]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/amazon.py
1 from .common
import InfoExtractor
2 from ..utils
import int_or_none
5 class AmazonStoreIE(InfoExtractor
):
6 _VALID_URL
= r
'https?://(?:www\.)?amazon\.(?:[a-z]{2,3})(?:\.[a-z]{2})?/(?:[^/]+/)?(?:dp|gp/product)/(?P<id>[^/&#$?]+)'
9 'url': 'https://www.amazon.co.uk/dp/B098XNCHLD/',
12 'title': 'md5:5f3194dbf75a8dcfc83079bd63a2abed',
14 'playlist_mincount': 1,
17 'id': 'A1F83G8C2ARO7P',
19 'title': 'mcdodo usb c cable 100W 5a',
20 'thumbnail': r
're:^https?://.*\.jpg$',
24 'url': 'https://www.amazon.in/Sony-WH-1000XM4-Cancelling-Headphones-Bluetooth/dp/B0863TXGM3',
27 'title': 'md5:b0bde4881d3cfd40d63af19f7898b8ff',
29 'playlist_mincount': 4,
31 'url': 'https://www.amazon.com/dp/B0845NXCXF/',
34 'title': 'md5:2145cd4e3c7782f1ee73649a3cff1171',
36 'playlist-mincount': 1,
39 def _real_extract(self
, url
):
40 id = self
._match
_id
(url
)
41 webpage
= self
._download
_webpage
(url
, id)
42 data_json
= self
._parse
_json
(self
._html
_search
_regex
(r
'var\s?obj\s?=\s?jQuery\.parseJSON\(\'(.*)\'\
)', webpage, 'data
'), id)
44 'id': video['marketPlaceID
'],
46 'title
': video.get('title
'),
47 'thumbnail
': video.get('thumbUrl
') or video.get('thumb
'),
48 'duration
': video.get('durationSeconds
'),
49 'height
': int_or_none(video.get('videoHeight
')),
50 'width
': int_or_none(video.get('videoWidth
')),
51 } for video in (data_json.get('videos
') or []) if video.get('isVideo
') and video.get('url
')]
52 return self.playlist_result(entries, playlist_id=id, playlist_title=data_json['title
'])