PythonScript_004_正则匹配_抓取静态网页(内涵吧)的图片

#!/usr/bin/env python
# -*- coding:utf-8 -*-

import urllib.request
import random
import re # 正则库
'''
正则匹配-抓取静态网页(内涵吧)的图片
Python3.7.0
'''
class Spider:
    def __init__(self):
        # 初始化起始页位置
        self.page = 2
        # 开关，为True继续爬去
        self.switch = True

    def loadPage(self):
        '''
            作用:下载页面
        '''
        url = "https://www.neihan8.com/mm/index_" + str(self.page) + ".html"
        headers = {"User-Agent" : "Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11"}
        request = urllib.request.Request(url, headers = headers)
        response = urllib.request.urlopen(request)

        # 获取Html源码字符串
        html = response.read().decode("utf-8")
        # print(html)

        # 创建正则表达式的匹配规则对象，\s表示空格 re.S表示匹配全文、re.I表示忽略大小写,返回正则表达式的对象
        patter = re.compile('<a\sclass="img"\shref="/mm/(.*?).html">\s<img\ssrc="(.*?)"></a>', re.S)

        # 匹配数据，findall返回的是一个列表
        content_list = patter.findall(html)

        for list in content_list:
            print(list[1])
            self.download_web_image(list[1])

    def download_web_image(self, url):
        '''
            作用:下载图片到本地
        '''
        name = random.randrange(1, 10000000000)
        full_name = str(name) + '.jpg'
        urllib.request.urlretrieve(url, full_name)

    def startWork(self):
        '''
            作用:控制爬虫运行
        '''
        while self.switch:
            command = input("如果继续爬取，请按回车（退出输入quit）")
            if command == "quit":
                self.switch = False
                break
            self.loadPage()
            self.page += 1
        print("谢谢使用!")

if __name__ == "__main__":
    picSpider = Spider()
    picSpider.startWork()