From 44369c9afa996e14e9f466754481d878811b5b4a Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Thu, 23 Mar 2023 11:18:42 -0500 Subject: [PATCH] [extractor/cbs] Add `ParamountPressExpress` extractor (#6604) Closes #6597 Authored by: bashonly --- yt_dlp/extractor/_extractors.py | 5 +- yt_dlp/extractor/brightcove.py | 6 +- yt_dlp/extractor/cbs.py | 113 ++++++++++++++++++++++++++++++++ 3 files changed, 121 insertions(+), 3 deletions(-) diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 01281b5a15..6c948e5fce 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -298,7 +298,10 @@ CBCGemPlaylistIE, CBCGemLiveIE, ) -from .cbs import CBSIE +from .cbs import ( + CBSIE, + ParamountPressExpressIE, +) from .cbslocal import ( CBSLocalIE, CBSLocalArticleIE, diff --git a/yt_dlp/extractor/brightcove.py b/yt_dlp/extractor/brightcove.py index 2b7ddcae8d..cd0e8ff275 100644 --- a/yt_dlp/extractor/brightcove.py +++ b/yt_dlp/extractor/brightcove.py @@ -575,6 +575,7 @@ def build_format_id(kind): self.raise_no_formats( error.get('message') or error.get('error_subcode') or error['error_code'], expected=True) + headers.pop('Authorization', None) # or else http formats will give error 400 for f in formats: f.setdefault('http_headers', {}).update(headers) @@ -895,8 +896,9 @@ def extract_policy_key(): store_pk(policy_key) return policy_key - api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/%ss/%s' % (account_id, content_type, video_id) - headers = {} + token = smuggled_data.get('token') + api_url = f'https://{"edge-auth" if token else "edge"}.api.brightcove.com/playback/v1/accounts/{account_id}/{content_type}s/{video_id}' + headers = {'Authorization': f'Bearer {token}'} if token else {} referrer = smuggled_data.get('referrer') # XXX: notice the spelling/case of the key if referrer: headers.update({ diff --git a/yt_dlp/extractor/cbs.py b/yt_dlp/extractor/cbs.py index 9aacd50c45..1c0dbdea94 100644 --- a/yt_dlp/extractor/cbs.py +++ b/yt_dlp/extractor/cbs.py @@ -1,8 +1,14 @@ +from .brightcove import BrightcoveNewIE +from .common import InfoExtractor from .theplatform import ThePlatformFeedIE +from .youtube import YoutubeIE from ..utils import ( ExtractorError, + extract_attributes, + get_element_html_by_id, int_or_none, find_xpath_attr, + smuggle_url, xpath_element, xpath_text, update_url_query, @@ -162,3 +168,110 @@ def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517): 'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000), 'thumbnail': url_or_none(xpath_text(video_data, 'previewImageURL')), }) + + +class ParamountPressExpressIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?paramountpressexpress\.com(?:/[\w-]+)+/(?Pyt-)?video/?\?watch=(?P[\w-]+)' + _TESTS = [{ + 'url': 'https://www.paramountpressexpress.com/cbs-entertainment/shows/survivor/video/?watch=pnzew7e2hx', + 'md5': '56631dbcadaab980d1fc47cb7b76cba4', + 'info_dict': { + 'id': '6322981580112', + 'ext': 'mp4', + 'title': 'I’m Felicia', + 'description': 'md5:88fad93f8eede1c9c8f390239e4c6290', + 'uploader_id': '6055873637001', + 'upload_date': '20230320', + 'timestamp': 1679334960, + 'duration': 49.557, + 'thumbnail': r're:^https://.