python-爬图小样

python-爬某页面图

注意：python3+版本与python2有一定区别，需要注意多点。

#! /usr/bin/env python3.5.4
# coding=utf-8
# 爬百度某贴吧页面图

import urllib.request
import re


def get_html(url):
    page = urllib.request.urlopen(url)
    htmla = page.read()
    return htmla


def get_img(htmlb):
    reg = r'src="(.+?\.jpg)" pic_ext'
    imgre = re.compile(reg)
    htmlb = htmlb.decode('utf-8')  # python3.5特性,必须添加
    imglist = re.findall(imgre, htmlb)
    x = 0
    for imgurl in imglist:
        urllib.request.urlretrieve(imgurl, '%s.jpg' % x)
        x += 1

htmlb = get_html("http://tieba.baidu.com/p/2460150866")

# 结尾要加换行符
print(get_img(htmlb))