# coding: utf-8 from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( determine_ext, extract_attributes, int_or_none, ) class FranceCultureIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emissions/(?:[^/]+/)*(?P[^/?#&]+)' _TEST = { 'url': 'http://www.franceculture.fr/emissions/carnet-nomade/rendez-vous-au-pays-des-geeks', 'info_dict': { 'id': 'rendez-vous-au-pays-des-geeks', 'display_id': 'rendez-vous-au-pays-des-geeks', 'ext': 'mp3', 'title': 'Rendez-vous au pays des geeks', 'thumbnail': r're:^https?://.*\.jpg$', 'upload_date': '20140301', 'timestamp': 1393642916, 'vcodec': 'none', } } def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) video_data = extract_attributes(self._search_regex( r'(?s)]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>.*?(]+data-asset-source="[^"]+"[^>]+>)', webpage, 'video data')) video_url = video_data['data-asset-source'] title = video_data.get('data-asset-title') or self._og_search_title(webpage) 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="([^"]+)"', webpage, 'thumbnail', fatal=False) uploader = self._html_search_regex( r'(?s)(.*?)', webpage, 'uploader', default=None) ext = determine_ext(video_url.lower()) return { 'id': display_id, 'display_id': display_id, 'url': video_url, 'title': title, 'description': description, 'thumbnail': thumbnail, 'ext': ext, 'vcodec': 'none' if ext == 'mp3' else None, 'uploader': uploader, 'timestamp': int_or_none(video_data.get('data-asset-created-date')), 'duration': int_or_none(video_data.get('data-duration')), }