]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ehow.py
Merge tag 'upstream/2013.08.17'
[youtubedl] / youtube_dl / extractor / ehow.py
1 import re
2
3 from ..utils import (
4 compat_urllib_parse,
5 determine_ext
6 )
7 from .common import InfoExtractor
8
9
10 class EHowIE(InfoExtractor):
11 IE_NAME = u'eHow'
12 _VALID_URL = r'(?:https?://)?(?:www\.)?ehow\.com/[^/_?]*_(?P<id>[0-9]+)'
13 _TEST = {
14 u'url': u'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html',
15 u'file': u'12245069.flv',
16 u'md5': u'9809b4e3f115ae2088440bcb4efbf371',
17 u'info_dict': {
18 u"title": u"Hardwood Flooring Basics",
19 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...",
20 u"uploader": u"Erick Nathan"
21 }
22 }
23
24 def _real_extract(self, url):
25 mobj = re.match(self._VALID_URL, url)
26 video_id = mobj.group('id')
27 webpage = self._download_webpage(url, video_id)
28 video_url = self._search_regex(r'(?:file|source)=(http[^\'"&]*)',
29 webpage, u'video URL')
30 final_url = compat_urllib_parse.unquote(video_url)
31 uploader = self._search_regex(r'<meta name="uploader" content="(.+?)" />',
32 webpage, u'uploader')
33 title = self._og_search_title(webpage).replace(' | eHow', '')
34 ext = determine_ext(final_url)
35
36 return {
37 '_type': 'video',
38 'id': video_id,
39 'url': final_url,
40 'ext': ext,
41 'title': title,
42 'thumbnail': self._og_search_thumbnail(webpage),
43 'description': self._og_search_description(webpage),
44 'uploader': uploader,
45 }
46