match_id(url)
  15
  16         webpage, urlh = self._download_webpage_handle(url, video_id)
  17
  18         if self._FILE_NOT_FOUND in webpage:
  19             raise ExtractorError(
  20                 'Video %s does not exist' % video_id, expected=True)
  21
  22         video_url = self._extract_video_url(webpage, video_id, url)
  23
  24         title = compat_b64decode(self._html_search_meta(
  25             'full:title', webpage, 'title')).decode('utf-8')
  26         filesize = int_or_none(self._html_search_meta(
  27             'full:size', webpage, 'file size', fatal=False))
  28
  29         return {
  30             'id': video_id,
  31             'url': video_url,
  32             'ext': 'mp4',
  33             'filesize': filesize,
  34             'title': title,
  35         }
  36
  37
  38 class SharedIE(SharedBaseIE):
  39     IE_DESC = 'shared.sx'
  40     _VALID_URL = r'https?://shared\.sx/(?P<id>[\da-z]{10})'
  41     _FILE_NOT_FOUND = '>File does not exist<'
  42
  43     _TEST = {
  44         'url': 'http://shared.sx/0060718775',
  45         'md5': '106fefed92a8a2adb8c98e6a0652f49b',
  46         'info_dict': {
  47             'id': '0060718775',
  48             'ext': 'mp4',
  49             'title': 'Bmp4',
  50             'filesize': 1720110,
  51         },
  52     }
  53
  54     def _extract_video_url(self, webpage, video_id, url):
  55         download_form = self._hidden_inputs(webpage)
  56
  57         video_page = self._download_webpage(
  58             url, video_id, 'Downloading video page',
  59             data=urlencode_postdata(download_form),
  60             headers={
  61                 'Content-Type': 'application/x-www-form-urlencoded',
  62                 'Referer': url,
  63             })
  64
  65         video_url = self._html_search_regex(
  66             r'data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
  67             video_page, 'video URL', group='url')
  68
  69         return video_url
  70
  71
  72 class VivoIE(SharedBaseIE):
  73     IE_DESC = 'vivo.sx'
  74     _VALID_URL = r'https?://vivo\.sx/(?P<id>[\da-z]{10})'
  75     _FILE_NOT_FOUND = '>The file you have requested does not exists or has been removed'
  76
  77     _TEST = {
  78         'url': 'http://vivo.sx/d7ddda0e78',
  79         'md5': '15b3af41be0b4fe01f4df075c2678b2c',
  80         'info_dict': {
  81             'id': 'd7ddda0e78',
  82             'ext': 'mp4',
  83             'title': 'Chicken',
  84             'filesize': 528031,
  85         },
  86     }
  87
  88     def _extract_video_url(self, webpage, video_id, *args):
  89         return self._parse_json(
  90             self._search_regex(
  91                 r'InitializeStream\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
  92                 webpage, 'stream', group='url'),
  93             video_id,
  94             transform_source=lambda x: compat_b64decode(x).decode('utf-8'))[0]