1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-24 09:16:50 +01:00

[quickvid] Add new extractor

This commit is contained in:
Philipp Hagemeister 2014-10-28 10:41:37 +01:00
parent 48a24ab746
commit 9ef55c5bbc
2 changed files with 52 additions and 0 deletions

View File

@ -294,6 +294,7 @@ from .pornoxo import PornoXOIE
from .promptfile import PromptFileIE
from .prosiebensat1 import ProSiebenSat1IE
from .pyvideo import PyvideoIE
from .quickvid import QuickVidIE
from .radiofrance import RadioFranceIE
from .rai import RaiIE
from .rbmaradio import RBMARadioIE

View File

@ -0,0 +1,51 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
compat_urlparse,
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,
},
}
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,
}