yt_dlp/extractor/amazon.py

   1 from .common import InfoExtractor
   2 from ..utils import ExtractorError, int_or_none
   3
   4
   5 class AmazonStoreIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?amazon\.(?:[a-z]{2,3})(?:\.[a-z]{2})?/(?:[^/]+/)?(?:dp|gp/product)/(?P<id>[^/&#$?]+)'
   7
   8     _TESTS = [{
   9         'url': 'https://www.amazon.co.uk/dp/B098XNCHLD/',
  10         'info_dict': {
  11             'id': 'B098XNCHLD',
  12             'title': 'md5:dae240564cbb2642170c02f7f0d7e472',
  13         },
  14         'playlist_mincount': 1,
  15         'playlist': [{
  16             'info_dict': {
  17                 'id': 'A1F83G8C2ARO7P',
  18                 'ext': 'mp4',
  19                 'title': 'mcdodo usb c cable 100W 5a',
  20                 'thumbnail': r're:^https?://.*\.jpg$',
  21                 'duration': 34,
  22             },
  23         }]
  24     }, {
  25         'url': 'https://www.amazon.in/Sony-WH-1000XM4-Cancelling-Headphones-Bluetooth/dp/B0863TXGM3',
  26         'info_dict': {
  27             'id': 'B0863TXGM3',
  28             'title': 'md5:d1d3352428f8f015706c84b31e132169',
  29         },
  30         'playlist_mincount': 4,
  31     }, {
  32         'url': 'https://www.amazon.com/dp/B0845NXCXF/',
  33         'info_dict': {
  34             'id': 'B0845NXCXF',
  35             'title': 'md5:f3fa12779bf62ddb6a6ec86a360a858e',
  36         },
  37         'playlist-mincount': 1,
  38     }, {
  39         'url': 'https://www.amazon.es/Samsung-Smartphone-s-AMOLED-Quad-c%C3%A1mara-espa%C3%B1ola/dp/B08WX337PQ',
  40         'info_dict': {
  41             'id': 'B08WX337PQ',
  42             'title': 'md5:f3fa12779bf62ddb6a6ec86a360a858e',
  43         },
  44         'playlist_mincount': 1,
  45     }]
  46
  47     def _real_extract(self, url):
  48         id = self._match_id(url)
  49
  50         for retry in self.RetryManager():
  51             webpage = self._download_webpage(url, id)
  52             try:
  53                 data_json = self._search_json(
  54                     r'var\s?obj\s?=\s?jQuery\.parseJSON\(\'', webpage, 'data', id,
  55                     transform_source=lambda x: x.replace(R'\\u', R'\u'))
  56             except ExtractorError as e:
  57                 retry.error = e
  58
  59         entries = [{
  60             'id': video['marketPlaceID'],
  61             'url': video['url'],
  62             'title': video.get('title'),
  63             'thumbnail': video.get('thumbUrl') or video.get('thumb'),
  64             'duration': video.get('durationSeconds'),
  65             'height': int_or_none(video.get('videoHeight')),
  66             'width': int_or_none(video.get('videoWidth')),
  67         } for video in (data_json.get('videos') or []) if video.get('isVideo') and video.get('url')]
  68         return self.playlist_result(entries, playlist_id=id, playlist_title=data_json.get('title'))