yt_dlp/extractor/vshare.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_chr
   5 from ..utils import (
   6     decode_packed_codes,
   7     ExtractorError,
   8 )
   9
  10
  11 class VShareIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?vshare\.io/[dv]/(?P<id>[^/?#&]+)'
  13     _TESTS = [{
  14         'url': 'https://vshare.io/d/0f64ce6',
  15         'md5': '17b39f55b5497ae8b59f5fbce8e35886',
  16         'info_dict': {
  17             'id': '0f64ce6',
  18             'title': 'vl14062007715967',
  19             'ext': 'mp4',
  20         }
  21     }, {
  22         'url': 'https://vshare.io/v/0f64ce6/width-650/height-430/1',
  23         'only_matching': True,
  24     }]
  25
  26     @staticmethod
  27     def _extract_urls(webpage):
  28         return re.findall(
  29             r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?vshare\.io/v/[^/?#&]+)',
  30             webpage)
  31
  32     def _extract_packed(self, webpage):
  33         packed = self._search_regex(
  34             r'(eval\(function.+)', webpage, 'packed code')
  35         unpacked = decode_packed_codes(packed)
  36         digits = self._search_regex(r'\[((?:\d+,?)+)\]', unpacked, 'digits')
  37         digits = [int(digit) for digit in digits.split(',')]
  38         key_digit = self._search_regex(
  39             r'fromCharCode\(.+?(\d+)\)}', unpacked, 'key digit')
  40         chars = [compat_chr(d - int(key_digit)) for d in digits]
  41         return ''.join(chars)
  42
  43     def _real_extract(self, url):
  44         video_id = self._match_id(url)
  45
  46         webpage = self._download_webpage(
  47             'https://vshare.io/v/%s/width-650/height-430/1' % video_id,
  48             video_id, headers={'Referer': url})
  49
  50         title = self._html_extract_title(webpage)
  51         title = title.split(' - ')[0]
  52
  53         error = self._html_search_regex(
  54             r'(?s)<div[^>]+\bclass=["\']xxx-error[^>]+>(.+?)</div', webpage,
  55             'error', default=None)
  56         if error:
  57             raise ExtractorError(error, expected=True)
  58
  59         info = self._parse_html5_media_entries(
  60             url, '<video>%s</video>' % self._extract_packed(webpage),
  61             video_id)[0]
  62
  63         self._sort_formats(info['formats'])
  64
  65         info.update({
  66             'id': video_id,
  67             'title': title,
  68         })
  69
  70         return info