From ecf17d165317078d0e31191e40903a74fc3da3e8 Mon Sep 17 00:00:00 2001 From: flatgreen Date: Sun, 27 Dec 2015 15:30:45 +0100 Subject: [PATCH] [franceculture] Add extractor for '/emission-*' urls (closes #3777, closes #8022) --- youtube_dl/extractor/__init__.py | 5 +++- youtube_dl/extractor/franceculture.py | 40 +++++++++++++++++++++++++-- 2 files changed, 42 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 971047ad4..68c9c1288 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -203,7 +203,10 @@ from .foxgay import FoxgayIE from .foxnews import FoxNewsIE from .foxsports import FoxSportsIE -from .franceculture import FranceCultureIE +from .franceculture import ( + FranceCultureIE, + FranceCultureEmissionIE, +) from .franceinter import FranceInterIE from .francetv import ( PluzzIE, diff --git a/youtube_dl/extractor/franceculture.py b/youtube_dl/extractor/franceculture.py index 2ac6157cd..e2ca96283 100644 --- a/youtube_dl/extractor/franceculture.py +++ b/youtube_dl/extractor/franceculture.py @@ -8,6 +8,7 @@ from ..utils import ( determine_ext, int_or_none, + ExtractorError, ) @@ -28,8 +29,7 @@ class FranceCultureIE(InfoExtractor): } } - def _real_extract(self, url): - video_id = self._match_id(url) + def _extract_from_player(self, url, video_id): webpage = self._download_webpage(url, video_id) video_path = self._search_regex( @@ -42,6 +42,9 @@ def _real_extract(self, url): r'\s+emission-(.*?)', webpage, 'display_id') + title = self._html_search_regex( r'(.*?)', webpage, 'title') alt_title = self._html_search_regex( @@ -66,4 +69,37 @@ def _real_extract(self, url): 'alt_title': alt_title, 'thumbnail': thumbnail, 'description': description, + 'display_id': display_id, } + + def _real_extract(self, url): + video_id = self._match_id(url) + return self._extract_from_player(url, video_id) + + +class FranceCultureEmissionIE(FranceCultureIE): + _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emission-(?P[^?#]+)' + _TEST = { + 'url': 'http://www.franceculture.fr/emission-les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13', + 'info_dict': { + 'title': 'Jean-Gabriel Périot, cinéaste', + 'alt_title': 'Les Carnets de la création', + 'id': '5093239', + 'display_id': 'les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13', + 'ext': 'mp3', + 'timestamp': 1444762500, + 'upload_date': '20151013', + 'description': 'startswith:Aujourd\'hui dans "Les carnets de la création", le cinéaste', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + video_path = self._html_search_regex( + r'[0-9]+)', video_path, 'new_id', group='id') + video_url = compat_urlparse.urljoin(url, video_path) + return self._extract_from_player(video_url, new_id)