简单抓取图片

Posted 2020-10-08 __Phoebe

# -*- coding:utf-8 -*-
‘‘‘ 使用urllib和BeautifulSoup
   简单的实现从百度贴吧获取图片‘‘‘
from urllib.request import Request,urlopen,urlretrieve
import traceback
from bs4 import BeautifulSoup

# urlopen请求html
html=urlopen("http://tieba.baidu.com/f?kw=%E9%A3%8E%E6%99%AF&ie=utf-8&pn=0")
# BeautifulSoup解析网站
bsObj = BeautifulSoup(html,‘html.parser‘)
x=0
imagelist = bsObj.find_all("img")
for image in imagelist:
    try:

        # print("url:",image[‘src‘])
        if image[‘src‘]:
            print("url:", image[‘src‘])
            # urlretrieve远程下载并且保存在本地
            urlretrieve(image[‘src‘],‘F:\pic\%s.jpg‘%x)
            x+=1
    except Exception as e:
        print("e :",e)
        fs = traceback.format_exc()
        print("fs:",fs)