diff options
author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2014-03-27 21:23:02 +0100 |
---|---|---|
committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2014-03-27 21:23:02 +0100 |
commit | d26ebe990fd0e12365202db9948702be7c5edd02 (patch) | |
tree | d2e8802188e1ebb5a4142761de7de1bb93f524b1 /youtube_dl | |
parent | 28acf5500a05f01111f65adc84ba7c8e78fcd10b (diff) |
[ehow] Modernize
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/extractor/ehow.py | 43 |
1 files changed, 20 insertions, 23 deletions
diff --git a/youtube_dl/extractor/ehow.py b/youtube_dl/extractor/ehow.py index 2bb77aec6..f8f49a013 100644 --- a/youtube_dl/extractor/ehow.py +++ b/youtube_dl/extractor/ehow.py @@ -1,23 +1,25 @@ +from __future__ import unicode_literals + 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]+)' + IE_NAME = '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" + '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', } } @@ -26,21 +28,16 @@ class EHowIE(InfoExtractor): 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) - uploader = self._search_regex(r'<meta name="uploader" content="(.+?)" />', - webpage, u'uploader') + 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', '') - ext = determine_ext(final_url) return { - '_type': 'video', - 'id': video_id, - 'url': final_url, - 'ext': ext, - 'title': title, - 'thumbnail': self._og_search_thumbnail(webpage), + 'id': video_id, + 'url': final_url, + 'title': title, + 'thumbnail': self._og_search_thumbnail(webpage), 'description': self._og_search_description(webpage), - 'uploader': uploader, + 'uploader': uploader, } - |