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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import (
   5     compat_b64decode,
   6     compat_urllib_parse_unquote_plus,
   7 )
   8 from ..utils import (
   9     determine_ext,
  10     ExtractorError,
  11     int_or_none,
  12     js_to_json,
  13     KNOWN_EXTENSIONS,
  14     parse_filesize,
  15     rot47,
  16     url_or_none,
  17     urlencode_postdata,
  18 )
  19
  20
  21 class SharedBaseIE(InfoExtractor):
  22     def _real_extract(self, url):
  23         video_id = self._match_id(url)
  24
  25         webpage, urlh = self._download_webpage_handle(url, video_id)
  26
  27         if self._FILE_NOT_FOUND in webpage:
  28             raise ExtractorError(
  29                 'Video %s does not exist' % video_id, expected=True)
  30
  31         video_url = self._extract_video_url(webpage, video_id, url)
  32
  33         title = self._extract_title(webpage)
  34         filesize = int_or_none(self._extract_filesize(webpage))
  35
  36         return {
  37             'id': video_id,
  38             'url': video_url,
  39             'ext': 'mp4',
  40             'filesize': filesize,
  41             'title': title,
  42         }
  43
  44     def _extract_title(self, webpage):
  45         return compat_b64decode(self._html_search_meta(
  46             'full:title', webpage, 'title')).decode('utf-8')
  47
  48     def _extract_filesize(self, webpage):
  49         return self._html_search_meta(
  50             'full:size', webpage, 'file size', fatal=False)
  51
  52
  53 class SharedIE(SharedBaseIE):
  54     IE_DESC = 'shared.sx'
  55     _VALID_URL = r'https?://shared\.sx/(?P<id>[\da-z]{10})'
  56     _FILE_NOT_FOUND = '>File does not exist<'
  57
  58     _TEST = {
  59         'url': 'http://shared.sx/0060718775',
  60         'md5': '106fefed92a8a2adb8c98e6a0652f49b',
  61         'info_dict': {
  62             'id': '0060718775',
  63             'ext': 'mp4',
  64             'title': 'Bmp4',
  65             'filesize': 1720110,
  66         },
  67     }
  68
  69     def _extract_video_url(self, webpage, video_id, url):
  70         download_form = self._hidden_inputs(webpage)
  71
  72         video_page = self._download_webpage(
  73             url, video_id, 'Downloading video page',
  74             data=urlencode_postdata(download_form),
  75             headers={
  76                 'Content-Type': 'application/x-www-form-urlencoded',
  77                 'Referer': url,
  78             })
  79
  80         video_url = self._html_search_regex(
  81             r'data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
  82             video_page, 'video URL', group='url')
  83
  84         return video_url
  85
  86
  87 class VivoIE(SharedBaseIE):
  88     IE_DESC = 'vivo.sx'
  89     _VALID_URL = r'https?://vivo\.sx/(?P<id>[\da-z]{10})'
  90     _FILE_NOT_FOUND = '>The file you have requested does not exists or has been removed'
  91
  92     _TEST = {
  93         'url': 'http://vivo.sx/d7ddda0e78',
  94         'md5': '15b3af41be0b4fe01f4df075c2678b2c',
  95         'info_dict': {
  96             'id': 'd7ddda0e78',
  97             'ext': 'mp4',
  98             'title': 'Chicken',
  99             'filesize': 515659,
 100         },
 101     }
 102
 103     def _extract_title(self, webpage):
 104         title = self._html_search_regex(
 105             r'data-name\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1', webpage,
 106             'title', default=None, group='title')
 107         if title:
 108             ext = determine_ext(title)
 109             if ext.lower() in KNOWN_EXTENSIONS:
 110                 title = title.rpartition('.' + ext)[0]
 111             return title
 112         return self._og_search_title(webpage)
 113
 114     def _extract_filesize(self, webpage):
 115         return parse_filesize(self._search_regex(
 116             r'data-type=["\']video["\'][^>]*>Watch.*?<strong>\s*\((.+?)\)',
 117             webpage, 'filesize', fatal=False))
 118
 119     def _extract_video_url(self, webpage, video_id, url):
 120         def decode_url_old(encoded_url):
 121             return compat_b64decode(encoded_url).decode('utf-8')
 122
 123         stream_url = self._search_regex(
 124             r'data-stream\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
 125             'stream url', default=None, group='url')
 126         if stream_url:
 127             stream_url = url_or_none(decode_url_old(stream_url))
 128         if stream_url:
 129             return stream_url
 130
 131         def decode_url(encoded_url):
 132             return rot47(compat_urllib_parse_unquote_plus(encoded_url))
 133
 134         return decode_url(self._parse_json(
 135             self._search_regex(
 136                 r'(?s)InitializeStream\s*\(\s*({.+?})\s*\)\s*;', webpage,
 137                 'stream'),
 138             video_id, transform_source=js_to_json)['source'])