X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/99a6f8745584b59fe0fa1f5e81f6c3667bd3fb2b..712213a489c35dbaf5120268f1a309dc457cea29:/youtube_dl/extractor/shared.py diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index b2250af..ff575f5 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -3,8 +3,12 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..compat import compat_b64decode from ..utils import ( + determine_ext, ExtractorError, int_or_none, + KNOWN_EXTENSIONS, + parse_filesize, + url_or_none, urlencode_postdata, ) @@ -21,10 +25,8 @@ class SharedBaseIE(InfoExtractor): video_url = self._extract_video_url(webpage, video_id, url) - title = compat_b64decode(self._html_search_meta( - 'full:title', webpage, 'title')).decode('utf-8') - filesize = int_or_none(self._html_search_meta( - 'full:size', webpage, 'file size', fatal=False)) + title = self._extract_title(webpage) + filesize = int_or_none(self._extract_filesize(webpage)) return { 'id': video_id, @@ -34,6 +36,14 @@ class SharedBaseIE(InfoExtractor): 'title': title, } + def _extract_title(self, webpage): + return compat_b64decode(self._html_search_meta( + 'full:title', webpage, 'title')).decode('utf-8') + + def _extract_filesize(self, webpage): + return self._html_search_meta( + 'full:size', webpage, 'file size', fatal=False) + class SharedIE(SharedBaseIE): IE_DESC = 'shared.sx' @@ -81,14 +91,37 @@ class VivoIE(SharedBaseIE): 'id': 'd7ddda0e78', 'ext': 'mp4', 'title': 'Chicken', - 'filesize': 528031, + 'filesize': 515659, }, } - def _extract_video_url(self, webpage, video_id, *args): + def _extract_title(self, webpage): + title = self._html_search_regex( + r'data-name\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, + 'title', default=None, group='title') + if title: + ext = determine_ext(title) + if ext.lower() in KNOWN_EXTENSIONS: + title = title.rpartition('.' + ext)[0] + return title + return self._og_search_title(webpage) + + def _extract_filesize(self, webpage): + return parse_filesize(self._search_regex( + r'data-type=["\']video["\'][^>]*>Watch.*?<strong>\s*\((.+?)\)', + webpage, 'filesize', fatal=False)) + + def _extract_video_url(self, webpage, video_id, url): + def decode_url(encoded_url): + return compat_b64decode(encoded_url).decode('utf-8') + + stream_url = url_or_none(decode_url(self._search_regex( + r'data-stream\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, + 'stream url', default=None, group='url'))) + if stream_url: + return stream_url return self._parse_json( self._search_regex( r'InitializeStream\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'stream', group='url'), - video_id, - transform_source=lambda x: compat_b64decode(x).decode('utf-8'))[0] + video_id, transform_source=decode_url)[0]