0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-14 01:05:06 +00:00
yt-dlp/yt_dlp/extractor/vshare.py

58 lines
1.9 KiB
Python
Raw Normal View History

2017-04-03 20:05:18 +00:00
from .common import InfoExtractor
from ..utils import ExtractorError, decode_packed_codes
2017-04-03 20:05:18 +00:00
class VShareIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?vshare\.io/[dv]/(?P<id>[^/?#&]+)'
_EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?vshare\.io/v/[^/?#&]+)']
2017-04-03 20:05:18 +00:00
_TESTS = [{
'url': 'https://vshare.io/d/0f64ce6',
'md5': '17b39f55b5497ae8b59f5fbce8e35886',
2017-04-03 20:05:18 +00:00
'info_dict': {
'id': '0f64ce6',
'title': 'vl14062007715967',
'ext': 'mp4',
}
}, {
'url': 'https://vshare.io/v/0f64ce6/width-650/height-430/1',
'only_matching': True,
}]
def _extract_packed(self, webpage):
packed = self._search_regex(
r'(eval\(function.+)', webpage, 'packed code')
unpacked = decode_packed_codes(packed)
2023-07-06 14:39:42 +00:00
digits = self._search_regex(r'\[([\d,]+)\]', unpacked, 'digits')
digits = [int(digit) for digit in digits.split(',')]
key_digit = self._search_regex(
r'fromCharCode\(.+?(\d+)\)}', unpacked, 'key digit')
chars = [chr(d - int(key_digit)) for d in digits]
return ''.join(chars)
2017-04-03 20:05:18 +00:00
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'https://vshare.io/v/%s/width-650/height-430/1' % video_id,
video_id, headers={'Referer': url})
2017-04-03 20:05:18 +00:00
2022-04-04 08:27:35 +00:00
title = self._html_extract_title(webpage)
title = title.split(' - ')[0]
2017-04-03 20:05:18 +00:00
error = self._html_search_regex(
r'(?s)<div[^>]+\bclass=["\']xxx-error[^>]+>(.+?)</div', webpage,
'error', default=None)
if error:
raise ExtractorError(error, expected=True)
info = self._parse_html5_media_entries(
url, '<video>%s</video>' % self._extract_packed(webpage),
video_id)[0]
info.update({
2017-04-03 20:05:18 +00:00
'id': video_id,
'title': title,
})
return info