爬取网站文章将图片保存到本地并将HTML的src属性更改到本地

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2018/11/5 15:06
# @Author  : jia.zhao
# @Desc    : 
# @File    : img_test.py
# @Software: PyCharm

import urllib.request
import re


def getHtml(url):
    # 通过urllib去请求
    page = urllib.request.urlopen(url)
    # 读取页面内容
    html = page.read()
    return html


def getImg(html):

    reg = r'src="(.+?\.jpg)" pic_ext'
    imgre = re.compile(reg)
    # Python3需要加的
    html = html.decode('utf-8')
    # 找到所有匹配项
    imglist = re.findall(imgre, html)

    x = 0
    # 循环
    for i in range(len(imglist)):
        # 保存图片
        # urllib.request.urlretrieve(imgurl, 'img/%s.jpg' % x)
        # 根据每个图片的src的内容进行替换
        html = re.sub(imglist[i], "G:/pachong/img/%s.jpg" % str(i), html)
        x += 1
    print(html)


html = getHtml("http://tieba.baidu.com/p/2460150866")

print(getImg(html))