X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ffranceinter.py;h=05806895c0a3300dd9db8e68efb15fcb70bb8006;hb=HEAD;hp=6613ee17acee4a3fade5470d17196864f4ccae29;hpb=cf372f0778e82cdc181a6173909589e640ac29fb;p=youtube-dl diff --git a/youtube_dl/extractor/franceinter.py b/youtube_dl/extractor/franceinter.py index 6613ee17a..05806895c 100644 --- a/youtube_dl/extractor/franceinter.py +++ b/youtube_dl/extractor/franceinter.py @@ -1,50 +1,54 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import month_by_name class FranceInterIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P[0-9]+)' + _VALID_URL = r'https?://(?:www\.)?franceinter\.fr/emissions/(?P[^?#]+)' + _TEST = { - 'url': 'http://www.franceinter.fr/player/reecouter?play=793962', - 'md5': '4764932e466e6f6c79c317d2e74f6884', - "info_dict": { - 'id': '793962', + 'url': 'https://www.franceinter.fr/emissions/affaires-sensibles/affaires-sensibles-07-septembre-2016', + 'md5': '9e54d7bdb6fdc02a841007f8a975c094', + 'info_dict': { + 'id': 'affaires-sensibles/affaires-sensibles-07-septembre-2016', 'ext': 'mp3', - 'title': 'L’Histoire dans les jeux vidéo', - 'description': 'md5:7e93ddb4451e7530022792240a3049c7', - 'timestamp': 1387369800, - 'upload_date': '20131218', + 'title': 'Affaire Cahuzac : le contentieux du compte en Suisse', + 'description': 'md5:401969c5d318c061f86bda1fa359292b', + 'upload_date': '20160907', }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - path = self._search_regex( - r'(.+?)', webpage, 'title') - description = self._html_search_regex( - r'(.*?)', - webpage, 'description', fatal=False) - timestamp = int_or_none(self._search_regex( - r'data-date="(\d+)"', webpage, 'upload date', fatal=False)) + video_url = self._search_regex( + r'(?s)]+class=["\']page-diffusion["\'][^>]*>.*?]+data-url=(["\'])(?P(?:(?!\1).)+)\1', + webpage, 'video url', group='url') + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + + upload_date_str = self._search_regex( + r'class=["\']\s*cover-emission-period\s*["\'][^>]*>[^<]+\s+(\d{1,2}\s+[^\s]+\s+\d{4})<', + webpage, 'upload date', fatal=False) + if upload_date_str: + upload_date_list = upload_date_str.split() + upload_date_list.reverse() + upload_date_list[1] = '%02d' % (month_by_name(upload_date_list[1], lang='fr') or 0) + upload_date_list[2] = '%02d' % int(upload_date_list[2]) + upload_date = ''.join(upload_date_list) + else: + upload_date = None return { 'id': video_id, 'title': title, 'description': description, - 'timestamp': timestamp, + 'upload_date': upload_date, 'formats': [{ 'url': video_url, 'vcodec': 'none',