From 393ca8c94d1adb1490b23265370ce69043b92546 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 20 Sep 2015 11:45:19 +0600 Subject: [PATCH] [arte:+7] Look for json vp url in iframe (Closes #6895) --- youtube_dl/extractor/arte.py | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 76de24477..9ecb6786c 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -4,6 +4,10 @@ import re from .common import InfoExtractor +from ..compat import ( + compat_parse_qs, + compat_urllib_parse_urlparse, +) from ..utils import ( find_xpath_attr, unified_strdate, @@ -77,7 +81,13 @@ def _real_extract(self, url): def _extract_from_webpage(self, webpage, video_id, lang): json_url = self._html_search_regex( [r'arte_vp_url=["\'](.*?)["\']', r'data-url=["\']([^"]+)["\']'], - webpage, 'json vp url') + webpage, 'json vp url', default=None) + if not json_url: + iframe_url = self._html_search_regex( + r']+src=(["\'])(?P.+\bjson_url=.+?)\1', + webpage, 'iframe url', group='iframe url') + json_url = compat_parse_qs( + compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0] return self._extract_from_json_url(json_url, video_id, lang) def _extract_from_json_url(self, json_url, video_id, lang):