yt_dlp/extractor/nate.py

   1 import itertools
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     str_or_none,
   7     traverse_obj,
   8     unified_strdate,
   9 )
  10
  11
  12 class NateIE(InfoExtractor):
  13     _VALID_URL = r'https?://tv\.nate\.com/clip/(?P<id>[0-9]+)'
  14
  15     _TESTS = [{
  16         'url': 'https://tv.nate.com/clip/1848976',
  17         'info_dict': {
  18             'id': '1848976',
  19             'ext': 'mp4',
  20             'title': '[결승 오프닝 타이틀] 2018 LCK 서머 스플릿 결승전 kt Rolster VS Griffin',
  21             'description': 'md5:e1b79a7dcf0d8d586443f11366f50e6f',
  22             'thumbnail': r're:^https?://.*\.jpg',
  23             'upload_date': '20180908',
  24             'age_limit': 15,
  25             'duration': 73,
  26             'uploader': '2018 LCK 서머 스플릿(롤챔스)',
  27             'channel': '2018 LCK 서머 스플릿(롤챔스)',
  28             'channel_id': '3606',
  29             'uploader_id': '3606',
  30             'tags': 'count:59',
  31         },
  32         'params': {'skip_download': True},
  33     }, {
  34         'url': 'https://tv.nate.com/clip/4300566',
  35         'info_dict': {
  36             'id': '4300566',
  37             'ext': 'mp4',
  38             'title': '[심쿵엔딩] 이준호x이세영, 서로를 기억하며 끌어안는 두 사람!💕, MBC 211204 방송',
  39             'description': 'md5:be1653502d9c13ce344ddf7828e089fa',
  40             'thumbnail': r're:^https?://.*\.jpg',
  41             'upload_date': '20211204',
  42             'age_limit': 15,
  43             'duration': 201,
  44             'uploader': '옷소매 붉은 끝동',
  45             'channel': '옷소매 붉은 끝동',
  46             'channel_id': '27987',
  47             'uploader_id': '27987',
  48             'tags': 'count:20',
  49         },
  50         'params': {'skip_download': True},
  51     }]
  52
  53     _QUALITY = {
  54         '36': 2160,
  55         '35': 1080,
  56         '34': 720,
  57         '33': 480,
  58         '32': 360,
  59         '31': 270,
  60     }
  61
  62     def _real_extract(self, url):
  63         video_id = self._match_id(url)
  64         video_data = self._download_json(f'https://tv.nate.com/api/v1/clip/{video_id}', video_id)
  65         formats = [{
  66             'format_id': f_url[-2:],
  67             'url': f_url,
  68             'height': self._QUALITY.get(f_url[-2:]),
  69             'quality': int_or_none(f_url[-2:]),
  70         } for f_url in video_data.get('smcUriList') or []]
  71         return {
  72             'id': video_id,
  73             'title': video_data.get('clipTitle'),
  74             'description': video_data.get('synopsis'),
  75             'thumbnail': video_data.get('contentImg'),
  76             'upload_date': unified_strdate(traverse_obj(video_data, 'broadDate', 'regDate')),
  77             'age_limit': video_data.get('targetAge'),
  78             'duration': video_data.get('playTime'),
  79             'formats': formats,
  80             'uploader': video_data.get('programTitle'),
  81             'channel': video_data.get('programTitle'),
  82             'channel_id': str_or_none(video_data.get('programSeq')),
  83             'uploader_id': str_or_none(video_data.get('programSeq')),
  84             'tags': video_data['hashTag'].split(',') if video_data.get('hashTag') else None,
  85         }
  86
  87
  88 class NateProgramIE(InfoExtractor):
  89     _VALID_URL = r'https?://tv\.nate\.com/program/clips/(?P<id>[0-9]+)'
  90
  91     _TESTS = [{
  92         'url': 'https://tv.nate.com/program/clips/27987',
  93         'playlist_mincount': 191,
  94         'info_dict': {
  95             'id': '27987',
  96         },
  97     }, {
  98         'url': 'https://tv.nate.com/program/clips/3606',
  99         'playlist_mincount': 15,
 100         'info_dict': {
 101             'id': '3606',
 102         },
 103     }]
 104
 105     def _entries(self, playlist_id):
 106         for page_num in itertools.count(1):
 107             program_data = self._download_json(
 108                 f'https://tv.nate.com/api/v1/program/{playlist_id}/clip/ranking?size=20&page={page_num}',
 109                 playlist_id, note=f'Downloading page {page_num}')
 110             for clip in program_data.get('content') or []:
 111                 clip_id = clip.get('clipSeq')
 112                 if clip_id:
 113                     yield self.url_result(
 114                         f'https://tv.nate.com/clip/{clip_id}', NateIE, playlist_id)
 115             if program_data.get('last'):
 116                 break
 117
 118     def _real_extract(self, url):
 119         playlist_id = self._match_id(url)
 120         return self.playlist_result(self._entries(playlist_id), playlist_id=playlist_id)