爬虫-爬取网站上的图片

思路：先访问网页，获得html，然后将网页中符合图片的地址的正则表达式的图片的下载下来

代码：

import urllib.request
import re

def open_url(url):
     req=urllib.request.Request(url)
     req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36')
     page=urllib.request.urlopen(req)
     html=page.read().decode('utf-8')
     return html


def get_img(html):
     p=r'<img class="BDE_Image" src="([^"]+\.jpg)"'
     #p=r'<img class="BDE_Image" pic_type="0" width="500" height="375" src="[^"]+\.jpg"'
     imglist=re.findall(p,html)
     '''
     for each in imglist:
          print(each)
      '''
     for each in imglist:
          filename=each.split("/")[-1]   #得到文件名
          urllib.request.urlretrieve(each,filename,None)#获得内容，自动下载地址
if __name__=='__main__':
     url="https://tieba.baidu.com/p/3563409202"
     #url="https://tieba.baidu.com/p/5137316528"
     html=open_url(url)
     get_img(html)