From 31a1214076ff41efbaa7f7243565da830d1e2c7e Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 25 Mar 2017 07:03:13 +0100 Subject: [PATCH] [franceculture] fix extraction(closes #12547) --- youtube_dl/extractor/franceculture.py | 31 ++++++++++++++++----------- 1 file changed, 19 insertions(+), 12 deletions(-) diff --git a/youtube_dl/extractor/franceculture.py b/youtube_dl/extractor/franceculture.py index b98da692c..df3d757f3 100644 --- a/youtube_dl/extractor/franceculture.py +++ b/youtube_dl/extractor/franceculture.py @@ -4,6 +4,8 @@ from .common import InfoExtractor from ..utils import ( determine_ext, + extract_attributes, + int_or_none, unified_strdate, ) @@ -19,6 +21,7 @@ class FranceCultureIE(InfoExtractor): 'title': 'Rendez-vous au pays des geeks', 'thumbnail': r're:^https?://.*\.jpg$', 'upload_date': '20140301', + 'timestamp': 1393642916, 'vcodec': 'none', } } @@ -28,30 +31,34 @@ def _real_extract(self, url): webpage = self._download_webpage(url, display_id) - video_url = self._search_regex( - r'(?s)]+class="[^"]*?title-zone-diffusion[^"]*?"[^>]*>.*?]+data-asset-source="([^"]+)"', - webpage, 'video path') + video_data = extract_attributes(self._search_regex( + r'(?s)]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>.*?(]+data-asset-source="[^"]+"[^>]+>)', + webpage, 'video data')) - title = self._og_search_title(webpage) + video_url = video_data['data-asset-source'] + title = video_data.get('data-asset-title') or self._og_search_title(webpage) - upload_date = unified_strdate(self._search_regex( - '(?s)]+class="date"[^>]*>.*?]+class="inner"[^>]*>([^<]+)<', - webpage, 'upload date', fatal=False)) + description = self._html_search_regex( + r'(?s)]+class="intro"[^>]*>.*?

(.+?)

', + webpage, 'description', default=None) thumbnail = self._search_regex( - r'(?s)]+itemtype="https://schema.org/ImageObject"[^>]*>.*?]+data-dejavu-src="([^"]+)"', + r'(?s)]+itemtype="https://schema.org/ImageObject"[^>]*>.*?]+(?:data-dejavu-)?src="([^"]+)"', webpage, 'thumbnail', fatal=False) uploader = self._html_search_regex( - r'(?s)
(.*?)', + r'(?s)(.*?)', webpage, 'uploader', default=None) - vcodec = 'none' if determine_ext(video_url.lower()) == 'mp3' else None + ext = determine_ext(video_url.lower()) return { 'id': display_id, 'display_id': display_id, 'url': video_url, 'title': title, + 'description': description, 'thumbnail': thumbnail, - 'vcodec': vcodec, + 'ext': ext, + 'vcodec': 'none' if ext == 'mp3' else None, 'uploader': uploader, - 'upload_date': upload_date, + 'timestamp': int_or_none(video_data.get('data-asset-created-date')), + 'duration': int_or_none(video_data.get('data-duration')), }