yt_dlp/extractor/slideshare.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_urlparse,
   8 )
   9 from ..utils import (
  10     ExtractorError,
  11     get_element_by_id,
  12 )
  13
  14
  15 class SlideshareIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?slideshare\.net/[^/]+?/(?P<title>.+?)($|\?)'
  17
  18     _TEST = {
  19         'url': 'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity',
  20         'info_dict': {
  21             'id': '25665706',
  22             'ext': 'mp4',
  23             'title': 'Managing Scale and Complexity',
  24             '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.',
  25         },
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = self._match_valid_url(url)
  30         page_title = mobj.group('title')
  31         webpage = self._download_webpage(url, page_title)
  32         slideshare_obj = self._search_regex(
  33             r'\$\.extend\(.*?slideshare_object,\s*(\{.*?\})\);',
  34             webpage, 'slideshare object')
  35         info = json.loads(slideshare_obj)
  36         if info['slideshow']['type'] != 'video':
  37             raise ExtractorError('Webpage type is "%s": only video extraction is supported for Slideshare' % info['slideshow']['type'], expected=True)
  38
  39         doc = info['doc']
  40         bucket = info['jsplayer']['video_bucket']
  41         ext = info['jsplayer']['video_extension']
  42         video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext)
  43         description = get_element_by_id('slideshow-description-paragraph', webpage) or self._html_search_regex(
  44             r'(?s)<p[^>]+itemprop="description"[^>]*>(.+?)</p>', webpage,
  45             'description', fatal=False)
  46
  47         return {
  48             '_type': 'video',
  49             'id': info['slideshow']['id'],
  50             'title': info['slideshow']['title'],
  51             'ext': ext,
  52             'url': video_url,
  53             'thumbnail': info['slideshow']['pin_image_url'],
  54             'description': description.strip() if description else None,
  55         }