1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-24 03:01:53 +00:00
youtube-dl/youtube_dl/extractor/moniker.py
Philipp Hagemeister 1cc79574fc Fix imports and general cleanup
· 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· Fix some outdated tests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
2014-12-13 12:35:45 +01:00

69 lines
2 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
import os.path
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
class MonikerIE(InfoExtractor):
IE_DESC = 'allmyvideos.net and vidspot.net'
_VALID_URL = r'https?://(?:www\.)?(?:allmyvideos|vidspot)\.net/(?P<id>[a-zA-Z0-9_-]+)'
_TESTS = [{
'url': 'http://allmyvideos.net/jih3nce3x6wn',
'md5': '710883dee1bfc370ecf9fa6a89307c88',
'info_dict': {
'id': 'jih3nce3x6wn',
'ext': 'mp4',
'title': 'youtube-dl test video',
},
}, {
'url': 'http://vidspot.net/l2ngsmhs8ci5',
'md5': '710883dee1bfc370ecf9fa6a89307c88',
'info_dict': {
'id': 'l2ngsmhs8ci5',
'ext': 'mp4',
'title': 'youtube-dl test video',
},
}, {
'url': 'https://www.vidspot.net/l2ngsmhs8ci5',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
orig_webpage = self._download_webpage(url, video_id)
fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
data = dict(fields)
post = compat_urllib_parse.urlencode(data)
headers = {
b'Content-Type': b'application/x-www-form-urlencoded',
}
req = compat_urllib_request.Request(url, post, headers)
webpage = self._download_webpage(
req, video_id, note='Downloading video page ...')
title = os.path.splitext(data['fname'])[0]
# Could be several links with different quality
links = re.findall(r'"file" : "?(.+?)",', webpage)
# Assume the links are ordered in quality
formats = [{
'url': l,
'quality': i,
} for i, l in enumerate(links)]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'formats': formats,
}