mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-16 09:49:26 +01:00
1cc79574fc
· Import from compat what comes from compat. Yes, some names are available in utils too, but that's an implementation detail. · Use _match_id consistently whenever possible · Fix some outdated tests · Use consistent valid URL (always match the whole protocol, no ^ at start required) · Use modern test definitions
64 lines
1.9 KiB
Python
64 lines
1.9 KiB
Python
# -*- coding: utf-8 -*-
|
|
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import (
|
|
compat_urllib_parse,
|
|
compat_urllib_request,
|
|
)
|
|
|
|
|
|
class VodlockerIE(InfoExtractor):
|
|
_VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
|
|
|
|
_TESTS = [{
|
|
'url': 'http://vodlocker.com/e8wvyzz4sl42',
|
|
'md5': 'ce0c2d18fa0735f1bd91b69b0e54aacf',
|
|
'info_dict': {
|
|
'id': 'e8wvyzz4sl42',
|
|
'ext': 'mp4',
|
|
'title': 'Germany vs Brazil',
|
|
'thumbnail': 're:http://.*\.jpg',
|
|
},
|
|
}]
|
|
|
|
def _real_extract(self, url):
|
|
video_id = self._match_id(url)
|
|
webpage = self._download_webpage(url, video_id)
|
|
|
|
fields = dict(re.findall(r'''(?x)<input\s+
|
|
type="hidden"\s+
|
|
name="([^"]+)"\s+
|
|
(?:id="[^"]+"\s+)?
|
|
value="([^"]*)"
|
|
''', webpage))
|
|
|
|
if fields['op'] == 'download1':
|
|
self._sleep(3, video_id) # they do detect when requests happen too fast!
|
|
post = compat_urllib_parse.urlencode(fields)
|
|
req = compat_urllib_request.Request(url, post)
|
|
req.add_header('Content-type', 'application/x-www-form-urlencoded')
|
|
webpage = self._download_webpage(
|
|
req, video_id, 'Downloading video page')
|
|
|
|
title = self._search_regex(
|
|
r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title')
|
|
thumbnail = self._search_regex(
|
|
r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail')
|
|
url = self._search_regex(
|
|
r'file:\s*"(http[^\"]+)",', webpage, 'file url')
|
|
|
|
formats = [{
|
|
'format_id': 'sd',
|
|
'url': url,
|
|
}]
|
|
|
|
return {
|
|
'id': video_id,
|
|
'title': title,
|
|
'thumbnail': thumbnail,
|
|
'formats': formats,
|
|
}
|