yt-dlp/youtube_dl/extractor/pornhd.py

82 lines
2.7 KiB
Python
Raw Normal View History

2014-01-27 21:53:00 -05:00
from __future__ import unicode_literals
2013-12-13 22:22:53 -05:00
import re
2014-04-04 11:45:39 -04:00
import json
2013-12-13 22:22:53 -05:00
from .common import InfoExtractor
2014-04-04 11:45:39 -04:00
from ..utils import int_or_none
2013-12-13 22:22:53 -05:00
2013-12-15 23:10:42 -05:00
2013-12-13 22:22:53 -05:00
class PornHdIE(InfoExtractor):
2014-04-04 11:45:39 -04:00
_VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)'
2013-12-13 22:22:53 -05:00
_TEST = {
2014-01-27 21:53:00 -05:00
'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
2014-04-04 11:47:38 -04:00
'md5': '956b8ca569f7f4d8ec563e2c41598441',
2014-01-27 21:53:00 -05:00
'info_dict': {
2014-04-04 11:45:39 -04:00
'id': '1962',
'ext': 'mp4',
'title': 'Sierra loves doing laundry',
'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
'age_limit': 18,
2013-12-13 22:22:53 -05:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2014-04-04 11:45:39 -04:00
video_id = mobj.group('id')
2013-12-13 22:22:53 -05:00
webpage = self._download_webpage(url, video_id)
2014-04-04 11:45:39 -04:00
title = self._og_search_title(webpage)
TITLE_SUFFIX = ' porn HD Video | PornHD.com '
if title.endswith(TITLE_SUFFIX):
title = title[:-len(TITLE_SUFFIX)]
description = self._html_search_regex(
r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
view_count = int_or_none(self._html_search_regex(
r'(\d+) views </span>', webpage, 'view count', fatal=False))
formats = [
{
2014-04-04 16:22:30 -04:00
'url': format_url,
2014-04-04 11:45:39 -04:00
'ext': format.lower(),
'format_id': '%s-%s' % (format.lower(), quality.lower()),
'quality': 1 if quality.lower() == 'high' else 0,
2014-04-04 16:22:30 -04:00
} for format, quality, format_url in re.findall(
2014-04-04 11:45:39 -04:00
r'var __video([\da-zA-Z]+?)(Low|High)StreamUrl = \'(http://.+?)\?noProxy=1\'', webpage)
]
mobj = re.search(r'flashVars = (?P<flashvars>{.+?});', webpage)
if mobj:
flashvars = json.loads(mobj.group('flashvars'))
formats.extend([
{
'url': flashvars['hashlink'].replace('?noProxy=1', ''),
'ext': 'flv',
'format_id': 'flv-low',
'quality': 0,
},
{
'url': flashvars['hd'].replace('?noProxy=1', ''),
'ext': 'flv',
'format_id': 'flv-high',
'quality': 1,
}
])
thumbnail = flashvars['urlWallpaper']
else:
thumbnail = self._og_search_thumbnail(webpage)
2014-01-27 21:53:00 -05:00
2014-04-04 11:45:39 -04:00
self._sort_formats(formats)
2013-12-13 22:22:53 -05:00
return {
2013-12-15 23:10:42 -05:00
'id': video_id,
2014-04-04 11:45:39 -04:00
'title': title,
'description': description,
'thumbnail': thumbnail,
'view_count': view_count,
'formats': formats,
'age_limit': 18,
2013-12-13 22:22:53 -05:00
}