etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-26 02:55:17 +00:00
Code Issues Projects Releases Wiki Activity

[ehow] improve minor bits

Browse source
This commit is contained in:
Philipp Hagemeister 2013-07-11 12:11:00 +02:00
parent 3fa9550837
commit 81082e046e
2 changed files with 17 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
youtube_dl/extractor/__init__.py
View file

@ -13,7 +13,7 @@
from .depositfiles import DepositFilesIE
from .dotsub import DotsubIE
from .dreisat import DreiSatIE
from .ehow import EhowIE
from .ehow import EHowIE
from .eighttracks import EightTracksIE
from .escapist import EscapistIE
from .facebook import FacebookIE

25
youtube_dl/extractor/ehow.py
View file

@ -1,10 +1,15 @@
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<id>[0-9]+)'
_TEST = {
u'url': u'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html',
u'file': u'12245069.flv',
@ -18,9 +23,9 @@ class EhowIE(InfoExtractor):
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'<meta property="og:image" content="(.+?)" />',
@ -28,11 +33,13 @@ def _real_extract(self, 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','')
webpage, u'Video title').replace(' | eHow', '')
description = self._search_regex(r'<meta property="og:description" content="(.+?)" />',
webpage, u'video description')
ext = final_url.split('.')[-1]
return [{
ext = determine_ext(final_url)
return {
'_type': 'video',
'id': video_id,
'url': final_url,
'ext': ext,
@ -40,5 +47,5 @@ def _real_extract(self, url):
'thumbnail': thumbnail_url,
'description': description,
'uploader': uploader,
}]
}