+\.jpg', + 'tags': [], + }, + }, { + 'url': 'https://www.paramountpressexpress.com/cbs-entertainment/video/?watch=2s5eh8kppc', + 'md5': 'edcb03e3210b88a3e56c05aa863e0e5b', + 'info_dict': { + 'id': '6323036027112', + 'ext': 'mp4', + 'title': '‘Y&R’ Set Visit: Jerry O’Connell Quizzes Cast on Pre-Love Scene Rituals and More', + 'description': 'md5:b929867a357aac5544b783d834c78383', + 'uploader_id': '6055873637001', + 'upload_date': '20230321', + 'timestamp': 1679430180, + 'duration': 132.032, + 'thumbnail': r're:^https://.+\.jpg', + 'tags': [], + }, + }, { + 'url': 'https://www.paramountpressexpress.com/paramount-plus/yt-video/?watch=OX9wJWOcqck', + 'info_dict': { + 'id': 'OX9wJWOcqck', + 'ext': 'mp4', + 'title': 'Rugrats | Season 2 Official Trailer | Paramount+', + 'description': 'md5:1f7e26f5625a9f0d6564d9ad97a9f7de', + 'uploader': 'Paramount Plus', + 'uploader_id': '@paramountplus', + 'uploader_url': 'http://www.youtube.com/@paramountplus', + 'channel': 'Paramount Plus', + 'channel_id': 'UCrRttZIypNTA1Mrfwo745Sg', + 'channel_url': 'https://www.youtube.com/channel/UCrRttZIypNTA1Mrfwo745Sg', + 'upload_date': '20230316', + 'duration': 88, + 'age_limit': 0, + 'availability': 'public', + 'live_status': 'not_live', + 'playable_in_embed': True, + 'view_count': int, + 'like_count': int, + 'channel_follower_count': int, + 'thumbnail': 'https://i.ytimg.com/vi/OX9wJWOcqck/maxresdefault.jpg', + 'categories': ['Entertainment'], + 'tags': ['Rugrats'], + }, + }, { + 'url': 'https://www.paramountpressexpress.com/showtime/yt-video/?watch=_ljssSoDLkw', + 'info_dict': { + 'id': '_ljssSoDLkw', + 'ext': 'mp4', + 'title': 'Lavell Crawford: THEE Lavell Crawford Comedy Special Official Trailer | SHOWTIME', + 'description': 'md5:39581bcc3fd810209b642609f448af70', + 'uploader': 'SHOWTIME', + 'uploader_id': '@Showtime', + 'uploader_url': 'http://www.youtube.com/@Showtime', + 'channel': 'SHOWTIME', + 'channel_id': 'UCtwMWJr2BFPkuJTnSvCESSQ', + 'channel_url': 'https://www.youtube.com/channel/UCtwMWJr2BFPkuJTnSvCESSQ', + 'upload_date': '20230209', + 'duration': 49, + 'age_limit': 0, + 'availability': 'public', + 'live_status': 'not_live', + 'playable_in_embed': True, + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'channel_follower_count': int, + 'thumbnail': 'https://i.ytimg.com/vi_webp/_ljssSoDLkw/maxresdefault.webp', + 'categories': ['People & Blogs'], + 'tags': 'count:27', + }, + }] + + def _real_extract(self, url): + display_id, is_youtube = self._match_valid_url(url).group('id', 'yt') + if is_youtube: + return self.url_result(display_id, YoutubeIE) + + webpage = self._download_webpage(url, display_id) + video_id = self._search_regex( + r'\bvideo_id\s*=\s*["\'](\d+)["\']\s*,', webpage, 'Brightcove ID') + token = self._search_regex(r'\btoken\s*=\s*["\']([\w.-]+)["\']', webpage, 'token') + + player = extract_attributes(get_element_html_by_id('vcbrightcoveplayer', webpage) or '') + account_id = player.get('data-account') or '6055873637001' + player_id = player.get('data-player') or 'OtLKgXlO9F' + embed = player.get('data-embed') or 'default' + + return self.url_result(smuggle_url( + f'https://players.brightcove.net/{account_id}/{player_id}_{embed}/index.html?videoId={video_id}', + {'token': token}), BrightcoveNewIE)