yt-dlp/youtube_dl/extractor/hellporno.py

53 lines
1.7 KiB
Python
Raw Normal View History

2014-12-26 14:49:12 +00:00
from __future__ import unicode_literals
from .common import InfoExtractor
2014-12-29 09:38:07 +00:00
2014-12-26 14:49:12 +00:00
class HellPornoIE(InfoExtractor):
2014-12-29 09:38:07 +00:00
_VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<id>[^/]+)'
2014-12-26 14:49:12 +00:00
_TEST = {
'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
'md5': '1fee339c610d2049699ef2aa699439f1',
'info_dict': {
'id': '149116',
2014-12-29 09:38:07 +00:00
'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
2014-12-26 14:49:12 +00:00
'ext': 'mp4',
'title': 'Dixie is posing with naked ass very erotic',
'thumbnail': 're:https?://.*\.jpg$',
'age_limit': 18,
}
}
def _real_extract(self, url):
2014-12-29 09:38:07 +00:00
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
2014-12-26 14:49:12 +00:00
2014-12-29 09:38:07 +00:00
video_id = self._html_search_regex(
r'video_id:\s*\'([^\']+)\'', webpage, 'id')
2014-12-26 14:49:12 +00:00
2014-12-29 09:38:07 +00:00
ext = self._html_search_regex(
r'postfix:\s*\'([^\']+)\'', webpage, 'ext')[1:]
2014-12-26 14:49:12 +00:00
2014-12-29 09:38:07 +00:00
video_url = self._html_search_regex(
r'video_url:\s*\'([^\']+)\'', webpage, 'video_url')
2014-12-26 14:49:12 +00:00
title = self._html_search_regex(
r'<title>([^<]+)\s*-\s*Hell Porno</title>', webpage, 'title')
thumbnail = self._html_search_regex(
r'preview_url:\s*\'([^\']+)\'',
webpage, 'thumbnail', fatal=False)
2014-12-29 09:38:07 +00:00
categories = self._html_search_meta(
'keywords', webpage, 'categories', default='').split(',')
2014-12-26 14:49:12 +00:00
return {
'id': video_id,
2014-12-29 09:38:07 +00:00
'display_id': display_id,
2014-12-26 14:49:12 +00:00
'url': video_url,
'title': title,
'ext': ext,
'thumbnail': thumbnail,
'categories': categories,
'age_limit': 18,
}