yt_dlp/extractor/banbye.py

   1 import math
   2 import urllib.parse
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     InAdvancePagedList,
   7     format_field,
   8     traverse_obj,
   9     unified_timestamp,
  10 )
  11
  12
  13 class BanByeBaseIE(InfoExtractor):
  14     _API_BASE = 'https://api.banbye.com'
  15     _CDN_BASE = 'https://cdn.banbye.com'
  16     _VIDEO_BASE = 'https://banbye.com/watch'
  17
  18     @staticmethod
  19     def _extract_playlist_id(url, param='playlist'):
  20         return urllib.parse.parse_qs(
  21             urllib.parse.urlparse(url).query).get(param, [None])[0]
  22
  23     def _extract_playlist(self, playlist_id):
  24         data = self._download_json(f'{self._API_BASE}/playlists/{playlist_id}', playlist_id)
  25         return self.playlist_result([
  26             self.url_result(f'{self._VIDEO_BASE}/{video_id}', BanByeIE)
  27             for video_id in data['videoIds']], playlist_id, data.get('name'))
  28
  29
  30 class BanByeIE(BanByeBaseIE):
  31     _VALID_URL = r'https?://(?:www\.)?banbye\.com/(?:en/)?watch/(?P<id>[\w-]+)'
  32     _TESTS = [{
  33         'url': 'https://banbye.com/watch/v_ytfmvkVYLE8T',
  34         'md5': '2f4ea15c5ca259a73d909b2cfd558eb5',
  35         'info_dict': {
  36             'id': 'v_ytfmvkVYLE8T',
  37             'ext': 'mp4',
  38             'title': 'md5:5ec098f88a0d796f987648de6322ba0f',
  39             'description': 'md5:4d94836e73396bc18ef1fa0f43e5a63a',
  40             'uploader': 'wRealu24',
  41             'channel_id': 'ch_wrealu24',
  42             'channel_url': 'https://banbye.com/channel/ch_wrealu24',
  43             'timestamp': 1647604800,
  44             'upload_date': '20220318',
  45             'duration': 1931,
  46             'thumbnail': r're:https?://.*\.webp',
  47             'tags': 'count:5',
  48             'like_count': int,
  49             'dislike_count': int,
  50             'view_count': int,
  51             'comment_count': int,
  52         },
  53     }, {
  54         'url': 'https://banbye.com/watch/v_2JjQtqjKUE_F?playlistId=p_Ld82N6gBw_OJ',
  55         'info_dict': {
  56             'title': 'Krzysztof Karoń',
  57             'id': 'p_Ld82N6gBw_OJ',
  58         },
  59         'playlist_mincount': 9,
  60     }, {
  61         'url': 'https://banbye.com/watch/v_kb6_o1Kyq-CD',
  62         'info_dict': {
  63             'id': 'v_kb6_o1Kyq-CD',
  64             'ext': 'mp4',
  65             'title': 'Co tak naprawdę dzieje się we Francji?! Czy Warszawa a potem cała Polska będzie drugim Paryżem?!🤔🇵🇱',
  66             'description': 'md5:82be4c0e13eae8ea1ca8b9f2e07226a8',
  67             'uploader': 'Marcin Rola - MOIM ZDANIEM!🇵🇱',
  68             'channel_id': 'ch_QgWnHvDG2fo5',
  69             'channel_url': 'https://banbye.com/channel/ch_QgWnHvDG2fo5',
  70             'duration': 597,
  71             'timestamp': 1688642656,
  72             'upload_date': '20230706',
  73             'thumbnail': 'https://cdn.banbye.com/video/v_kb6_o1Kyq-CD/96.webp',
  74             'tags': ['Paryż', 'Francja', 'Polska', 'Imigranci', 'Morawiecki', 'Tusk'],
  75             'like_count': int,
  76             'dislike_count': int,
  77             'view_count': int,
  78             'comment_count': int,
  79         },
  80     }]
  81
  82     def _real_extract(self, url):
  83         video_id = self._match_id(url)
  84         playlist_id = self._extract_playlist_id(url, 'playlistId')
  85
  86         if self._yes_playlist(playlist_id, video_id):
  87             return self._extract_playlist(playlist_id)
  88
  89         data = self._download_json(f'{self._API_BASE}/videos/{video_id}', video_id)
  90         thumbnails = [{
  91             'id': f'{quality}p',
  92             'url': f'{self._CDN_BASE}/video/{video_id}/{quality}.webp',
  93         } for quality in [48, 96, 144, 240, 512, 1080]]
  94         formats = [{
  95             'format_id': f'http-{quality}p',
  96             'quality': quality,
  97             'url': f'{self._CDN_BASE}/video/{video_id}/{quality}.mp4',
  98         } for quality in data['quality']]
  99
 100         return {
 101             'id': video_id,
 102             'title': data.get('title'),
 103             'description': data.get('desc'),
 104             'uploader': traverse_obj(data, ('channel', 'name')),
 105             'channel_id': data.get('channelId'),
 106             'channel_url': format_field(data, 'channelId', 'https://banbye.com/channel/%s'),
 107             'timestamp': unified_timestamp(data.get('publishedAt')),
 108             'duration': data.get('duration'),
 109             'tags': data.get('tags'),
 110             'formats': formats,
 111             'thumbnails': thumbnails,
 112             'like_count': data.get('likes'),
 113             'dislike_count': data.get('dislikes'),
 114             'view_count': data.get('views'),
 115             'comment_count': data.get('commentCount'),
 116         }
 117
 118
 119 class BanByeChannelIE(BanByeBaseIE):
 120     _VALID_URL = r'https?://(?:www\.)?banbye\.com/(?:en/)?channel/(?P<id>\w+)'
 121     _TESTS = [{
 122         'url': 'https://banbye.com/channel/ch_wrealu24',
 123         'info_dict': {
 124             'title': 'wRealu24',
 125             'id': 'ch_wrealu24',
 126             'description': 'md5:da54e48416b74dfdde20a04867c0c2f6',
 127         },
 128         'playlist_mincount': 791,
 129     }, {
 130         'url': 'https://banbye.com/channel/ch_wrealu24?playlist=p_Ld82N6gBw_OJ',
 131         'info_dict': {
 132             'title': 'Krzysztof Karoń',
 133             'id': 'p_Ld82N6gBw_OJ',
 134         },
 135         'playlist_count': 9,
 136     }]
 137     _PAGE_SIZE = 100
 138
 139     def _real_extract(self, url):
 140         channel_id = self._match_id(url)
 141         playlist_id = self._extract_playlist_id(url)
 142
 143         if playlist_id:
 144             return self._extract_playlist(playlist_id)
 145
 146         def page_func(page_num):
 147             data = self._download_json(f'{self._API_BASE}/videos', channel_id, query={
 148                 'channelId': channel_id,
 149                 'sort': 'new',
 150                 'limit': self._PAGE_SIZE,
 151                 'offset': page_num * self._PAGE_SIZE,
 152             }, note=f'Downloading page {page_num + 1}')
 153             return [
 154                 self.url_result(f"{self._VIDEO_BASE}/{video['_id']}", BanByeIE)
 155                 for video in data['items']
 156             ]
 157
 158         channel_data = self._download_json(f'{self._API_BASE}/channels/{channel_id}', channel_id)
 159         entries = InAdvancePagedList(
 160             page_func,
 161             math.ceil(channel_data['videoCount'] / self._PAGE_SIZE),
 162             self._PAGE_SIZE)
 163
 164         return self.playlist_result(
 165             entries, channel_id, channel_data.get('name'), channel_data.get('description'))