github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

Move FunnyOrDie into its own file

Browse source
This commit is contained in:
Philipp Hagemeister 2013-06-23 22:05:23 +02:00
parent 250f557872
commit 8f0578f0fc
2 changed files with 35 additions and 28 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

29
youtube_dl/InfoExtractors.py
View file

@ -27,6 +27,7 @@
from .extractor.depositfiles import DepositFilesIE
from .extractor.escapist import EscapistIE
from .extractor.facebook import FacebookIE
from .extractor.funnyordie import FunnyOrDieIE
from .extractor.gametrailers import GametrailersIE
from .extractor.generic import GenericIE
from .extractor.googleplus import GooglePlusIE
@ -197,34 +198,6 @@ def _real_extract(self, url):
offset += limit
return info
class FunnyOrDieIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'invalid URL: %s' % url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
video_url = self._html_search_regex(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"',
webpage, u'video URL', flags=re.DOTALL)
title = self._html_search_regex((r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>",
r'<title>(?P<title>[^<]+?)</title>'), webpage, 'title', flags=re.DOTALL)
video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
webpage, u'description', fatal=False, flags=re.DOTALL)
info = {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': title,
'description': video_description,
}
return [info]
class UstreamIE(InfoExtractor):

34
youtube_dl/extractor/funnyordie.py Normal file
View file

@ -0,0 +1,34 @@
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class FunnyOrDieIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
video_url = self._html_search_regex(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"',
webpage, u'video URL', flags=re.DOTALL)
title = self._html_search_regex((r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>",
r'<title>(?P<title>[^<]+?)</title>'), webpage, 'title', flags=re.DOTALL)
video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
webpage, u'description', fatal=False, flags=re.DOTALL)
info = {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': title,
'description': video_description,
}
return [info]