1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 12:38:05 +01:00
youtube-dl/youtube_dl/extractor/sexu.py

62 lines
1.9 KiB
Python
Raw Normal View History

2014-11-12 20:41:13 +01:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class SexuIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?sexu\.com/(?P<id>\d+)'
_TEST = {
'url': 'http://sexu.com/961791/',
'md5': 'ff615aca9691053c94f8f10d96cd7884',
'info_dict': {
'id': '961791',
'ext': 'mp4',
2014-11-13 14:02:53 +01:00
'title': 'md5:4d05a19a5fc049a63dbbaf05fb71d91b',
2014-11-12 20:41:13 +01:00
'description': 'md5:c5ed8625eb386855d5a7967bd7b77a54',
'categories': list, # NSFW
'thumbnail': 're:https?://.*\.jpg$',
'age_limit': 18,
}
}
def _real_extract(self, url):
2014-11-13 15:20:49 +01:00
video_id = self._match_id(url)
2014-11-12 20:41:13 +01:00
webpage = self._download_webpage(url, video_id)
2014-11-13 15:20:49 +01:00
quality_arr = self._search_regex(
r'sources:\s*\[([^\]]+)\]', webpage, 'forrmat string')
2014-11-12 20:41:13 +01:00
formats = [{
'url': fmt[0].replace('\\', ''),
'format_id': fmt[1],
'height': int(fmt[1][:3]),
} for fmt in re.findall(r'"file":"([^"]+)","label":"([^"]+)"', quality_arr)]
self._sort_formats(formats)
title = self._html_search_regex(
2014-11-13 15:20:49 +01:00
r'<title>([^<]+)\s*-\s*Sexu\.Com</title>', webpage, 'title')
2014-11-12 20:41:13 +01:00
2014-11-13 15:20:49 +01:00
description = self._html_search_meta(
'description', webpage, 'description')
2014-11-12 20:41:13 +01:00
thumbnail = self._html_search_regex(
r'image:\s*"([^"]+)"',
webpage, 'thumbnail', fatal=False)
2014-11-13 15:20:49 +01:00
categories_str = self._html_search_meta(
'keywords', webpage, 'categories')
2014-11-12 20:41:13 +01:00
categories = (
None if categories_str is None
else categories_str.split(','))
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'categories': categories,
'formats': formats,
'age_limit': 18,
}