slideshare.py (2132B)
1 from __future__ import unicode_literals 2 3 import re 4 import json 5 6 from .common import InfoExtractor 7 from ..compat import ( 8 compat_urlparse, 9 ) 10 from ..utils import ( 11 ExtractorError, 12 get_element_by_id, 13 ) 14 15 16 class SlideshareIE(InfoExtractor): 17 _VALID_URL = r'https?://(?:www\.)?slideshare\.net/[^/]+?/(?P<title>.+?)($|\?)' 18 19 _TEST = { 20 'url': 'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity', 21 'info_dict': { 22 'id': '25665706', 23 'ext': 'mp4', 24 'title': 'Managing Scale and Complexity', 25 '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 }, 27 } 28 29 def _real_extract(self, url): 30 mobj = re.match(self._VALID_URL, url) 31 page_title = mobj.group('title') 32 webpage = self._download_webpage(url, page_title) 33 slideshare_obj = self._search_regex( 34 r'\$\.extend\(.*?slideshare_object,\s*(\{.*?\})\);', 35 webpage, 'slideshare object') 36 info = json.loads(slideshare_obj) 37 if info['slideshow']['type'] != 'video': 38 raise ExtractorError('Webpage type is "%s": only video extraction is supported for Slideshare' % info['slideshow']['type'], expected=True) 39 40 doc = info['doc'] 41 bucket = info['jsplayer']['video_bucket'] 42 ext = info['jsplayer']['video_extension'] 43 video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext) 44 description = get_element_by_id('slideshow-description-paragraph', webpage) or self._html_search_regex( 45 r'(?s)<p[^>]+itemprop="description"[^>]*>(.+?)</p>', webpage, 46 'description', fatal=False) 47 48 return { 49 '_type': 'video', 50 'id': info['slideshow']['id'], 51 'title': info['slideshow']['title'], 52 'ext': ext, 53 'url': video_url, 54 'thumbnail': info['slideshow']['pin_image_url'], 55 'description': description.strip() if description else None, 56 }