X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fehow.py;h=2bb77aec6cb0d9ae2a7b4c6301c6deefc4548c57;hb=355e4fd07e7f9c0632d9d78415675f8b5cc3c2ce;hp=1844d8b00988ea73af1adedae1d27be4e700d960;hpb=f35b84c807265f10024e52309b5cac4ca95a9510;p=youtube-dl diff --git a/youtube_dl/extractor/ehow.py b/youtube_dl/extractor/ehow.py index 1844d8b00..2bb77aec6 100644 --- a/youtube_dl/extractor/ehow.py +++ b/youtube_dl/extractor/ehow.py @@ -1,42 +1,46 @@ import re -from ..utils import compat_urllib_parse + +from ..utils import ( + compat_urllib_parse, + determine_ext +) from .common import InfoExtractor -class EhowIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?ehow\.com/([^/]+)' +class EHowIE(InfoExtractor): + IE_NAME = u'eHow' + _VALID_URL = r'(?:https?://)?(?:www\.)?ehow\.com/[^/_?]*_(?P[0-9]+)' _TEST = { - u'url': u'http://www.break.com/video/when-girls-act-like-guys-2468056', - u'file': u'2468056.mp4', - u'md5': u'a3513fb1547fba4fb6cfac1bffc6c46b', + 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"When Girls Act Like D-Bags" + 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(1).split("_")[1] + video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - video_url = self._search_regex(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', + 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'', - webpage, u'thumbnail URL') uploader = self._search_regex(r'', webpage, u'uploader') - title = self._search_regex(r'', - webpage, u'Video title').replace(' | eHow','') - description = self._search_regex(r'', - webpage, u'video description') - ext = final_url.split('.')[-1] - return [{ + title = self._og_search_title(webpage).replace(' | eHow', '') + ext = determine_ext(final_url) + + return { + '_type': 'video', 'id': video_id, 'url': final_url, 'ext': ext, 'title': title, - 'thumbnail': thumbnail_url, - 'description': description, + 'thumbnail': self._og_search_thumbnail(webpage), + 'description': self._og_search_description(webpage), 'uploader': uploader, - }] + }