yt-dlp/youtube_dl/extractor/ehow.py

44 lines
1.5 KiB
Python
Raw Normal View History

2014-03-27 16:23:02 -04:00
from __future__ import unicode_literals
2013-07-11 05:25:14 -04:00
import re
2013-07-11 06:11:00 -04:00
from ..utils import (
compat_urllib_parse,
)
2013-07-11 05:25:14 -04:00
from .common import InfoExtractor
2013-07-11 06:11:00 -04:00
class EHowIE(InfoExtractor):
2014-03-27 16:23:02 -04:00
IE_NAME = 'eHow'
_VALID_URL = r'https?://(?:www\.)?ehow\.com/[^/_?]*_(?P<id>[0-9]+)'
2013-07-11 05:25:14 -04:00
_TEST = {
2014-03-27 16:23:02 -04:00
'url': 'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html',
'md5': '9809b4e3f115ae2088440bcb4efbf371',
'info_dict': {
'id': '12245069',
'ext': 'flv',
'title': 'Hardwood Flooring Basics',
'description': 'Hardwood flooring may be time consuming, but its ultimately a pretty straightforward concept. Learn about hardwood flooring basics with help from a hardware flooring business owner in this free video...',
'uploader': 'Erick Nathan',
2013-07-11 05:25:14 -04:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2013-07-11 06:11:00 -04:00
video_id = mobj.group('id')
2013-07-11 05:25:14 -04:00
webpage = self._download_webpage(url, video_id)
2013-07-11 06:11:00 -04:00
video_url = self._search_regex(r'(?:file|source)=(http[^\'"&]*)',
2014-03-27 16:23:02 -04:00
webpage, 'video URL')
final_url = compat_urllib_parse.unquote(video_url)
uploader = self._html_search_meta('uploader', webpage)
title = self._og_search_title(webpage).replace(' | eHow', '')
2013-07-11 06:11:00 -04:00
return {
2014-03-27 16:23:02 -04:00
'id': video_id,
'url': final_url,
'title': title,
'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage),
2014-03-27 16:23:02 -04:00
'uploader': uploader,
2013-07-11 06:11:00 -04:00
}