From 9a054fcbbadf06101b081f8be0594b38b654364f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 19 Mar 2018 23:28:37 +0700 Subject: [PATCH] [ceskatelevize] Add support for iframe embeds (closes #15918) --- youtube_dl/extractor/ceskatelevize.py | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index e250de18c..6bad90859 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -13,6 +13,7 @@ from ..utils import ( float_or_none, sanitized_Request, unescapeHTML, + update_url_query, urlencode_postdata, USER_AGENTS, ) @@ -265,6 +266,10 @@ class CeskaTelevizePoradyIE(InfoExtractor): # m3u8 download 'skip_download': True, }, + }, { + # iframe embed + 'url': 'http://www.ceskatelevize.cz/porady/10614999031-neviditelni/21251212048/', + 'only_matching': True, }] def _real_extract(self, url): @@ -272,8 +277,11 @@ class CeskaTelevizePoradyIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - data_url = unescapeHTML(self._search_regex( - r']*\bdata-url=(["\'])(?P(?:(?!\1).)+)\1', - webpage, 'iframe player url', group='url')) + data_url = update_url_query(unescapeHTML(self._search_regex( + (r']*\bdata-url=(["\'])(?P(?:(?!\1).)+)\1', + r']+\bsrc=(["\'])(?P(?:https?:)?//(?:www\.)?ceskatelevize\.cz/ivysilani/embed/iFramePlayer\.php.*?)\1'), + webpage, 'iframe player url', group='url')), query={ + 'autoStart': 'true', + }) return self.url_result(data_url, ie=CeskaTelevizeIE.ie_key())