X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9dc487f48b50767cf540fa36c3de2c386fd74c04..99b46abf79266c2bf5eabc291dc4f366e61b5dde:/youtube_dl/extractor/shared.py diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index e7e5f65..d592dfe 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -6,7 +6,6 @@ from .common import InfoExtractor from ..utils import ( ExtractorError, int_or_none, - sanitized_Request, urlencode_postdata, ) @@ -37,28 +36,33 @@ class SharedIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + + webpage, urlh = self._download_webpage_handle(url, video_id) if '>File does not exist<' in webpage: raise ExtractorError( 'Video %s does not exist' % video_id, expected=True) download_form = self._hidden_inputs(webpage) - request = sanitized_Request( - url, urlencode_postdata(download_form)) - request.add_header('Content-Type', 'application/x-www-form-urlencoded') video_page = self._download_webpage( - request, video_id, 'Downloading video page') + urlh.geturl(), video_id, 'Downloading video page', + data=urlencode_postdata(download_form), + headers={ + 'Content-Type': 'application/x-www-form-urlencoded', + 'Referer': urlh.geturl(), + }) video_url = self._html_search_regex( - r'data-url="([^"]+)"', video_page, 'video URL') + r'data-url=(["\'])(?P(?:(?!\1).)+)\1', + video_page, 'video URL', group='url') title = base64.b64decode(self._html_search_meta( 'full:title', webpage, 'title').encode('utf-8')).decode('utf-8') filesize = int_or_none(self._html_search_meta( 'full:size', webpage, 'file size', fatal=False)) thumbnail = self._html_search_regex( - r'data-poster="([^"]+)"', video_page, 'thumbnail', default=None) + r'data-poster=(["\'])(?P(?:(?!\1).)+)\1', + video_page, 'thumbnail', default=None, group='url') return { 'id': video_id,