ytdl-nightly/youtube_dl/extractor/pornhd.py

75 lines
2.6 KiB
Python
Raw Normal View History

2014-01-28 03:53:00 +01:00
from __future__ import unicode_literals
2013-12-14 04:22:53 +01:00
import re
2014-04-04 17:45:39 +02:00
import json
2013-12-14 04:22:53 +01:00
from .common import InfoExtractor
2014-04-04 17:45:39 +02:00
from ..utils import int_or_none
2013-12-14 04:22:53 +01:00
2013-12-16 05:10:42 +01:00
2013-12-14 04:22:53 +01:00
class PornHdIE(InfoExtractor):
2014-04-04 17:45:39 +02:00
_VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)'
2013-12-14 04:22:53 +01:00
_TEST = {
2014-01-28 03:53:00 +01:00
'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
2014-04-04 17:47:38 +02:00
'md5': '956b8ca569f7f4d8ec563e2c41598441',
2014-01-28 03:53:00 +01:00
'info_dict': {
2014-04-04 17:45:39 +02:00
'id': '1962',
'ext': 'mp4',
'title': 'Sierra loves doing laundry',
'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
'age_limit': 18,
2013-12-14 04:22:53 +01:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2014-04-04 17:45:39 +02:00
video_id = mobj.group('id')
2013-12-14 04:22:53 +01:00
webpage = self._download_webpage(url, video_id)
2014-09-13 16:45:53 +02:00
title = self._html_search_regex(
r'<title>(.+) porn HD.+?</title>', webpage, 'title')
2014-04-04 17:45:39 +02:00
description = self._html_search_regex(
r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
view_count = int_or_none(self._html_search_regex(
2014-09-13 16:45:53 +02:00
r'(\d+) views\s*</span>', webpage, 'view count', fatal=False))
2014-04-04 17:45:39 +02:00
2014-09-13 16:45:53 +02:00
videos = re.findall(
r'var __video([\da-zA-Z]+?)(Low|High)StreamUrl = \'(http://.+?)\?noProxy=1\'', webpage)
2014-04-04 17:45:39 +02:00
mobj = re.search(r'flashVars = (?P<flashvars>{.+?});', webpage)
if mobj:
flashvars = json.loads(mobj.group('flashvars'))
2014-09-13 16:45:53 +02:00
for key, quality in [('hashlink', 'low'), ('hd', 'high')]:
redirect_url = flashvars.get(key)
if redirect_url:
videos.append(('flv', quality, redirect_url))
2014-04-04 17:45:39 +02:00
thumbnail = flashvars['urlWallpaper']
else:
thumbnail = self._og_search_thumbnail(webpage)
2014-01-28 03:53:00 +01:00
2014-09-13 16:45:53 +02:00
formats = []
for format_, quality, redirect_url in videos:
format_id = '%s-%s' % (format_.lower(), quality.lower())
video_url = self._download_webpage(
redirect_url, video_id, 'Downloading %s video link' % format_id, fatal=False)
if not video_url:
continue
formats.append({
'url': video_url,
'ext': format_.lower(),
'format_id': format_id,
'quality': 1 if quality.lower() == 'high' else 0,
})
2014-04-04 17:45:39 +02:00
self._sort_formats(formats)
2013-12-14 04:22:53 +01:00
return {
2013-12-16 05:10:42 +01:00
'id': video_id,
2014-04-04 17:45:39 +02:00
'title': title,
'description': description,
'thumbnail': thumbnail,
'view_count': view_count,
'formats': formats,
'age_limit': 18,
2013-12-14 04:22:53 +01:00
}