youtube-dl/youtube_dl/extractor/nuvid.py

72 lines
2.5 KiB
Python
Raw Normal View History

2014-05-13 17:08:32 +09:00
from __future__ import unicode_literals
2014-05-12 19:48:40 +09:00
import re
from .common import InfoExtractor
2014-06-09 22:37:04 +09:00
from ..utils import (
parse_duration,
)
2014-05-12 19:48:40 +09:00
2014-05-13 17:08:32 +09:00
2014-05-12 19:48:40 +09:00
class NuvidIE(InfoExtractor):
_VALID_URL = r'https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)'
2014-05-12 19:48:40 +09:00
_TEST = {
2014-05-13 17:08:32 +09:00
'url': 'http://m.nuvid.com/video/1310741/',
'md5': 'eab207b7ac4fccfb4e23c86201f11277',
'info_dict': {
'id': '1310741',
'ext': 'mp4',
2014-06-09 22:37:04 +09:00
'title': 'Horny babes show their awesome bodeis and',
'duration': 129,
'age_limit': 18,
2014-05-12 19:48:40 +09:00
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
2014-05-12 19:48:40 +09:00
2016-04-28 18:51:20 +09:00
page_url = 'http://m.nuvid.com/video/%s' % video_id
webpage = self._download_webpage(
page_url, video_id, 'Downloading video page')
# When dwnld_speed exists and has a value larger than the MP4 file's
# bitrate, Nuvid returns the MP4 URL
# It's unit is 100bytes/millisecond, see mobile-nuvid-min.js for the algorithm
self._set_cookie('nuvid.com', 'dwnld_speed', '10.0')
mp4_webpage = self._download_webpage(
page_url, video_id, 'Downloading video page for MP4 format')
2014-05-13 17:08:32 +09:00
2016-04-28 18:51:20 +09:00
html5_video_re = r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']',
video_url = self._html_search_regex(html5_video_re, webpage, video_id)
mp4_video_url = self._html_search_regex(html5_video_re, mp4_webpage, video_id)
formats = [{
'url': video_url,
}]
if mp4_video_url != video_url:
2014-06-09 22:37:04 +09:00
formats.append({
2016-04-28 18:51:20 +09:00
'url': mp4_video_url,
2014-06-09 22:37:04 +09:00
})
2014-05-13 17:08:32 +09:00
2014-06-09 22:37:04 +09:00
title = self._html_search_regex(
2014-08-22 23:41:51 +09:00
[r'<span title="([^"]+)">',
2016-04-28 18:51:20 +09:00
r'<div class="thumb-holder video">\s*<h5[^>]*>([^<]+)</h5>',
r'<span[^>]+class="title_thumb">([^<]+)</span>'], webpage, 'title').strip()
2014-08-22 23:41:51 +09:00
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 22:37:04 +09:00
duration = parse_duration(self._html_search_regex(
2016-04-28 18:51:20 +09:00
[r'<i class="fa fa-clock-o"></i>\s*(\d{2}:\d{2})',
r'<span[^>]+class="view_time">([^<]+)</span>'], webpage, 'duration', fatal=False))
2014-05-13 17:08:32 +09:00
return {
'id': video_id,
'title': title,
2014-08-22 23:41:51 +09:00
'thumbnails': thumbnails,
'thumbnail': thumbnail,
2014-06-09 22:37:04 +09:00
'duration': duration,
2014-05-13 17:08:32 +09:00
'age_limit': 18,
2014-06-09 22:37:04 +09:00
'formats': formats,
2014-11-24 04:41:03 +09:00
}