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