1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-05 03:02:56 +01:00
youtube-dl/youtube_dl/extractor/nuvid.py

76 lines
2.6 KiB
Python
Raw Normal View History

2014-05-13 10:08:32 +02:00
from __future__ import unicode_literals
2014-05-12 12:48:40 +02:00
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_request,
)
2014-06-09 15:37:04 +02:00
from ..utils import (
parse_duration,
unified_strdate,
)
2014-05-12 12:48:40 +02:00
2014-05-13 10:08:32 +02:00
2014-05-12 12:48:40 +02:00
class NuvidIE(InfoExtractor):
_VALID_URL = r'https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)'
2014-05-12 12:48:40 +02:00
_TEST = {
2014-05-13 10:08:32 +02:00
'url': 'http://m.nuvid.com/video/1310741/',
'md5': 'eab207b7ac4fccfb4e23c86201f11277',
'info_dict': {
'id': '1310741',
'ext': 'mp4',
2014-06-09 15:37:04 +02:00
'title': 'Horny babes show their awesome bodeis and',
'duration': 129,
'upload_date': '20140508',
'age_limit': 18,
2014-05-12 12:48:40 +02:00
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
2014-05-12 12:48:40 +02:00
2014-06-09 15:37:04 +02:00
formats = []
2014-05-13 10:08:32 +02:00
2014-06-09 15:37:04 +02:00
for dwnld_speed, format_id in [(0, '3gp'), (5, 'mp4')]:
request = compat_urllib_request.Request(
'http://m.nuvid.com/play/%s' % video_id)
request.add_header('Cookie', 'skip_download_page=1; dwnld_speed=%d; adv_show=1' % dwnld_speed)
webpage = self._download_webpage(
request, video_id, 'Downloading %s page' % format_id)
video_url = self._html_search_regex(
2014-08-22 16:41:51 +02:00
r'<a\s+href="([^"]+)"\s+class="b_link">', webpage, '%s video URL' % format_id, fatal=False)
2014-06-09 15:37:04 +02:00
if not video_url:
continue
formats.append({
'url': video_url,
'format_id': format_id,
})
2014-05-13 10:08:32 +02:00
2014-06-09 15:37:04 +02:00
webpage = self._download_webpage(
'http://m.nuvid.com/video/%s' % video_id, video_id, 'Downloading video page')
title = self._html_search_regex(
2014-08-22 16:41:51 +02:00
[r'<span title="([^"]+)">',
r'<div class="thumb-holder video">\s*<h5[^>]*>([^<]+)</h5>'], webpage, 'title').strip()
thumbnails = [
{
'url': thumb_url,
} for thumb_url in re.findall(r'<img src="([^"]+)" alt="" />', webpage)
]
thumbnail = thumbnails[0]['url'] if thumbnails else None
2014-06-09 15:37:04 +02:00
duration = parse_duration(self._html_search_regex(
2014-08-22 16:41:51 +02:00
r'<i class="fa fa-clock-o"></i>\s*(\d{2}:\d{2})', webpage, 'duration', fatal=False))
2014-06-09 15:37:04 +02:00
upload_date = unified_strdate(self._html_search_regex(
2014-08-22 16:41:51 +02:00
r'<i class="fa fa-user"></i>\s*(\d{4}-\d{2}-\d{2})', webpage, 'upload date', fatal=False))
2014-05-13 10:08:32 +02:00
return {
'id': video_id,
'title': title,
2014-08-22 16:41:51 +02:00
'thumbnails': thumbnails,
'thumbnail': thumbnail,
2014-06-09 15:37:04 +02:00
'duration': duration,
'upload_date': upload_date,
2014-05-13 10:08:32 +02:00
'age_limit': 18,
2014-06-09 15:37:04 +02:00
'formats': formats,
2014-11-23 20:41:03 +01:00
}