yt_dlp/extractor/skynewsarabia.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     parse_duration,
   4     parse_iso8601,
   5 )
   6
   7
   8 class SkyNewsArabiaBaseIE(InfoExtractor):
   9     _IMAGE_BASE_URL = 'http://www.skynewsarabia.com/web/images'
  10
  11     def _call_api(self, path, value):
  12         return self._download_json(f'http://api.skynewsarabia.com/web/rest/v2/{path}/{value}.json', value)
  13
  14     def _get_limelight_media_id(self, url):
  15         return self._search_regex(r'/media/[^/]+/([a-z0-9]{32})', url, 'limelight media id')
  16
  17     def _get_image_url(self, image_path_template, width='1600', height='1200'):
  18         return self._IMAGE_BASE_URL + image_path_template.format(width=width, height=height)
  19
  20     def _extract_video_info(self, video_data):
  21         video_id = str(video_data['id'])
  22         topic = video_data.get('topicTitle')
  23         return {
  24             '_type': 'url_transparent',
  25             'url': 'limelight:media:{}'.format(self._get_limelight_media_id(video_data['videoUrl'][0]['url'])),
  26             'id': video_id,
  27             'title': video_data['headline'],
  28             'description': video_data.get('summary'),
  29             'thumbnail': self._get_image_url(video_data['mediaAsset']['imageUrl']),
  30             'timestamp': parse_iso8601(video_data.get('date')),
  31             'duration': parse_duration(video_data.get('runTime')),
  32             'tags': video_data.get('tags', []),
  33             'categories': [topic] if topic else [],
  34             'webpage_url': f'http://www.skynewsarabia.com/web/video/{video_id}',
  35             'ie_key': 'LimelightMedia',
  36         }
  37
  38
  39 class SkyNewsArabiaIE(SkyNewsArabiaBaseIE):
  40     _WORKING = False
  41     IE_NAME = 'skynewsarabia:video'
  42     _VALID_URL = r'https?://(?:www\.)?skynewsarabia\.com/web/video/(?P<id>[0-9]+)'
  43     _TEST = {
  44         'url': 'http://www.skynewsarabia.com/web/video/794902/%D9%86%D8%B5%D9%81-%D9%85%D9%84%D9%8A%D9%88%D9%86-%D9%85%D8%B5%D8%A8%D8%A7%D8%AD-%D8%B4%D8%AC%D8%B1%D8%A9-%D9%83%D8%B1%D9%8A%D8%B3%D9%85%D8%A7%D8%B3',
  45         'info_dict': {
  46             'id': '794902',
  47             'ext': 'flv',
  48             'title': 'نصف مليون مصباح على شجرة كريسماس',
  49             'description': 'md5:22f1b27f0850eeb10c7e59b1f16eb7c6',
  50             'upload_date': '20151128',
  51             'timestamp': 1448697198,
  52             'duration': 2119,
  53         },
  54         'params': {
  55             # rtmp download
  56             'skip_download': True,
  57         },
  58     }
  59
  60     def _real_extract(self, url):
  61         video_id = self._match_id(url)
  62         video_data = self._call_api('video', video_id)
  63         return self._extract_video_info(video_data)
  64
  65
  66 class SkyNewsArabiaArticleIE(SkyNewsArabiaBaseIE):
  67     _WORKING = False
  68     IE_NAME = 'skynewsarabia:article'
  69     _VALID_URL = r'https?://(?:www\.)?skynewsarabia\.com/web/article/(?P<id>[0-9]+)'
  70     _TESTS = [{
  71         'url': 'http://www.skynewsarabia.com/web/article/794549/%D8%A7%D9%94%D8%AD%D8%AF%D8%A7%D8%AB-%D8%A7%D9%84%D8%B4%D8%B1%D9%82-%D8%A7%D9%84%D8%A7%D9%94%D9%88%D8%B3%D8%B7-%D8%AE%D8%B1%D9%8A%D8%B7%D8%A9-%D8%A7%D9%84%D8%A7%D9%94%D9%84%D8%B9%D8%A7%D8%A8-%D8%A7%D9%84%D8%B0%D9%83%D9%8A%D8%A9',
  72         'info_dict': {
  73             'id': '794549',
  74             'ext': 'flv',
  75             'title': 'بالفيديو.. ألعاب ذكية تحاكي واقع المنطقة',
  76             'description': 'md5:0c373d29919a851e080ee4edd0c5d97f',
  77             'upload_date': '20151126',
  78             'timestamp': 1448559336,
  79             'duration': 281.6,
  80         },
  81         'params': {
  82             # rtmp download
  83             'skip_download': True,
  84         },
  85     }, {
  86         'url': 'http://www.skynewsarabia.com/web/article/794844/%D8%A7%D8%B3%D8%AA%D9%87%D8%AF%D8%A7%D9%81-%D9%82%D9%88%D8%A7%D8%B1%D8%A8-%D8%A7%D9%94%D8%B3%D9%84%D8%AD%D8%A9-%D9%84%D9%85%D9%8A%D9%84%D9%8A%D8%B4%D9%8A%D8%A7%D8%AA-%D8%A7%D9%84%D8%AD%D9%88%D8%AB%D9%8A-%D9%88%D8%B5%D8%A7%D9%84%D8%AD',
  87         'info_dict': {
  88             'id': '794844',
  89             'title': 'إحباط تهريب أسلحة لميليشيات الحوثي وصالح بجنوب اليمن',
  90             'description': 'md5:5c927b8b2e805796e7f693538d96fc7e',
  91         },
  92         'playlist_mincount': 2,
  93     }]
  94
  95     def _real_extract(self, url):
  96         article_id = self._match_id(url)
  97         article_data = self._call_api('article', article_id)
  98         media_asset = article_data['mediaAsset']
  99         if media_asset['type'] == 'VIDEO':
 100             topic = article_data.get('topicTitle')
 101             return {
 102                 '_type': 'url_transparent',
 103                 'url': 'limelight:media:{}'.format(self._get_limelight_media_id(media_asset['videoUrl'][0]['url'])),
 104                 'id': article_id,
 105                 'title': article_data['headline'],
 106                 'description': article_data.get('summary'),
 107                 'thumbnail': self._get_image_url(media_asset['imageUrl']),
 108                 'timestamp': parse_iso8601(article_data.get('date')),
 109                 'tags': article_data.get('tags', []),
 110                 'categories': [topic] if topic else [],
 111                 'webpage_url': url,
 112                 'ie_key': 'LimelightMedia',
 113             }
 114         entries = [self._extract_video_info(item) for item in article_data.get('inlineItems', []) if item['type'] == 'VIDEO']
 115         return self.playlist_result(entries, article_id, article_data['headline'], article_data.get('summary'))