1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-12-05 06:37:54 +01:00
youtube-dl/youtube_dl/extractor/vidbit.py

85 lines
2.8 KiB
Python
Raw Normal View History

2016-06-12 03:18:56 +02:00
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urlparse
2016-06-26 11:59:28 +02:00
from ..utils import (
int_or_none,
js_to_json,
remove_end,
unified_strdate,
)
2016-06-12 03:18:56 +02:00
class VidbitIE(InfoExtractor):
2016-06-26 11:59:28 +02:00
_VALID_URL = r'https?://(?:www\.)?vidbit\.co/(?:watch|embed)\?.*?\bv=(?P<id>[\da-zA-Z]+)'
_TESTS = [{
'url': 'http://www.vidbit.co/watch?v=jkL2yDOEq2',
'md5': '1a34b7f14defe3b8fafca9796892924d',
2016-06-12 03:18:56 +02:00
'info_dict': {
2016-06-26 11:59:28 +02:00
'id': 'jkL2yDOEq2',
2016-06-12 03:18:56 +02:00
'ext': 'mp4',
2016-06-26 11:59:28 +02:00
'title': 'Intro to VidBit',
'description': 'md5:5e0d6142eec00b766cbf114bfd3d16b7',
'thumbnail': r're:https?://.*\.jpg$',
2016-06-26 11:59:28 +02:00
'upload_date': '20160618',
'view_count': int,
'comment_count': int,
2016-06-12 03:18:56 +02:00
}
2016-06-26 11:59:28 +02:00
}, {
'url': 'http://www.vidbit.co/embed?v=jkL2yDOEq2&auto=0&water=0',
'only_matching': True,
}]
2016-06-12 03:18:56 +02:00
def _real_extract(self, url):
video_id = self._match_id(url)
2016-06-26 11:59:28 +02:00
webpage = self._download_webpage(
compat_urlparse.urljoin(url, '/watch?v=%s' % video_id), video_id)
video_url, title = [None] * 2
config = self._parse_json(self._search_regex(
r'(?s)\.setup\(({.+?})\);', webpage, 'setup', default='{}'),
video_id, transform_source=js_to_json)
if config:
if config.get('file'):
video_url = compat_urlparse.urljoin(url, config['file'])
title = config.get('title')
if not video_url:
video_url = compat_urlparse.urljoin(url, self._search_regex(
r'file\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'video URL', group='url'))
if not title:
title = remove_end(
self._html_search_regex(
(r'<h1>(.+?)</h1>', r'<title>(.+?)</title>'),
webpage, 'title', default=None) or self._og_search_title(webpage),
' - VidBit')
description = self._html_search_meta(
('description', 'og:description', 'twitter:description'),
webpage, 'description')
upload_date = unified_strdate(self._html_search_meta(
'datePublished', webpage, 'upload date'))
view_count = int_or_none(self._search_regex(
r'<strong>(\d+)</strong> views',
webpage, 'view count', fatal=False))
comment_count = int_or_none(self._search_regex(
r'id=["\']cmt_num["\'][^>]*>\((\d+)\)',
webpage, 'comment count', fatal=False))
2016-06-12 03:18:56 +02:00
return {
'id': video_id,
2016-06-26 11:59:28 +02:00
'url': video_url,
'title': title,
'description': description,
2016-06-12 03:18:56 +02:00
'thumbnail': self._og_search_thumbnail(webpage),
2016-06-26 11:59:28 +02:00
'upload_date': upload_date,
'view_count': view_count,
'comment_count': comment_count,
2016-06-12 03:18:56 +02:00
}