python爬百度文库课件

库:re;selenium;requests

 

源码:

from selenium import webdriver
import re
import requests
def open_img(items):
    for item in items:
        item = re.sub('&','&',item)
        rsp =requests.get(item)
        yield rsp.content
   

url ='https://wenku.baidu.com/view/4e3d35d969eae009581becd5.html?from=search'    #可修改成别的ppt网址
browser =webdriver.Chrome()
try:
    browser.get(url)
    html =browser.page_source
    pattern =re.compile('<div class="ppt-page-item.*?src="(.*?)".*?>',re.S)
    items =re.findall(pattern,html)
    n =0
    for i in open_img(items):
        with open('%d.jpeg'%n,'wb') as file:
            file.write(i)·
            n +=1
            print('第%d张图片下载完成'%n)
  
finally:
    browser.close()
input()
 
posted @ 2018-09-17 15:41  vlj  阅读(494)  评论(0编辑  收藏  举报