yt_dlp/extractor/banbye.py

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