From 07463ea16249965fa4033e1383a8f51866ee851c Mon Sep 17 00:00:00 2001 From: =?utf8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Tue, 10 Sep 2013 11:19:58 +0200 Subject: [PATCH] Add an extractor for Slideshare (closes #1400) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/slideshare.py | 47 ++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) create mode 100644 youtube_dl/extractor/slideshare.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index fbe0b8cb7..bedb208fb 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -75,6 +75,7 @@ from .roxwel import RoxwelIE from .rtlnow import RTLnowIE from .sina import SinaIE from .slashdot import SlashdotIE +from .slideshare import SlideshareIE from .sohu import SohuIE from .soundcloud import SoundcloudIE, SoundcloudSetIE from .spiegel import SpiegelIE diff --git a/youtube_dl/extractor/slideshare.py b/youtube_dl/extractor/slideshare.py new file mode 100644 index 000000000..afc3001b5 --- /dev/null +++ b/youtube_dl/extractor/slideshare.py @@ -0,0 +1,47 @@ +import re +import json + +from .common import InfoExtractor +from ..utils import ( + compat_urlparse, + ExtractorError, +) + + +class SlideshareIE(InfoExtractor): + _VALID_URL = r'https?://www\.slideshare\.net/[^/]+?/(?P.+?)($|\?)' + + _TEST = { + u'url': u'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity', + u'file': u'25665706.mp4', + u'info_dict': { + u'title': u'Managing Scale and Complexity', + u'description': u'This was a keynote presentation at the NoSQL Now! 2013 Conference & Expo (http://www.nosqlnow.com). This presentation was given by Adrian Cockcroft from Netflix', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + page_title = mobj.group('title') + webpage = self._download_webpage(url, page_title) + slideshare_obj = self._search_regex( + r'var slideshare_object = ({.*?}); var user_info =', + webpage, u'slideshare object') + info = json.loads(slideshare_obj) + if info['slideshow']['type'] != u'video': + raise ExtractorError(u'Webpage type is "%s": only video extraction is supported for Slideshare' % info['slideshow']['type'], expected=True) + + doc = info['doc'] + bucket = info['jsplayer']['video_bucket'] + ext = info['jsplayer']['video_extension'] + video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext) + + return { + '_type': 'video', + 'id': info['slideshow']['id'], + 'title': info['slideshow']['title'], + 'ext': ext, + 'url': video_url, + 'thumbnail': info['slideshow']['pin_image_url'], + 'description': self._og_search_description(webpage), + } -- 2.22.2