1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-24 20:42:51 +08:00
youtube-dl/youtube_dl/extractor/quickvid.py
2015-06-25 16:40:29 +08:00

55 lines
1.7 KiB
Python

from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
)
from ..utils import (
determine_ext,
int_or_none,
)
class QuickVidIE(InfoExtractor):
_VALID_URL = r'https?://(www\.)?quickvid\.org/watch\.php\?v=(?P<id>[a-zA-Z_0-9-]+)'
_TEST = {
'url': 'http://quickvid.org/watch.php?v=sUQT3RCG8dx',
'md5': 'c0c72dd473f260c06c808a05d19acdc5',
'info_dict': {
'id': 'sUQT3RCG8dx',
'ext': 'mp4',
'title': 'Nick Offerman\'s Summer Reading Recap',
'thumbnail': 're:^https?://.*\.(?:png|jpg|gif)$',
'view_count': int,
},
'skip': 'Not accessible from Travis CI server',
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h2>(.*?)</h2>', webpage, 'title')
view_count = int_or_none(self._html_search_regex(
r'(?s)<div id="views">(.*?)</div>',
webpage, 'view count', fatal=False))
video_code = self._search_regex(
r'(?s)<video id="video"[^>]*>(.*?)</video>', webpage, 'video code')
formats = [
{
'url': compat_urlparse.urljoin(url, src),
'format_id': determine_ext(src, None),
} for src in re.findall('<source\s+src="([^"]+)"', video_code)
]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': self._og_search_thumbnail(webpage),
'view_count': view_count,
}