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     url_or_none,
   9     urlencode_postdata,
  10 )
  11
  12
  13 class SharedBaseIE(InfoExtractor):
  14     def _real_extract(self, url):
  15         video_id = self._match_id(url)
  16
  17         webpage, urlh = self._download_webpage_handle(url, video_id)
  18
  19         if self._FILE_NOT_FOUND in webpage:
  20             raise ExtractorError(
  21                 'Video %s does not exist' % video_id, expected=True)
  22
  23         video_url = self._extract_video_url(webpage, video_id, url)
  24
  25         title = compat_b64decode(self._html_search_meta(
  26             'full:title', webpage, 'title')).decode('utf-8')
  27         filesize = int_or_none(self._html_search_meta(
  28             'full:size', webpage, 'file size', fatal=False))
  29
  30         return {
  31             'id': video_id,
  32             'url': video_url,
  33             'ext': 'mp4',
  34             'filesize': filesize,
  35             'title': title,
  36         }
  37
  38
  39 class SharedIE(SharedBaseIE):
  40     IE_DESC = 'shared.sx'
  41     _VALID_URL = r'https?://shared\.sx/(?P<id>[\da-z]{10})'
  42     _FILE_NOT_FOUND = '>File does not exist<'
  43
  44     _TEST = {
  45         'url': 'http://shared.sx/0060718775',
  46         'md5': '106fefed92a8a2adb8c98e6a0652f49b',
  47         'info_dict': {
  48             'id': '0060718775',
  49             'ext': 'mp4',
  50             'title': 'Bmp4',
  51             'filesize': 1720110,
  52         },
  53     }
  54
  55     def _extract_video_url(self, webpage, video_id, url):
  56         download_form = self._hidden_inputs(webpage)
  57
  58         video_page = self._download_webpage(
  59             url, video_id, 'Downloading video page',
  60             data=urlencode_postdata(download_form),
  61             headers={
  62                 'Content-Type': 'application/x-www-form-urlencoded',
  63                 'Referer': url,
  64             })
  65
  66         video_url = self._html_search_regex(
  67             r'data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
  68             video_page, 'video URL', group='url')
  69
  70         return video_url
  71
  72
  73 class VivoIE(SharedBaseIE):
  74     IE_DESC = 'vivo.sx'
  75     _VALID_URL = r'https?://vivo\.sx/(?P<id>[\da-z]{10})'
  76     _FILE_NOT_FOUND = '>The file you have requested does not exists or has been removed'
  77
  78     _TEST = {
  79         'url': 'http://vivo.sx/d7ddda0e78',
  80         'md5': '15b3af41be0b4fe01f4df075c2678b2c',
  81         'info_dict': {
  82             'id': 'd7ddda0e78',
  83             'ext': 'mp4',
  84             'title': 'Chicken',
  85             'filesize': 528031,
  86         },
  87     }
  88
  89     def _extract_video_url(self, webpage, video_id, *args):
  90         def decode_url(encoded_url):
  91             return compat_b64decode(encoded_url).decode('utf-8')
  92
  93         stream_url = url_or_none(decode_url(self._search_regex(
  94             r'data-stream\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
  95             'stream url', default=None, group='url')))
  96         if stream_url:
  97             return stream_url
  98         return self._parse_json(
  99             self._search_regex(
 100                 r'InitializeStream\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
 101                 webpage, 'stream', group='url'),
 102             video_id, transform_source=decode_url)[0]