爬取酷漫网漫画

# -*- coding: utf-8 -*-
# @Time    : 2019/6/11 9:47
# @Author  : wujf
# @Email   : [email protected]
# @File    : 斗罗大陆2.py
# @Software: PyCharm


import re
import requests
import urllib.request
from bs4 import BeautifulSoup

urls = ['http://www.kuman.com/mh-1003692/{}/'.format(str(i)) for i in range(1,22)]
for url in urls:

    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}
    r =requests.get(url,headers =headers,timeout= 5)
    # r.raise_for_status()

    r.encoding = r.apparent_encoding    #直接加密
    content = r.text

    beaobj = BeautifulSoup(content.replace(' ', ' '),'html5lib')
    lis = beaobj.findAll('li',style="margin-top: -3.6px")
    for li in lis:
        image = re.findall(r'src="(.*?)"',str(li))  ################得到的无法判定对象数据类型，所以一定要加 str 否则报错
        name = image[0].split('/')[-1]
        image_name = 'E:\\Python\\python_image\\%s'%name
        try:
            s= urllib.request.urlretrieve(image[0],image_name)
            print("正在下载%s"%(image[0]))
        except Exception as e:
            print(e)

　　后面付费怎么爬取 稍后更新