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

72 lines
2.4 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
from ..utils import (
int_or_none,
js_to_json,
qualities,
)
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):
_VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
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',
'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
2014-04-04 17:45:39 +02:00
'ext': 'mp4',
'title': 'Sierra loves doing laundry',
'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
'thumbnail': 're:^https?://.*\.jpg',
'view_count': int,
2014-04-04 17:45:39 +02:00
'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')
display_id = mobj.group('display_id')
2013-12-14 04:22:53 +01:00
webpage = self._download_webpage(url, display_id or video_id)
2013-12-14 04:22:53 +01:00
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))
thumbnail = self._search_regex(
r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
2014-04-04 17:45:39 +02:00
quality = qualities(['sd', 'hd'])
sources = json.loads(js_to_json(self._search_regex(
2015-02-10 03:41:31 +01:00
r"(?s)'sources'\s*:\s*(\{.+?\})\s*\}[;,)]",
webpage, 'sources')))
formats = []
2015-02-10 03:41:31 +01:00
for qname, video_url in sources.items():
if not video_url:
continue
formats.append({
'url': video_url,
'format_id': qname,
'quality': quality(qname),
})
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,
'display_id': display_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
}