laudom/haruhi-dl
2
0
Fork 0
Code Issues 13 Pull requests Packages Projects Releases Wiki Activity

[slideshare] Fix description extraction and modernize

Browse source 
The ‘og:description’  property doesn’t contain the full description
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-02-09 14:22:56 +01:00
parent 524c2c716a
commit 1afe753462
1 changed files with 14 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
youtube_dl/extractor/slideshare.py
View file

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re import re
import json import json
@ -12,11 +14,12 @@ class SlideshareIE(InfoExtractor):
_VALID_URL = r'https?://www\.slideshare\.net/[^/]+?/(?P<title>.+?)($|\?)' _VALID_URL = r'https?://www\.slideshare\.net/[^/]+?/(?P<title>.+?)($|\?)'
_TEST = { _TEST = {
u'url': u'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity', 'url': 'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity',
u'file': u'25665706.mp4', 'info_dict': {
u'info_dict': { 'id': '25665706',
u'title': u'Managing Scale and Complexity', 'ext': 'mp4',
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', 'title': 'Managing Scale and Complexity',
'description': '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.',
}, },
} }
@ -26,15 +29,17 @@ class SlideshareIE(InfoExtractor):
webpage = self._download_webpage(url, page_title) webpage = self._download_webpage(url, page_title)
slideshare_obj = self._search_regex( slideshare_obj = self._search_regex(
r'var slideshare_object = ({.*?}); var user_info =', r'var slideshare_object = ({.*?}); var user_info =',
webpage, u'slideshare object') webpage, 'slideshare object')
info = json.loads(slideshare_obj) info = json.loads(slideshare_obj)
if info['slideshow']['type'] != u'video': if info['slideshow']['type'] != 'video':
raise ExtractorError(u'Webpage type is "%s": only video extraction is supported for Slideshare' % info['slideshow']['type'], expected=True) raise ExtractorError('Webpage type is "%s": only video extraction is supported for Slideshare' % info['slideshow']['type'], expected=True)
doc = info['doc'] doc = info['doc']
bucket = info['jsplayer']['video_bucket'] bucket = info['jsplayer']['video_bucket']
ext = info['jsplayer']['video_extension'] ext = info['jsplayer']['video_extension']
video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext) video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext)
description = self._html_search_regex(
r'<p class="description.*?"[^>]*>(.*?)</p>', webpage, 'description')
return { return {
'_type': 'video', '_type': 'video',
@ -43,5 +48,5 @@ class SlideshareIE(InfoExtractor):
'ext': ext, 'ext': ext,
'url': video_url, 'url': video_url,
'thumbnail': info['slideshow']['pin_image_url'], 'thumbnail': info['slideshow']['pin_image_url'],
'description': self._og_search_description(webpage), 'description': description,
} }