From 95b31e266b930dc753b8bf5a1673ced9b50fd519 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 9 Jul 2016 03:28:04 +0700 Subject: [PATCH] [extractor/common] Add expected_type in json ld routines --- youtube_dl/extractor/common.py | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 9ffe64d05..816baa424 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -805,15 +805,17 @@ class InfoExtractor(object): return self._html_search_meta('twitter:player', html, 'twitter card player') - def _search_json_ld(self, html, video_id, **kwargs): + def _search_json_ld(self, html, video_id, expected_type=None, **kwargs): json_ld = self._search_regex( r'(?s)]+type=(["\'])application/ld\+json\1[^>]*>(?P.+?)', html, 'JSON-LD', group='json_ld', **kwargs) if not json_ld: return {} - return self._json_ld(json_ld, video_id, fatal=kwargs.get('fatal', True)) + return self._json_ld( + json_ld, video_id, fatal=kwargs.get('fatal', True), + expected_type=expected_type) - def _json_ld(self, json_ld, video_id, fatal=True): + def _json_ld(self, json_ld, video_id, fatal=True, expected_type=None): if isinstance(json_ld, compat_str): json_ld = self._parse_json(json_ld, video_id, fatal=fatal) if not json_ld: @@ -821,6 +823,8 @@ class InfoExtractor(object): info = {} if json_ld.get('@context') == 'http://schema.org': item_type = json_ld.get('@type') + if expected_type is not None and expected_type != item_type: + return info if item_type == 'TVEpisode': info.update({ 'episode': unescapeHTML(json_ld.get('name')),