From 4b3c5d1b81b1fa1ed580eec8c920cd281da946fc Mon Sep 17 00:00:00 2001 From: BohwaZ Date: Thu, 17 Mar 2022 01:40:27 +0100 Subject: [PATCH] [FranceCulture] Support playlists (#1872) Authored by: bohwaz --- yt_dlp/extractor/franceculture.py | 101 +++++++++++++++++++++++------- 1 file changed, 78 insertions(+), 23 deletions(-) diff --git a/yt_dlp/extractor/franceculture.py b/yt_dlp/extractor/franceculture.py index 14f4cb489..9dc28d801 100644 --- a/yt_dlp/extractor/franceculture.py +++ b/yt_dlp/extractor/franceculture.py @@ -1,18 +1,45 @@ # coding: utf-8 from __future__ import unicode_literals +import re from .common import InfoExtractor from ..utils import ( determine_ext, extract_attributes, int_or_none, + traverse_obj, + unified_strdate, ) class FranceCultureIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emissions/(?:[^/]+/)*(?P[^/?#&]+)' _TESTS = [{ - 'url': 'http://www.franceculture.fr/emissions/carnet-nomade/rendez-vous-au-pays-des-geeks', + # playlist + 'url': 'https://www.franceculture.fr/emissions/serie/hasta-dente', + 'playlist_count': 12, + 'info_dict': { + 'id': 'hasta-dente', + 'title': 'Hasta Dente', + 'description': 'md5:57479af50648d14e9bb649e6b1f8f911', + 'thumbnail': r're:^https?://.*\.jpg$', + 'upload_date': '20201024', + }, + 'playlist': [{ + 'info_dict': { + 'id': '3c1c2e55-41a0-11e5-9fe0-005056a87c89', + 'ext': 'mp3', + 'title': 'Jeudi, vous avez dit bizarre ?', + 'description': 'md5:47cf1e00cc21c86b0210279996a812c6', + 'duration': 604, + 'upload_date': '20201024', + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1603576680 + }, + }, + ], + }, { + 'url': 'https://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', @@ -20,9 +47,9 @@ class FranceCultureIE(InfoExtractor): 'title': 'Rendez-vous au pays des geeks', 'thumbnail': r're:^https?://.*\.jpg$', 'upload_date': '20140301', - 'timestamp': 1393700400, 'vcodec': 'none', - } + 'duration': 3569, + }, }, { # no thumbnail 'url': 'https://www.franceculture.fr/emissions/la-recherche-montre-en-main/la-recherche-montre-en-main-du-mercredi-10-octobre-2018', @@ -31,9 +58,54 @@ class FranceCultureIE(InfoExtractor): def _real_extract(self, url): display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) + info = { + 'id': display_id, + 'title': self._html_search_regex( + r'(?s)]*itemprop="[^"]*name[^"]*"[^>]*>(.+?)', + webpage, 'title', default=self._og_search_title(webpage)), + 'description': self._html_search_regex( + r'(?s)]+class="excerpt"[^>]*>(.*?)', webpage, 'description', default=None), + 'thumbnail': self._og_search_thumbnail(webpage), + 'uploader': self._html_search_regex( + r'(?s)(.*?)', webpage, 'uploader', default=None), + 'upload_date': unified_strdate(self._html_search_regex( + r'(?s)class="teaser-text-date".*?(\d{2}/\d{2}/\d{4})', webpage, 'date', default=None)), + } + + playlist_data = self._search_regex( + r'''(?sx) + ]+data-xiti-place="[^"]*?liste_episodes[^"?]*?"[^>]*> + (.*?) + + ''', + webpage, 'playlist data', fatal=False, default=None) + + if playlist_data: + entries = [] + for item, item_description in re.findall( + r'(?s)(]*>).*?]*class="[^"]*teaser-text-chapo[^>]*>(.*?)

', + playlist_data): + + item_attributes = extract_attributes(item) + entries.append({ + 'id': item_attributes.get('data-emission-uuid'), + 'url': item_attributes.get('data-url'), + 'title': item_attributes.get('data-diffusion-title'), + 'duration': int_or_none(traverse_obj(item_attributes, 'data-duration-seconds', 'data-duration-seconds')), + 'description': item_description, + 'timestamp': int_or_none(item_attributes.get('data-start-time')), + 'thumbnail': info['thumbnail'], + 'uploader': info['uploader'], + }) + + return { + '_type': 'playlist', + 'entries': entries, + **info + } + video_data = extract_attributes(self._search_regex( r'''(?sx) (?: @@ -43,31 +115,14 @@ def _real_extract(self, url): (]+data-(?:url|asset-source)="[^"]+"[^>]+>) ''', webpage, 'video data')) - - video_url = video_data.get('data-url') or video_data['data-asset-source'] - title = video_data.get('data-asset-title') or video_data.get('data-diffusion-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', default=None) - uploader = self._html_search_regex( - r'(?s)(.*?)', - webpage, 'uploader', default=None) + video_url = traverse_obj(video_data, 'data-url', 'data-asset-source') 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-start-time')) or int_or_none(video_data.get('data-asset-created-date')), 'duration': int_or_none(video_data.get('data-duration')), + **info }