From 80ea6d3dea8483cddd39fc89b5ee1fc06670c33c Mon Sep 17 00:00:00 2001 From: JChris246 <43832407+JChris246@users.noreply.github.com> Date: Sun, 12 Mar 2023 14:02:17 -0400 Subject: [PATCH] [extractor/Parler] Rewrite extractor (#6446) Authored by: JChris246 Closes #6068 --- yt_dlp/extractor/parler.py | 94 +++++++++++++++----------------------- 1 file changed, 37 insertions(+), 57 deletions(-) diff --git a/yt_dlp/extractor/parler.py b/yt_dlp/extractor/parler.py index 68a60bc84..2af805e7f 100644 --- a/yt_dlp/extractor/parler.py +++ b/yt_dlp/extractor/parler.py @@ -1,13 +1,14 @@ +import functools + from .common import InfoExtractor from .youtube import YoutubeIE from ..utils import ( clean_html, - format_field, int_or_none, strip_or_none, traverse_obj, unified_timestamp, - urlencode_postdata, + urljoin, ) @@ -24,7 +25,7 @@ class ParlerIE(InfoExtractor): 'thumbnail': 'https://bl-images.parler.com/videos/6ce7cdf3-a27a-4d72-bf9c-d3e17ce39a66/thumbnail.jpeg', 'title': 'Parler video #df79fdba-07cc-48fe-b085-3293897520d7', 'description': 'md5:6f220bde2df4a97cbb89ac11f1fd8197', - 'timestamp': 1659744000, + 'timestamp': 1659785481, 'upload_date': '20220806', 'uploader': 'Tulsi Gabbard', 'uploader_id': 'TulsiGabbard', @@ -34,78 +35,57 @@ class ParlerIE(InfoExtractor): 'repost_count': int, }, }, - { - 'url': 'https://parler.com/feed/a7406eb4-91e5-4793-b5e3-ade57a24e287', - 'md5': '11687e2f5bb353682cee338d181422ed', - 'info_dict': { - 'id': 'a7406eb4-91e5-4793-b5e3-ade57a24e287', - 'ext': 'mp4', - 'thumbnail': 'https://bl-images.parler.com/videos/317827a8-1e48-4cbc-981f-7dd17d4c1183/thumbnail.jpeg', - 'title': 'Parler video #a7406eb4-91e5-4793-b5e3-ade57a24e287', - 'description': 'This man should run for office', - 'timestamp': 1659657600, - 'upload_date': '20220805', - 'uploader': 'Benny Johnson', - 'uploader_id': 'BennyJohnson', - 'uploader_url': 'https://parler.com/BennyJohnson', - 'view_count': int, - 'comment_count': int, - 'repost_count': int, - }, - }, { 'url': 'https://parler.com/feed/f23b85c1-6558-470f-b9ff-02c145f28da5', 'md5': 'eaba1ff4a10fe281f5ce74e930ab2cb4', 'info_dict': { 'id': 'r5vkSaz8PxQ', 'ext': 'mp4', - 'thumbnail': 'https://i.ytimg.com/vi_webp/r5vkSaz8PxQ/maxresdefault.webp', - 'title': 'Tom MacDonald Names Reaction', - 'description': 'md5:33c21f0d35ae6dc2edf3007d6696baea', - 'upload_date': '20220716', - 'duration': 1267, - 'uploader': 'Mahesh Chookolingo', - 'uploader_id': 'maheshchookolingo', - 'uploader_url': 'http://www.youtube.com/user/maheshchookolingo', - 'channel': 'Mahesh Chookolingo', - 'channel_id': 'UCox6YeMSY1PQInbCtTaZj_w', - 'channel_url': 'https://www.youtube.com/channel/UCox6YeMSY1PQInbCtTaZj_w', - 'categories': ['Entertainment'], - 'tags': list, - 'availability': 'public', 'live_status': 'not_live', - 'view_count': int, 'comment_count': int, + 'duration': 1267, 'like_count': int, 'channel_follower_count': int, - 'age_limit': 0, + 'channel_id': 'UCox6YeMSY1PQInbCtTaZj_w', + 'upload_date': '20220716', + 'thumbnail': 'https://i.ytimg.com/vi/r5vkSaz8PxQ/maxresdefault.jpg', + 'tags': 'count:17', + 'availability': 'public', + 'categories': ['Entertainment'], 'playable_in_embed': True, + 'channel': 'Who Knows What! With Mahesh & Friends', + 'title': 'Tom MacDonald Names Reaction', + 'uploader': 'Who Knows What! With Mahesh & Friends', + 'uploader_id': '@maheshchookolingo', + 'age_limit': 0, + 'description': 'md5:33c21f0d35ae6dc2edf3007d6696baea', + 'channel_url': 'https://www.youtube.com/channel/UCox6YeMSY1PQInbCtTaZj_w', + 'view_count': int, + 'uploader_url': 'http://www.youtube.com/@maheshchookolingo', }, }, ] def _real_extract(self, url): video_id = self._match_id(url) - data = self._download_json( - 'https://parler.com/open-api/ParleyDetailEndpoint.php', video_id, - data=urlencode_postdata({'uuid': video_id}))['data'][0] - primary = data['primary'] - - embed = self._parse_json(primary.get('V2LINKLONG') or '', video_id, fatal=False) - if embed: - return self.url_result(embed[0], YoutubeIE) + data = self._download_json(f'https://api.parler.com/v0/public/parleys/{video_id}', + video_id)['data'] + if data.get('link'): + return self.url_result(data['link'], YoutubeIE) return { 'id': video_id, - 'url': traverse_obj(primary, ('video_data', 'videoSrc')), - 'thumbnail': traverse_obj(primary, ('video_data', 'thumbnailUrl')), - 'title': '', - 'description': strip_or_none(clean_html(primary.get('full_body'))) or None, - 'timestamp': unified_timestamp(primary.get('date_created')), - 'uploader': strip_or_none(primary.get('name')), - 'uploader_id': strip_or_none(primary.get('username')), - 'uploader_url': format_field(strip_or_none(primary.get('username')), None, 'https://parler.com/%s'), - 'view_count': int_or_none(primary.get('view_count')), - 'comment_count': int_or_none(traverse_obj(data, ('engagement', 'commentCount'))), - 'repost_count': int_or_none(traverse_obj(data, ('engagement', 'echoCount'))), + 'title': strip_or_none(data.get('title')) or '', + **traverse_obj(data, { + 'url': ('video', 'videoSrc'), + 'thumbnail': ('video', 'thumbnailUrl'), + 'description': ('body', {clean_html}), + 'timestamp': ('date_created', {unified_timestamp}), + 'uploader': ('user', 'name', {strip_or_none}), + 'uploader_id': ('user', 'username', {str}), + 'uploader_url': ('user', 'username', {functools.partial(urljoin, 'https://parler.com/')}), + 'view_count': ('views', {int_or_none}), + 'comment_count': ('total_comments', {int_or_none}), + 'repost_count': ('echos', {int_or_none}), + }) }