From: anovicecodemonkey Date: Thu, 26 Feb 2015 16:06:45 +0000 (+1030) Subject: [TheChiveIE] added support for TheChive.com (Closes #5016) X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=1a2313a6f2d83c9e0a5c0c25bf5a2e3167994dbe;p=youtube-dl [TheChiveIE] added support for TheChive.com (Closes #5016) --- diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index ddb9d6670..b064a3a7c 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -481,6 +481,7 @@ from .tenplay import TenPlayIE from .testurl import TestURLIE from .testtube import TestTubeIE from .tf1 import TF1IE +from .thechive import TheChiveIE from .theonion import TheOnionIE from .theplatform import ThePlatformIE from .thesixtyone import TheSixtyOneIE diff --git a/youtube_dl/extractor/thechive.py b/youtube_dl/extractor/thechive.py new file mode 100644 index 000000000..df1a7998d --- /dev/null +++ b/youtube_dl/extractor/thechive.py @@ -0,0 +1,60 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import unified_strdate + + + +class TheChiveIE(InfoExtractor): + _VALID_URL = r'http://(www\.)?thechive\.com/[^/]+/[^/]+/[^/]+/(?P[A-Za-z\-]+)' + _TEST = { + 'url': "http://thechive.com/2015/02/20/so-thats-what-a-set-of-redneck-bagpipes-sound-like-video/", + 'md5': "366710dda77cfa727bdef3523ba8466f", + 'info_dict': { + 'id': "so-thats-what-a-set-of-redneck-bagpipes-sound-like-video", + 'title': "So that's what a set of redneck bagpipes sound like... (Video)", + 'description': "Okay that was pretty good. Now play Freebird!...", + 'thumbnail': "https://thechive.files.wordpress.com/2015/02/0_07dghz0w-thumbnail2.jpg", + 'author': "Ben", + 'upload_date': "20150220", + 'ext': "mp4" + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('video_id') + webpage = self._download_webpage(url, video_id) + + title = self._og_search_title(webpage) + description = self._html_search_regex(r'(?s)', webpage, 'description') + thumbnail = self._og_search_thumbnail(webpage) + author = self._html_search_regex( + r'(?s)itemprop="author">(.+?)', webpage, 'author', fatal=False).capitalize() + upload_date = unified_strdate(self._html_search_regex( + r'(?s)itemprop="datePublished" datetime="(.+?)">', webpage, 'upload_date', fatal=False)) + + # Adapted from extractor/musicvault.py + VIDEO_URL_TEMPLATE = 'http://cdnapi.kaltura.com/p/%(uid)s/sp/%(wid)s/playManifest/entryId/%(entry_id)s/format/url/protocol/http' + + kaltura_id = self._search_regex( + r'entry_id=([^"]+)', + webpage, 'kaltura ID') + video_url = VIDEO_URL_TEMPLATE % { + 'entry_id': kaltura_id, + 'wid': self._search_regex(r'partner_id/([0-9]+)\?', webpage, 'wid'), + 'uid': self._search_regex(r'uiconf_id/([0-9]+)/', webpage, 'uid'), + } + + return { + 'url': video_url, + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'author': author, + 'upload_date': upload_date, + 'ext': 'mp4' + } \ No newline at end of file