urllib/request爬取百度贴吧图片

import re
from urllib import request,parse
import os

# 突破下载函数
def download(img_html):
    # 正则匹配图片url
    img_url = re.findall('<img class="BDE_Image" src="(.*?)"',img_html,re.S)
    # print(img_url)
    # 判断文件夹不存在就创建
    if not os.path.exists('tieba'):
        os.mkdir('tieba')
    # 遍历所有突破url
    for i in img_url:
        # 切割突破文件名
        img_name = i.split('/')[-1]
        print(i)
        # 保存图片
        request.urlretrieve(i,'./tieba/'+str(img_name))


def pn():
    kw = input('输入贴吧名字')
    # 转换为URL编码
    kw = parse.quote(kw)
    # 拼接url
    base_url = 'https://tieba.baidu.com/f?kw='+kw
    # print(base_url)
    # 发送请求
    response = request.urlopen(base_url)
    # 转换格式
    html = response.read().decode('utf-8')
    # 获取最后一页的数据
    url = re.findall(r'pn=(\d+)',html)
    # 总页数 获取最后一个pn算出总页数
    p = int(int(url[-1])/50+1)
    print('总页数为'+str(p))
    start = input('输入开始页：')
    end = input('输入结束页：')
    # 遍历所有列表页url
    for i in range(int(start)-1,int(end)):
        # 拼接列表url
        pn_url = base_url+'&pn='+str(i*50)
        print(pn_url)
        # 发送详情页请求
        response = request.urlopen(pn_url)
        # 转换格式
        html = (response.read().decode('utf-8'))
        # 匹配详情页url
        pat = re.findall(r'href="(/p/\d*)',html)
        print(pat)
        # 遍历所有详情页url
        for j in pat:
            deta_url = 'http://tieba.baidu.com'+j
            print(deta_url)
            response = request.urlopen(deta_url)
            # deta_html = response.read().decode('utf-8')
            img_html = response.read().decode('utf-8','ignore')
            download(img_html)
            # break




if __name__=='__main__':
    pn()