用Beautifulsoup 来爬取贴吧图片

Posted 2020-09-16 Braveliberty

import urllib.request
import bs4
import  re
import os

url="https://tieba.baidu.com/p/1988291937?fr=ala0&pstaala=1&tpl=5&isgod=0"
html=urllib.request.urlopen(url)
bsobj=bs4.BeautifulSoup(html)    #将整个网页的标签提取出来

namelist=bsobj.findAll(‘img‘,{‘class‘:‘BDE_Image‘})#找到img标签 并放到集合中

foder=‘c://hand‘   建立一个文件夹
os.mkdir(foder)
os.chdir(foder)

for name in namelist:
    addr=name.attrs[‘src‘] #迭代每一条标签src属性
    filename=addr.split(‘/‘)[-1]
    urllib.request.urlretrieve(addr,filename,None)


另一种迭代并保存网页图片的方式

 for name in namelist:
#     addr=name.attrs[‘src‘] #迭代每一条标签src属性    
#     filename=addr.split(‘/‘)[-1]
#     with open(filename,‘wb‘) as f:
#         response = urllib.request.urlopen(addr)    
#         img = response.read()
#         f.write(img)