#!/usr/bin/python
import re
import urllib
import urllib.request #python3中urlopen、urlritrieve都在request库里面了,所以要导入此库
def htmlGet(url):
page = urllib.request.urlopen(url)
html = page.read()
return html
def imgGet(html):
res = r'src="(https.*?\.jpg)"'
imgre = re.compile(res)
imglist = re.findall(imgre,html.decode("utf-8")) #html不加后面的会报错typeerror,因为编码格式的变化,这里需要指定一下
x = 0
for i in imglist:
urllib.request.urlretrieve(i,"%s.jpg" % x)
x+=1
html = htmlGet("http://***")
imgGet(html)
网站题目:python3.7脚本---爬取网页图片
标题链接:
http://cdxtjz.cn/article/jipidp.html