0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-04 04:07:26 +00:00
yt-dlp/yt_dlp/extractor/slideshare.py

52 lines
2 KiB
Python
Raw Normal View History

import json
import urllib.parse
from .common import InfoExtractor
from ..utils import (
ExtractorError,
get_element_by_id,
)
class SlideshareIE(InfoExtractor):
2016-09-08 11:29:05 +00:00
_VALID_URL = r'https?://(?:www\.)?slideshare\.net/[^/]+?/(?P<title>.+?)($|\?)'
_TEST = {
'url': 'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity',
'info_dict': {
'id': '25665706',
'ext': 'mp4',
'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.',
},
}
def _real_extract(self, url):
mobj = self._match_valid_url(url)
page_title = mobj.group('title')
webpage = self._download_webpage(url, page_title)
slideshare_obj = self._search_regex(
2017-07-14 15:11:07 +00:00
r'\$\.extend\(.*?slideshare_object,\s*(\{.*?\})\);',
webpage, 'slideshare object')
info = json.loads(slideshare_obj)
if info['slideshow']['type'] != 'video':
raise ExtractorError('Webpage type is "{}": only video extraction is supported for Slideshare'.format(info['slideshow']['type']), expected=True)
doc = info['doc']
bucket = info['jsplayer']['video_bucket']
ext = info['jsplayer']['video_extension']
video_url = urllib.parse.urljoin(bucket, doc + '-SD.' + ext)
description = get_element_by_id('slideshow-description-paragraph', webpage) or self._html_search_regex(
2014-12-31 18:26:19 +00:00
r'(?s)<p[^>]+itemprop="description"[^>]*>(.+?)</p>', webpage,
2014-04-11 00:19:15 +00:00
'description', fatal=False)
return {
'_type': 'video',
'id': info['slideshow']['id'],
'title': info['slideshow']['title'],
'ext': ext,
'url': video_url,
'thumbnail': info['slideshow']['pin_image_url'],
'description': description.strip() if description else None,
}