From 91a670a4f7babe9c8aa2018f57d8c8952a6f49d8 Mon Sep 17 00:00:00 2001 From: gillux Date: Sat, 7 Oct 2023 06:27:54 +0800 Subject: [PATCH] [ie/LiTV] Fix extractor (#7785) Closes #5456 Authored by: jiru --- yt_dlp/extractor/litv.py | 48 ++++++++++++++++++++++------------------ 1 file changed, 27 insertions(+), 21 deletions(-) diff --git a/yt_dlp/extractor/litv.py b/yt_dlp/extractor/litv.py index 19b298ec6c..2c7c7175ea 100644 --- a/yt_dlp/extractor/litv.py +++ b/yt_dlp/extractor/litv.py @@ -13,7 +13,7 @@ class LiTVIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?litv\.tv/(?:vod|promo)/[^/]+/(?:content\.do)?\?.*?\b(?:content_)?id=(?P[^&]+)' - _URL_TEMPLATE = 'https://www.litv.tv/vod/%s/content.do?id=%s' + _URL_TEMPLATE = 'https://www.litv.tv/vod/%s/content.do?content_id=%s' _TESTS = [{ 'url': 'https://www.litv.tv/vod/drama/content.do?brc_id=root&id=VOD00041610&isUHEnabled=true&autoPlay=1', @@ -21,16 +21,18 @@ class LiTVIE(InfoExtractor): 'id': 'VOD00041606', 'title': '花千骨', }, - 'playlist_count': 50, + 'playlist_count': 51, # 50 episodes + 1 trailer }, { 'url': 'https://www.litv.tv/vod/drama/content.do?brc_id=root&id=VOD00041610&isUHEnabled=true&autoPlay=1', - 'md5': '969e343d9244778cb29acec608e53640', + 'md5': 'b90ff1e9f1d8f5cfcd0a44c3e2b34c7a', 'info_dict': { 'id': 'VOD00041610', 'ext': 'mp4', 'title': '花千骨第1集', 'thumbnail': r're:https?://.*\.jpg$', - 'description': 'md5:c7017aa144c87467c4fb2909c4b05d6f', + 'description': '《花千骨》陸劇線上看。十六年前，平靜的村莊內，一名女嬰隨異相出生，途徑此地的蜀山掌門清虛道長算出此女命運非同一般，她體內散發的異香易招惹妖魔。一念慈悲下，他在村莊周邊設下結界阻擋妖魔入侵，讓其年滿十六後去蜀山，並賜名花千骨。', + 'categories': ['奇幻', '愛情', '中國', '仙俠'], + 'episode': 'Episode 1', 'episode_number': 1, }, 'params': { @@ -46,20 +48,17 @@ class LiTVIE(InfoExtractor): 'title': '芈月傳第1集　霸星芈月降世楚國', 'description': '楚威王二年，太史令唐昧夜觀星象，發現霸星即將現世。王后得知霸星的預言後，想盡辦法不讓孩子順利出生，幸得莒姬相護化解危機。沒想到眾人期待下出生的霸星卻是位公主，楚威王對此失望至極。楚王后命人將女嬰丟棄河中，居然奇蹟似的被少司命像攔下，楚威王認為此女非同凡響，為她取名芈月。', }, - 'skip': 'Georestricted to Taiwan', + 'skip': 'No longer exists', }] - def _extract_playlist(self, season_list, video_id, program_info, prompt=True): - episode_title = program_info['title'] - content_id = season_list['contentId'] - + def _extract_playlist(self, playlist_data, content_type): all_episodes = [ self.url_result(smuggle_url( - self._URL_TEMPLATE % (program_info['contentType'], episode['contentId']), + self._URL_TEMPLATE % (content_type, episode['contentId']), {'force_noplaylist': True})) # To prevent infinite recursion - for episode in season_list['episode']] + for episode in traverse_obj(playlist_data, ('seasons', ..., 'episode', lambda _, v: v['contentId']))] - return self.playlist_result(all_episodes, content_id, episode_title) + return self.playlist_result(all_episodes, playlist_data['contentId'], playlist_data.get('title')) def _real_extract(self, url): url, smuggled_data = unsmuggle_url(url, {}) @@ -68,24 +67,31 @@ def _real_extract(self, url): webpage = self._download_webpage(url, video_id) + if self._search_regex( + r'(?i)]*http-equiv="refresh"\s[^>]*content="[0-9]+;\s*url=https://www\.litv\.tv/"', + webpage, 'meta refresh redirect', default=False, group=0): + raise ExtractorError('No such content found', expected=True) + program_info = self._parse_json(self._search_regex( r'var\s+programInfo\s*=\s*([^;]+)', webpage, 'VOD data', default='{}'), video_id) - season_list = list(program_info.get('seasonList', {}).values()) - playlist_id = traverse_obj(season_list, 0, 'contentId') - if self._yes_playlist(playlist_id, video_id, smuggled_data): - return self._extract_playlist(season_list[0], video_id, program_info) - - # In browsers `getMainUrl` request is always issued. Usually this + # In browsers `getProgramInfo` request is always issued. Usually this # endpoint gives the same result as the data embedded in the webpage. - # If georestricted, there are no embedded data, so an extra request is - # necessary to get the error code + # If, for some reason, there are no embedded data, we do an extra request. if 'assetId' not in program_info: program_info = self._download_json( 'https://www.litv.tv/vod/ajax/getProgramInfo', video_id, query={'contentId': video_id}, headers={'Accept': 'application/json'}) + + series_id = program_info['seriesId'] + if self._yes_playlist(series_id, video_id, smuggled_data): + playlist_data = self._download_json( + 'https://www.litv.tv/vod/ajax/getSeriesTree', video_id, + query={'seriesId': series_id}, headers={'Accept': 'application/json'}) + return self._extract_playlist(playlist_data, program_info['contentType']) + video_data = self._parse_json(self._search_regex( r'uiHlsUrl\s*=\s*testBackendData\(([^;]+)\);', webpage, 'video data', default='{}'), video_id) @@ -96,7 +102,7 @@ def _real_extract(self, url): 'contentType': program_info['contentType'], } video_data = self._download_json( - 'https://www.litv.tv/vod/getMainUrl', video_id, + 'https://www.litv.tv/vod/ajax/getMainUrlNoAuth', video_id, data=json.dumps(payload).encode('utf-8'), headers={'Content-Type': 'application/json'})