youtube_dl/extractor/line.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import js_to_json
   8
   9
  10 class LineTVIE(InfoExtractor):
  11     _VALID_URL = r'https?://tv\.line\.me/v/(?P<id>\d+)_[^/]+-(?P<segment>ep\d+-\d+)'
  12
  13     _TESTS = [{
  14         'url': 'https://tv.line.me/v/793123_goodbye-mrblack-ep1-1/list/69246',
  15         'info_dict': {
  16             'id': '793123_ep1-1',
  17             'ext': 'mp4',
  18             'title': 'Goodbye Mr.Black | EP.1-1',
  19             'thumbnail': r're:^https?://.*\.jpg$',
  20             'duration': 998.509,
  21             'view_count': int,
  22         },
  23     }, {
  24         'url': 'https://tv.line.me/v/2587507_%E6%B4%BE%E9%81%A3%E5%A5%B3%E9%86%ABx-ep1-02/list/185245',
  25         'only_matching': True,
  26     }]
  27
  28     def _real_extract(self, url):
  29         series_id, segment = re.match(self._VALID_URL, url).groups()
  30         video_id = '%s_%s' % (series_id, segment)
  31
  32         webpage = self._download_webpage(url, video_id)
  33
  34         player_params = self._parse_json(self._search_regex(
  35             r'naver\.WebPlayer\(({[^}]+})\)', webpage, 'player parameters'),
  36             video_id, transform_source=js_to_json)
  37
  38         video_info = self._download_json(
  39             'https://global-nvapis.line.me/linetv/rmcnmv/vod_play_videoInfo.json',
  40             video_id, query={
  41                 'videoId': player_params['videoId'],
  42                 'key': player_params['key'],
  43             })
  44
  45         stream = video_info['streams'][0]
  46         extra_query = '?__gda__=' + stream['key']['value']
  47         formats = self._extract_m3u8_formats(
  48             stream['source'] + extra_query, video_id, ext='mp4',
  49             entry_protocol='m3u8_native', m3u8_id='hls')
  50
  51         for a_format in formats:
  52             a_format['url'] += extra_query
  53
  54         duration = None
  55         for video in video_info.get('videos', {}).get('list', []):
  56             encoding_option = video.get('encodingOption', {})
  57             abr = video['bitrate']['audio']
  58             vbr = video['bitrate']['video']
  59             tbr = abr + vbr
  60             formats.append({
  61                 'url': video['source'],
  62                 'format_id': 'http-%d' % int(tbr),
  63                 'height': encoding_option.get('height'),
  64                 'width': encoding_option.get('width'),
  65                 'abr': abr,
  66                 'vbr': vbr,
  67                 'filesize': video.get('size'),
  68             })
  69             if video.get('duration') and duration is None:
  70                 duration = video['duration']
  71
  72         self._sort_formats(formats)
  73
  74         if not formats[0].get('width'):
  75             formats[0]['vcodec'] = 'none'
  76
  77         title = self._og_search_title(webpage)
  78
  79         # like_count requires an additional API request https://tv.line.me/api/likeit/getCount
  80
  81         return {
  82             'id': video_id,
  83             'title': title,
  84             'formats': formats,
  85             'extra_param_to_segment_url': extra_query[1:],
  86             'duration': duration,
  87             'thumbnails': [{'url': thumbnail['source']}
  88                            for thumbnail in video_info.get('thumbnails', {}).get('list', [])],
  89             'view_count': video_info.get('meta', {}).get('count'),
  90         }