yt_dlp/extractor/gopro.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     remove_end,
   8     str_or_none,
   9     try_get,
  10     unified_timestamp,
  11     url_or_none,
  12 )
  13
  14
  15 class GoProIE(InfoExtractor):
  16     _VALID_URL = r'https?://(www\.)?gopro\.com/v/(?P<id>[A-Za-z0-9]+)'
  17
  18     _TESTS = [{
  19         'url': 'https://gopro.com/v/ZNVvED8QDzR5V',
  20         'info_dict': {
  21             'id': 'ZNVvED8QDzR5V',
  22             'title': 'My GoPro Adventure - 9/19/21',
  23             'thumbnail': r're:https?://.+',
  24             'ext': 'mp4',
  25             'timestamp': 1632072947,
  26             'upload_date': '20210919',
  27             'uploader_id': 'fireydive30018',
  28             'duration': 396062,
  29         }
  30     }, {
  31         'url': 'https://gopro.com/v/KRm6Vgp2peg4e',
  32         'info_dict': {
  33             'id': 'KRm6Vgp2peg4e',
  34             'title': 'じゃがいも カリカリ オーブン焼き',
  35             'thumbnail': r're:https?://.+',
  36             'ext': 'mp4',
  37             'timestamp': 1607231125,
  38             'upload_date': '20201206',
  39             'uploader_id': 'dc9bcb8b-47d2-47c6-afbc-4c48f9a3769e',
  40             'duration': 45187,
  41             'track': 'The Sky Machine',
  42         }
  43     }, {
  44         'url': 'https://gopro.com/v/kVrK9wlJvBMwn',
  45         'info_dict': {
  46             'id': 'kVrK9wlJvBMwn',
  47             'title': 'DARKNESS',
  48             'thumbnail': r're:https?://.+',
  49             'ext': 'mp4',
  50             'timestamp': 1594183735,
  51             'upload_date': '20200708',
  52             'uploader_id': '闇夜乃皇帝',
  53             'duration': 313075,
  54             'track': 'Battery (Live)',
  55             'artist': 'Metallica',
  56         }
  57     }]
  58
  59     def _real_extract(self, url):
  60         video_id = self._match_id(url)
  61         webpage = self._download_webpage(url, video_id)
  62
  63         metadata = self._parse_json(
  64             self._html_search_regex(r'window\.__reflectData\s*=\s*([^;]+)', webpage, 'metadata'), video_id)
  65
  66         video_info = metadata['collectionMedia'][0]
  67         media_data = self._download_json(
  68             'https://api.gopro.com/media/%s/download' % video_info['id'], video_id)
  69
  70         formats = []
  71         for fmt in try_get(media_data, lambda x: x['_embedded']['variations']) or []:
  72             format_url = url_or_none(fmt.get('url'))
  73             if not format_url:
  74                 continue
  75             formats.append({
  76                 'url': format_url,
  77                 'format_id': str_or_none(fmt.get('quality')),
  78                 'format_note': str_or_none(fmt.get('label')),
  79                 'ext': str_or_none(fmt.get('type')),
  80                 'width': int_or_none(fmt.get('width')),
  81                 'height': int_or_none(fmt.get('height')),
  82             })
  83
  84         self._sort_formats(formats)
  85
  86         title = str_or_none(
  87             try_get(metadata, lambda x: x['collection']['title'])
  88             or self._html_search_meta(['og:title', 'twitter:title'], webpage)
  89             or remove_end(self._html_search_regex(
  90                 r'<title[^>]*>([^<]+)</title>', webpage, 'title', fatal=False), ' | GoPro'))
  91         if title:
  92             title = title.replace('\n', ' ')
  93
  94         return {
  95             'id': video_id,
  96             'title': title,
  97             'formats': formats,
  98             'thumbnail': url_or_none(
  99                 self._html_search_meta(['og:image', 'twitter:image'], webpage)),
 100             'timestamp': unified_timestamp(
 101                 try_get(metadata, lambda x: x['collection']['created_at'])),
 102             'uploader_id': str_or_none(
 103                 try_get(metadata, lambda x: x['account']['nickname'])),
 104             'duration': int_or_none(
 105                 video_info.get('source_duration')),
 106             'artist': str_or_none(
 107                 video_info.get('music_track_artist')),
 108             'track': str_or_none(
 109                 video_info.get('music_track_name')),
 110         }