yt_dlp/extractor/abcotvs.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     dict_get,
   5     int_or_none,
   6     try_get,
   7 )
   8
   9
  10 class ABCOTVSIE(InfoExtractor):
  11     IE_NAME = 'abcotvs'
  12     IE_DESC = 'ABC Owned Television Stations'
  13     _VALID_URL = r'https?://(?P<site>abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:(?:/[^/]+)*/(?P<display_id>[^/]+))?/(?P<id>\d+)'
  14     _TESTS = [
  15         {
  16             'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
  17             'info_dict': {
  18                 'id': '472548',
  19                 'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
  20                 'ext': 'mp4',
  21                 'title': 'East Bay museum celebrates synthesized music',
  22                 'description': 'md5:24ed2bd527096ec2a5c67b9d5a9005f3',
  23                 'thumbnail': r're:^https?://.*\.jpg$',
  24                 'timestamp': 1421118520,
  25                 'upload_date': '20150113',
  26             },
  27             'params': {
  28                 # m3u8 download
  29                 'skip_download': True,
  30             },
  31         },
  32         {
  33             'url': 'http://abc7news.com/472581',
  34             'only_matching': True,
  35         },
  36         {
  37             'url': 'https://6abc.com/man-75-killed-after-being-struck-by-vehicle-in-chester/5725182/',
  38             'only_matching': True,
  39         },
  40     ]
  41     _SITE_MAP = {
  42         '6abc': 'wpvi',
  43         'abc11': 'wtvd',
  44         'abc13': 'ktrk',
  45         'abc30': 'kfsn',
  46         'abc7': 'kabc',
  47         'abc7chicago': 'wls',
  48         'abc7news': 'kgo',
  49         'abc7ny': 'wabc',
  50     }
  51
  52     def _real_extract(self, url):
  53         site, display_id, video_id = self._match_valid_url(url).groups()
  54         display_id = display_id or video_id
  55         station = self._SITE_MAP[site]
  56
  57         data = self._download_json(
  58             'https://api.abcotvs.com/v2/content', display_id, query={
  59                 'id': video_id,
  60                 'key': 'otv.web.%s.story' % station,
  61                 'station': station,
  62             })['data']
  63         video = try_get(data, lambda x: x['featuredMedia']['video'], dict) or data
  64         video_id = compat_str(dict_get(video, ('id', 'publishedKey'), video_id))
  65         title = video.get('title') or video['linkText']
  66
  67         formats = []
  68         m3u8_url = video.get('m3u8')
  69         if m3u8_url:
  70             formats = self._extract_m3u8_formats(
  71                 video['m3u8'].split('?')[0], display_id, 'mp4', m3u8_id='hls', fatal=False)
  72         mp4_url = video.get('mp4')
  73         if mp4_url:
  74             formats.append({
  75                 'abr': 128,
  76                 'format_id': 'https',
  77                 'height': 360,
  78                 'url': mp4_url,
  79                 'width': 640,
  80             })
  81         self._sort_formats(formats)
  82
  83         image = video.get('image') or {}
  84
  85         return {
  86             'id': video_id,
  87             'display_id': display_id,
  88             'title': title,
  89             'description': dict_get(video, ('description', 'caption'), try_get(video, lambda x: x['meta']['description'])),
  90             'thumbnail': dict_get(image, ('source', 'dynamicSource')),
  91             'timestamp': int_or_none(video.get('date')),
  92             'duration': int_or_none(video.get('length')),
  93             'formats': formats,
  94         }
  95
  96
  97 class ABCOTVSClipsIE(InfoExtractor):
  98     IE_NAME = 'abcotvs:clips'
  99     _VALID_URL = r'https?://clips\.abcotvs\.com/(?:[^/]+/)*video/(?P<id>\d+)'
 100     _TEST = {
 101         'url': 'https://clips.abcotvs.com/kabc/video/214814',
 102         'info_dict': {
 103             'id': '214814',
 104             'ext': 'mp4',
 105             'title': 'SpaceX launch pad explosion destroys rocket, satellite',
 106             'description': 'md5:9f186e5ad8f490f65409965ee9c7be1b',
 107             'upload_date': '20160901',
 108             'timestamp': 1472756695,
 109         },
 110         'params': {
 111             # m3u8 download
 112             'skip_download': True,
 113         },
 114     }
 115
 116     def _real_extract(self, url):
 117         video_id = self._match_id(url)
 118         video_data = self._download_json('https://clips.abcotvs.com/vogo/video/getByIds?ids=' + video_id, video_id)['results'][0]
 119         title = video_data['title']
 120         formats = self._extract_m3u8_formats(
 121             video_data['videoURL'].split('?')[0], video_id, 'mp4')
 122         self._sort_formats(formats)
 123
 124         return {
 125             'id': video_id,
 126             'title': title,
 127             'description': video_data.get('description'),
 128             'thumbnail': video_data.get('thumbnailURL'),
 129             'duration': int_or_none(video_data.get('duration')),
 130             'timestamp': int_or_none(video_data.get('pubDate')),
 131             'formats': formats,
 132         }