X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fehow.py;h=b766e17f26a9e79d654d4b160fa8f98f5f21503f;hb=9e1a5b845586a0a5431fb72467142046d8571e6f;hp=1844d8b00988ea73af1adedae1d27be4e700d960;hpb=f35b84c807265f10024e52309b5cac4ca95a9510;p=youtube-dl diff --git a/youtube_dl/extractor/ehow.py b/youtube_dl/extractor/ehow.py index 1844d8b00..b766e17f2 100644 --- a/youtube_dl/extractor/ehow.py +++ b/youtube_dl/extractor/ehow.py @@ -1,42 +1,43 @@ +from __future__ import unicode_literals + import re -from ..utils import compat_urllib_parse + +from ..utils import ( + compat_urllib_parse, +) from .common import InfoExtractor -class EhowIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?ehow\.com/([^/]+)' +class EHowIE(InfoExtractor): + IE_NAME = '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'info_dict': { - u"title": u"When Girls Act Like D-Bags" + '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', } } 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[^\'"&]*)', - 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 [{ - 'id': video_id, - 'url': final_url, - 'ext': ext, - 'title': title, - 'thumbnail': thumbnail_url, - 'description': description, - 'uploader': uploader, - }] + video_url = self._search_regex(r'(?:file|source)=(http[^\'"&]*)', + 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', '') + return { + 'id': video_id, + 'url': final_url, + 'title': title, + 'thumbnail': self._og_search_thumbnail(webpage), + 'description': self._og_search_description(webpage), + 'uploader': uploader, + }