[nuvid] Improve extraction

This commit is contained in:
Sergey M․ 2014-06-09 20:37:04 +07:00
parent 09ffa08ba1
commit 3048e82a94

View File

@ -3,6 +3,11 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
parse_duration,
unified_strdate,
compat_urllib_request,
)
class NuvidIE(InfoExtractor): class NuvidIE(InfoExtractor):
@ -13,8 +18,10 @@ class NuvidIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '1310741', 'id': '1310741',
'ext': 'mp4', 'ext': 'mp4',
"title": "Horny babes show their awesome bodeis and", 'title': 'Horny babes show their awesome bodeis and',
"age_limit": 18, 'duration': 129,
'upload_date': '20140508',
'age_limit': 18,
} }
} }
@ -22,27 +29,41 @@ class NuvidIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
murl = url.replace('://www.', '://m.') formats = []
webpage = self._download_webpage(murl, video_id)
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(
r'<a href="([^"]+)"\s*>Continue to watch video', webpage, '%s video URL' % format_id, fatal=False)
if not video_url:
continue
formats.append({
'url': video_url,
'format_id': format_id,
})
webpage = self._download_webpage(
'http://m.nuvid.com/video/%s' % video_id, video_id, 'Downloading video page')
title = self._html_search_regex( title = self._html_search_regex(
r'<div class="title">\s+<h2[^>]*>([^<]+)</h2>', r'<div class="title">\s+<h2[^>]*>([^<]+)</h2>', webpage, 'title').strip()
webpage, 'title').strip()
url_end = self._html_search_regex(
r'href="(/[^"]+)"[^>]*data-link_type="mp4"',
webpage, 'video_url')
video_url = 'http://m.nuvid.com' + url_end
thumbnail = self._html_search_regex( thumbnail = self._html_search_regex(
r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"', r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"',
webpage, 'thumbnail URL', fatal=False) webpage, 'thumbnail URL', fatal=False)
duration = parse_duration(self._html_search_regex(
r'Length:\s*<span>(\d{2}:\d{2})</span>',webpage, 'duration', fatal=False))
upload_date = unified_strdate(self._html_search_regex(
r'Added:\s*<span>(\d{4}-\d{2}-\d{2})</span>', webpage, 'upload date', fatal=False))
return { return {
'id': video_id, 'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': title, 'title': title,
'thumbnail': thumbnail, 'thumbnail': 'http://m.nuvid.com/%s' % thumbnail,
'duration': duration,
'upload_date': upload_date,
'age_limit': 18, 'age_limit': 18,
} 'formats': formats,
}