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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_b64decode
   7 from ..utils import (
   8     ExtractorError,
   9     int_or_none,
  10     url_or_none,
  11     urlencode_postdata,
  12     unescapeHTML,
  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._html_search_meta(
  30             'full:size', webpage, 'file size', fatal=False))
  31
  32         return {
  33             'id': video_id,
  34             'url': video_url,
  35             'ext': 'mp4',
  36             'filesize': filesize,
  37             'title': title,
  38         }
  39
  40     def _extract_title(self, webpage):
  41         return compat_b64decode(self._html_search_meta(
  42             'full:title', webpage, 'title')).decode('utf-8')
  43
  44
  45 class SharedIE(SharedBaseIE):
  46     IE_DESC = 'shared.sx'
  47     _VALID_URL = r'https?://shared\.sx/(?P<id>[\da-z]{10})'
  48     _FILE_NOT_FOUND = '>File does not exist<'
  49
  50     _TEST = {
  51         'url': 'http://shared.sx/0060718775',
  52         'md5': '106fefed92a8a2adb8c98e6a0652f49b',
  53         'info_dict': {
  54             'id': '0060718775',
  55             'ext': 'mp4',
  56             'title': 'Bmp4',
  57             'filesize': 1720110,
  58         },
  59     }
  60
  61     def _extract_video_url(self, webpage, video_id, url):
  62         download_form = self._hidden_inputs(webpage)
  63
  64         video_page = self._download_webpage(
  65             url, video_id, 'Downloading video page',
  66             data=urlencode_postdata(download_form),
  67             headers={
  68                 'Content-Type': 'application/x-www-form-urlencoded',
  69                 'Referer': url,
  70             })
  71
  72         video_url = self._html_search_regex(
  73             r'data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
  74             video_page, 'video URL', group='url')
  75
  76         return video_url
  77
  78
  79 class VivoIE(SharedBaseIE):
  80     IE_DESC = 'vivo.sx'
  81     _VALID_URL = r'https?://vivo\.sx/(?P<id>[\da-z]{10})'
  82     _FILE_NOT_FOUND = '>The file you have requested does not exists or has been removed'
  83
  84     _TEST = {
  85         'url': 'http://vivo.sx/d7ddda0e78',
  86         'md5': '15b3af41be0b4fe01f4df075c2678b2c',
  87         'info_dict': {
  88             'id': 'd7ddda0e78',
  89             'ext': 'mp4',
  90             'title': 'Chicken',
  91             'filesize': 528031,
  92         },
  93     }
  94
  95     def _extract_title(self, webpage):
  96         data_title = self._search_regex(
  97             r'data-name\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1', webpage,
  98             'title', default=None, group='title')
  99         if data_title:
 100             return unescapeHTML(re.sub(r"\.[a-z0-9]{3,4}$", "", data_title))
 101         return self._og_search_title(webpage)
 102
 103     def _extract_video_url(self, webpage, video_id, *args):
 104         def decode_url(encoded_url):
 105             return compat_b64decode(encoded_url).decode('utf-8')
 106
 107         stream_url = url_or_none(decode_url(self._search_regex(
 108             r'data-stream\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
 109             'stream url', default=None, group='url')))
 110         if stream_url:
 111             return stream_url
 112         return self._parse_json(
 113             self._search_regex(
 114                 r'InitializeStream\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
 115                 webpage, 'stream', group='url'),
 116             video_id, transform_source=decode_url)[0]