mirror of
https://github.com/ytdl-org/youtube-dl
synced 2024-11-05 09:57:59 +09:00
52 lines
2.0 KiB
Python
52 lines
2.0 KiB
Python
import re
|
|
|
|
from ..utils import (
|
|
compat_urllib_parse,
|
|
determine_ext
|
|
)
|
|
from .common import InfoExtractor
|
|
|
|
|
|
class EHowIE(InfoExtractor):
|
|
IE_NAME = u'eHow'
|
|
_VALID_URL = r'(?:https?://)?(?:www\.)?ehow\.com/[^/_?]*_(?P<id>[0-9]+)'
|
|
_TEST = {
|
|
u'url': u'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html',
|
|
u'file': u'12245069.flv',
|
|
u'md5': u'9809b4e3f115ae2088440bcb4efbf371',
|
|
u'info_dict': {
|
|
u"title": u"Hardwood Flooring Basics",
|
|
u"description": u"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...",
|
|
u"uploader": u"Erick Nathan"
|
|
}
|
|
}
|
|
|
|
def _real_extract(self, url):
|
|
mobj = re.match(self._VALID_URL, url)
|
|
video_id = mobj.group('id')
|
|
webpage = self._download_webpage(url, video_id)
|
|
video_url = self._search_regex(r'(?:file|source)=(http[^\'"&]*)',
|
|
webpage, u'video URL')
|
|
final_url = compat_urllib_parse.unquote(video_url)
|
|
thumbnail_url = self._search_regex(r'<meta property="og:image" content="(.+?)" />',
|
|
webpage, u'thumbnail URL')
|
|
uploader = self._search_regex(r'<meta name="uploader" content="(.+?)" />',
|
|
webpage, u'uploader')
|
|
title = self._search_regex(r'<meta property="og:title" content="(.+?)" />',
|
|
webpage, u'Video title').replace(' | eHow', '')
|
|
description = self._search_regex(r'<meta property="og:description" content="(.+?)" />',
|
|
webpage, u'video description')
|
|
ext = determine_ext(final_url)
|
|
|
|
return {
|
|
'_type': 'video',
|
|
'id': video_id,
|
|
'url': final_url,
|
|
'ext': ext,
|
|
'title': title,
|
|
'thumbnail': thumbnail_url,
|
|
'description': description,
|
|
'uploader': uploader,
|
|
}
|
|
|