A simple script to download SlideShare slides (as images)

slideshare_downloader.py

import requests
import scrapy
import os.path

presentationLink = '...'
presentationId = presentationLink.split("/")[-1]

userAgent = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36'
presentationResponse = requests.get(presentationLink, headers = {'User-agent': userAgent})

if presentationResponse.status_code != 200:
    print("ERROR " + str(presentationResponse.status_code) + " while scrping " + presentationLink)
else:
    presentationContet = presentationResponse.text
    presentationSelector = scrapy.Selector(text=presentationContet)
    slidesLinks = presentationSelector.xpath('//*[@id="svPlayerId"]/div[1]/div[2]').css('section > img').xpath('@data-full').getall()    

presentationOutPath = os.path.dirname(__file__) + '/' + presentationId
if not os.path.exists(presentationOutPath):
    os.makedirs(presentationOutPath)

for slideNumber,slideLink in enumerate(slidesLinks):
    slideReturn = requests.get(slideLink).content
    with open(presentationOutPath + '/slide' + str(slideNumber) + '.jpg', 'wb') as slideFile:
        slideFile.write(slideReturn)