2014-09-16 11:48:53 -07:00
|
|
|
# coding: utf-8
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
2014-09-16 13:56:31 -07:00
|
|
|
import os.path
|
2014-09-16 11:48:53 -07:00
|
|
|
import re
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
2014-12-13 03:24:42 -08:00
|
|
|
from ..compat import (
|
2014-09-16 11:48:53 -07:00
|
|
|
compat_urllib_parse,
|
|
|
|
compat_urllib_request,
|
|
|
|
)
|
2015-08-15 00:17:27 -07:00
|
|
|
from ..utils import (
|
|
|
|
ExtractorError,
|
|
|
|
remove_start,
|
|
|
|
)
|
2014-09-16 11:48:53 -07:00
|
|
|
|
|
|
|
|
2014-09-18 12:37:09 -07:00
|
|
|
class MonikerIE(InfoExtractor):
|
2014-09-18 09:54:03 -07:00
|
|
|
IE_DESC = 'allmyvideos.net and vidspot.net'
|
2015-10-29 09:44:01 -07:00
|
|
|
_VALID_URL = r'https?://(?:www\.)?(?:allmyvideos|vidspot)\.net/(?:(?:2|v)/v-)?(?P<id>[a-zA-Z0-9_-]+)'
|
2014-09-16 11:48:53 -07:00
|
|
|
|
2014-09-18 09:54:03 -07:00
|
|
|
_TESTS = [{
|
2014-09-16 11:48:53 -07:00
|
|
|
'url': 'http://allmyvideos.net/jih3nce3x6wn',
|
2014-09-16 13:56:31 -07:00
|
|
|
'md5': '710883dee1bfc370ecf9fa6a89307c88',
|
2014-09-16 11:48:53 -07:00
|
|
|
'info_dict': {
|
|
|
|
'id': 'jih3nce3x6wn',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'title': 'youtube-dl test video',
|
|
|
|
},
|
2015-08-15 00:17:27 -07:00
|
|
|
}, {
|
|
|
|
'url': 'http://allmyvideos.net/embed-jih3nce3x6wn',
|
|
|
|
'md5': '710883dee1bfc370ecf9fa6a89307c88',
|
|
|
|
'info_dict': {
|
|
|
|
'id': 'jih3nce3x6wn',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'title': 'youtube-dl test video',
|
|
|
|
},
|
2014-09-18 09:54:03 -07:00
|
|
|
}, {
|
|
|
|
'url': 'http://vidspot.net/l2ngsmhs8ci5',
|
|
|
|
'md5': '710883dee1bfc370ecf9fa6a89307c88',
|
|
|
|
'info_dict': {
|
|
|
|
'id': 'l2ngsmhs8ci5',
|
|
|
|
'ext': 'mp4',
|
|
|
|
'title': 'youtube-dl test video',
|
|
|
|
},
|
2014-09-18 09:56:02 -07:00
|
|
|
}, {
|
|
|
|
'url': 'https://www.vidspot.net/l2ngsmhs8ci5',
|
|
|
|
'only_matching': True,
|
2014-09-18 09:54:03 -07:00
|
|
|
}]
|
2014-09-16 11:48:53 -07:00
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2015-08-15 00:17:27 -07:00
|
|
|
orig_video_id = self._match_id(url)
|
|
|
|
video_id = remove_start(orig_video_id, 'embed-')
|
|
|
|
url = url.replace(orig_video_id, video_id)
|
|
|
|
assert re.match(self._VALID_URL, url) is not None
|
2014-09-16 12:05:50 -07:00
|
|
|
orig_webpage = self._download_webpage(url, video_id)
|
2014-12-13 03:24:42 -08:00
|
|
|
|
2015-04-27 10:46:16 -07:00
|
|
|
if '>File Not Found<' in orig_webpage:
|
|
|
|
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
|
|
|
|
|
2015-04-27 10:44:05 -07:00
|
|
|
error = self._search_regex(
|
|
|
|
r'class="err">([^<]+)<', orig_webpage, 'error', default=None)
|
|
|
|
if error:
|
|
|
|
raise ExtractorError(
|
|
|
|
'%s returned error: %s' % (self.IE_NAME, error), expected=True)
|
|
|
|
|
2015-10-29 09:44:01 -07:00
|
|
|
builtin_url = self._search_regex(
|
|
|
|
r'<iframe[^>]+src=(["\'])(?P<url>.+?/builtin-.+?)\1',
|
|
|
|
orig_webpage, 'builtin URL', default=None, group='url')
|
2014-09-16 12:05:50 -07:00
|
|
|
|
2015-10-29 09:44:01 -07:00
|
|
|
if builtin_url:
|
|
|
|
req = compat_urllib_request.Request(builtin_url)
|
|
|
|
req.add_header('Referer', url)
|
|
|
|
webpage = self._download_webpage(req, video_id, 'Downloading builtin page')
|
|
|
|
title = self._og_search_title(orig_webpage).strip()
|
|
|
|
description = self._og_search_description(orig_webpage).strip()
|
|
|
|
else:
|
|
|
|
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 ...')
|
2014-09-16 13:56:31 -07:00
|
|
|
|
2015-10-29 09:44:01 -07:00
|
|
|
title = os.path.splitext(data['fname'])[0]
|
|
|
|
description = None
|
2014-09-16 12:05:50 -07:00
|
|
|
|
2014-11-23 11:41:03 -08:00
|
|
|
# Could be several links with different quality
|
2014-09-16 12:05:50 -07:00
|
|
|
links = re.findall(r'"file" : "?(.+?)",', webpage)
|
2014-09-16 13:56:31 -07:00
|
|
|
# Assume the links are ordered in quality
|
|
|
|
formats = [{
|
|
|
|
'url': l,
|
|
|
|
'quality': i,
|
|
|
|
} for i, l in enumerate(links)]
|
|
|
|
self._sort_formats(formats)
|
2014-09-16 12:05:50 -07:00
|
|
|
|
|
|
|
return {
|
|
|
|
'id': video_id,
|
2014-09-16 13:56:31 -07:00
|
|
|
'title': title,
|
2015-10-29 09:44:01 -07:00
|
|
|
'description': description,
|
2014-09-16 13:56:31 -07:00
|
|
|
'formats': formats,
|
|
|
|
}
|