1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-05 02:32:44 +01:00
yt-dlp/yt_dlp/extractor/kankanews.py
lkw123 074b2fae90
[extractor/kankanews] Add extractor (#5729)
Authored by: synthpop123
2022-12-29 13:08:49 +05:30

49 lines
1.7 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import time
import random
import string
import hashlib
import urllib.parse
from .common import InfoExtractor
class KankaNewsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?kankanews\.com/a/\d+\-\d+\-\d+/(?P<id>\d+)\.shtml'
_TESTS = [{
'url': 'https://www.kankanews.com/a/2022-11-08/00310276054.shtml?appid=1088227',
'md5': '05e126513c74b1258d657452a6f4eef9',
'info_dict': {
'id': '4485057',
'url': 'http://mediaplay.kksmg.com/2022/11/08/h264_450k_mp4_1a388ad771e0e4cc28b0da44d245054e_ncm.mp4',
'ext': 'mp4',
'title': '视频第23个中国记者节我们在进博切蛋糕',
'thumbnail': r're:^https?://.*\.jpg*',
}
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(r'omsid\s*=\s*"(\d+)"', webpage, 'video id')
params = {
'nonce': ''.join(random.choices(string.ascii_lowercase + string.digits, k=8)),
'omsid': video_id,
'platform': 'pc',
'timestamp': int(time.time()),
'version': '1.0',
}
params['sign'] = hashlib.md5((hashlib.md5((
urllib.parse.urlencode(params) + '&28c8edde3d61a0411511d3b1866f0636'
).encode()).hexdigest()).encode()).hexdigest()
meta = self._download_json('https://api-app.kankanews.com/kankan/pc/getvideo',
video_id, query=params)['result']['video']
return {
'id': video_id,
'url': meta['videourl'],
'title': self._search_regex(r'g\.title\s*=\s*"([^"]+)"', webpage, 'title'),
'thumbnail': meta.get('titlepic'),
}