yt_dlp/extractor/aol.py

   1 import re
   2
   3 from .yahoo import YahooIE
   4 from ..utils import (
   5     ExtractorError,
   6     int_or_none,
   7     parse_qs,
   8     url_or_none,
   9 )
  10
  11
  12 class AolIE(YahooIE):  # XXX: Do not subclass from concrete IE
  13     IE_NAME = 'aol.com'
  14     _VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.(?:com|ca|co\.uk|de|jp)/video/(?:[^/]+/)*)(?P<id>\d{9}|[0-9a-f]{24}|[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12})'
  15
  16     _TESTS = [{
  17         # video with 5min ID
  18         'url': 'https://www.aol.com/video/view/u-s--official-warns-of-largest-ever-irs-phone-scam/518167793/',
  19         'md5': '18ef68f48740e86ae94b98da815eec42',
  20         'info_dict': {
  21             'id': '518167793',
  22             'ext': 'mp4',
  23             'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
  24             'description': 'A major phone scam has cost thousands of taxpayers more than $1 million, with less than a month until income tax returns are due to the IRS.',
  25             'timestamp': 1395405060,
  26             'upload_date': '20140321',
  27             'uploader': 'Newsy Studio',
  28         },
  29         'params': {
  30             # m3u8 download
  31             'skip_download': True,
  32         }
  33     }, {
  34         # video with vidible ID
  35         'url': 'https://www.aol.com/video/view/netflix-is-raising-rates/5707d6b8e4b090497b04f706/',
  36         'info_dict': {
  37             'id': '5707d6b8e4b090497b04f706',
  38             'ext': 'mp4',
  39             'title': 'Netflix is Raising Rates',
  40             'description': 'Netflix is rewarding millions of it’s long-standing members with an increase in cost. Veuer’s Carly Figueroa has more.',
  41             'upload_date': '20160408',
  42             'timestamp': 1460123280,
  43             'uploader': 'Veuer',
  44         },
  45         'params': {
  46             # m3u8 download
  47             'skip_download': True,
  48         }
  49     }, {
  50         'url': 'https://www.aol.com/video/view/park-bench-season-2-trailer/559a1b9be4b0c3bfad3357a7/',
  51         'only_matching': True,
  52     }, {
  53         'url': 'https://www.aol.com/video/view/donald-trump-spokeswoman-tones-down-megyn-kelly-attacks/519442220/',
  54         'only_matching': True,
  55     }, {
  56         'url': 'aol-video:5707d6b8e4b090497b04f706',
  57         'only_matching': True,
  58     }, {
  59         'url': 'https://www.aol.com/video/playlist/PL8245/5ca79d19d21f1a04035db606/',
  60         'only_matching': True,
  61     }, {
  62         'url': 'https://www.aol.ca/video/view/u-s-woman-s-family-arrested-for-murder-first-pinned-on-panhandler-police/5c7ccf45bc03931fa04b2fe1/',
  63         'only_matching': True,
  64     }, {
  65         'url': 'https://www.aol.co.uk/video/view/-one-dead-and-22-hurt-in-bus-crash-/5cb3a6f3d21f1a072b457347/',
  66         'only_matching': True,
  67     }, {
  68         'url': 'https://www.aol.de/video/view/eva-braun-privataufnahmen-von-hitlers-geliebter-werden-digitalisiert/5cb2d49de98ab54c113d3d5d/',
  69         'only_matching': True,
  70     }, {
  71         'url': 'https://www.aol.jp/video/playlist/5a28e936a1334d000137da0c/5a28f3151e642219fde19831/',
  72         'only_matching': True,
  73     }, {
  74         # Yahoo video
  75         'url': 'https://www.aol.com/video/play/991e6700-ac02-11ea-99ff-357400036f61/24bbc846-3e30-3c46-915e-fe8ccd7fcc46/',
  76         'only_matching': True,
  77     }]
  78
  79     def _real_extract(self, url):
  80         video_id = self._match_id(url)
  81         if '-' in video_id:
  82             return self._extract_yahoo_video(video_id, 'us')
  83
  84         response = self._download_json(
  85             'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id,
  86             video_id)['response']
  87         if response['statusText'] != 'Ok':
  88             raise ExtractorError('%s said: %s' % (self.IE_NAME, response['statusText']), expected=True)
  89
  90         video_data = response['data']
  91         formats = []
  92         m3u8_url = url_or_none(video_data.get('videoMasterPlaylist'))
  93         if m3u8_url:
  94             formats.extend(self._extract_m3u8_formats(
  95                 m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
  96         for rendition in video_data.get('renditions', []):
  97             video_url = url_or_none(rendition.get('url'))
  98             if not video_url:
  99                 continue
 100             ext = rendition.get('format')
 101             if ext == 'm3u8':
 102                 formats.extend(self._extract_m3u8_formats(
 103                     video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
 104             else:
 105                 f = {
 106                     'url': video_url,
 107                     'format_id': rendition.get('quality'),
 108                 }
 109                 mobj = re.search(r'(\d+)x(\d+)', video_url)
 110                 if mobj:
 111                     f.update({
 112                         'width': int(mobj.group(1)),
 113                         'height': int(mobj.group(2)),
 114                     })
 115                 else:
 116                     qs = parse_qs(video_url)
 117                     f.update({
 118                         'width': int_or_none(qs.get('w', [None])[0]),
 119                         'height': int_or_none(qs.get('h', [None])[0]),
 120                     })
 121                 formats.append(f)
 122
 123         return {
 124             'id': video_id,
 125             'title': video_data['title'],
 126             'duration': int_or_none(video_data.get('duration')),
 127             'timestamp': int_or_none(video_data.get('publishDate')),
 128             'view_count': int_or_none(video_data.get('views')),
 129             'description': video_data.get('description'),
 130             'uploader': video_data.get('videoOwner'),
 131             'formats': formats,
 132         }