yt_dlp/extractor/slideshare.py

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