X-Git-Url: https://jfr.im/git/yt-dlp.git/blobdiff_plain/7a5c1cfe93924351387b44919b3c0b2f66c4b883..61edf57f8f13f6dfd81154174e647eb5fdd26089:/yt_dlp/extractor/wat.py diff --git a/yt_dlp/extractor/wat.py b/yt_dlp/extractor/wat.py index f6940b371..03bac66ac 100644 --- a/yt_dlp/extractor/wat.py +++ b/yt_dlp/extractor/wat.py @@ -1,12 +1,9 @@ -# coding: utf-8 -from __future__ import unicode_literals - from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( - unified_strdate, - HEADRequest, + ExtractorError, int_or_none, + try_get, + unified_strdate, ) @@ -29,6 +26,7 @@ class WatIE(InfoExtractor): 'skip_download': True, }, 'expected_warnings': ['HTTP Error 404'], + 'skip': 'This content is no longer available', }, { 'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html', @@ -40,80 +38,81 @@ class WatIE(InfoExtractor): 'upload_date': '20140816', }, 'expected_warnings': ["Ce contenu n'est pas disponible pour l'instant."], + 'skip': 'This content is no longer available', + }, + { + 'url': 'wat:14010600', + 'info_dict': { + 'id': '14010600', + 'title': 'Burger Quiz - S03 EP21 avec Eye Haidara, Anne Depétrini, Jonathan Zaccaï et Pio Marmaï', + 'thumbnail': 'https://photos.tf1.fr/1280/720/burger-quiz-11-9adb79-0@1x.jpg', + 'upload_date': '20230819', + 'duration': 2312, + 'ext': 'mp4', + }, + 'params': {'skip_download': 'm3u8'}, }, ] + _GEO_BYPASS = False def _real_extract(self, url): video_id = self._match_id(url) - video_id = video_id if video_id.isdigit() and len(video_id) > 6 else compat_str(int(video_id, 36)) + video_id = video_id if video_id.isdigit() and len(video_id) > 6 else str(int(video_id, 36)) # 'contentv4' is used in the website, but it also returns the related # videos, we don't need them + # video_data = self._download_json( + # 'http://www.wat.tv/interface/contentv4s/' + video_id, video_id) video_data = self._download_json( - 'http://www.wat.tv/interface/contentv4s/' + video_id, video_id) + 'https://mediainfo.tf1.fr/mediainfocombo/' + video_id, + video_id, query={'pver': '5010000'}) video_info = video_data['media'] error_desc = video_info.get('error_desc') if error_desc: - self.report_warning( - '%s returned error: %s' % (self.IE_NAME, error_desc)) - - chapters = video_info['chapters'] - if chapters: - first_chapter = chapters[0] - - def video_id_for_chapter(chapter): - return chapter['tc_start'].split('-')[0] + if video_info.get('error_code') == 'GEOBLOCKED': + self.raise_geo_restricted(error_desc, video_info.get('geoList')) + raise ExtractorError(error_desc, expected=True) - if video_id_for_chapter(first_chapter) != video_id: - self.to_screen('Multipart video detected') - entries = [self.url_result('wat:%s' % video_id_for_chapter(chapter)) for chapter in chapters] - return self.playlist_result(entries, video_id, video_info['title']) - # Otherwise we can continue and extract just one part, we have to use - # the video id for getting the video url - else: - first_chapter = video_info - - title = first_chapter['title'] - - def extract_url(path_template, url_type): - req_url = 'http://www.wat.tv/get/%s' % (path_template % video_id) - head = self._request_webpage(HEADRequest(req_url), video_id, 'Extracting %s url' % url_type, fatal=False) - if head: - red_url = head.geturl() - if req_url != red_url: - return red_url - return None + title = video_info['title'] formats = [] - manifest_urls = self._download_json( - 'http://www.wat.tv/get/webhtml/' + video_id, video_id) - m3u8_url = manifest_urls.get('hls') - if m3u8_url: - formats.extend(self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', - 'm3u8_native', m3u8_id='hls', fatal=False)) - mpd_url = manifest_urls.get('mpd') - if mpd_url: - formats.extend(self._extract_mpd_formats( - mpd_url.replace('://das-q1.tf1.fr/', '://das-q1-ssl.tf1.fr/'), - video_id, mpd_id='dash', fatal=False)) - self._sort_formats(formats) + subtitles = {} + + def extract_formats(manifest_urls): + for f, f_url in manifest_urls.items(): + if not f_url: + continue + if f in ('dash', 'mpd'): + fmts, subs = self._extract_mpd_formats_and_subtitles( + f_url.replace('://das-q1.tf1.fr/', '://das-q1-ssl.tf1.fr/'), + video_id, mpd_id='dash', fatal=False) + elif f == 'hls': + fmts, subs = self._extract_m3u8_formats_and_subtitles( + f_url, video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False) + else: + continue + formats.extend(fmts) + self._merge_subtitles(subs, target=subtitles) - date_diffusion = first_chapter.get('date_diffusion') or video_data.get('configv4', {}).get('estatS4') - upload_date = unified_strdate(date_diffusion) if date_diffusion else None - duration = None - files = video_info['files'] - if files: - duration = int_or_none(files[0].get('duration')) + delivery = video_data.get('delivery') or {} + extract_formats({delivery.get('format'): delivery.get('url')}) + if not formats: + if delivery.get('drm'): + self.report_drm(video_id) + manifest_urls = self._download_json( + 'http://www.wat.tv/get/webhtml/' + video_id, video_id, fatal=False) + if manifest_urls: + extract_formats(manifest_urls) return { 'id': video_id, 'title': title, - 'thumbnail': first_chapter.get('preview'), - 'description': first_chapter.get('description'), - 'view_count': int_or_none(video_info.get('views')), - 'upload_date': upload_date, - 'duration': duration, + 'thumbnail': video_info.get('preview'), + 'upload_date': unified_strdate(try_get( + video_data, lambda x: x['mediametrie']['chapters'][0]['estatS4'])), + 'duration': int_or_none(video_info.get('duration')), 'formats': formats, + 'subtitles': subtitles, }