youtube_dl/extractor/skynewsarabia.py

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