11-内涵段子-爬虫(python+正则)

爬取内涵段子，使用正则进行简单处理：

#_*_ coding: utf-8 _*_

'''
Created on 2018年7月14日
@author: sss
function:爬去内涵段子（静态网页抓取）

'''

import requests
import urllib
import re
import random
from Tools.scripts.treesync import raw_input

class Spider:
    def __init__(self):
        #初始话起始页的位置
        self.page = 1
        #爬去开关，ture表示继续爬取
        self.switch = True
    
    def loadPage(self):
        """
                    下载页面
        """
        print('开始下载第'+ str(self.page) + '页：')
        url = 'https://www.neihan8.com/article/list_5_' + str(self.page) + '.html'
        ua_list = [
            "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36",
            "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko",
            "Mozilla/5.0 (X11; CrOS i686 2268.111.0)like Gecko",
            "Mozilla/5.0 (Macintosh; U; PPC Mac OS X ",
            "Mozilla/5.0 (Macintosh; Intel Mac OS "
        ]
        
        user_agnet = random.choice(ua_list)
        
        headers = {
                "Connection" : "keep-alive",
                "Accept" : "application/json, text/javascript, */*; q=0.01",
                "User-Agent" : user_agnet,
            }

#         response = requests.get(url, headers = headers)
        request = urllib.request.Request(url, headers = headers)
        response = urllib.request.urlopen(request)
        
        #获取每页的html源码：
        html = response.read().decode('gbk')
#         print(html)
        
        #创建正则表达式规则对象，匹配每页里的段子内容，re.Sb表示匹配全部字符串内容
        pattern = re.compile('<divsclass="f18 mb20">(.*?)</div>', re.RegexFlag.S)  #在py3中不是re.S
         
        #将正则匹配的对象应用到html源码字符串里，返回这个页面里的所有段子的列表
        content_list = pattern.findall(html)
         
#         print(content_list)
        self.dealPage(content_list)
        
    def dealPage(self, content_list ):
        """
                    处理每页都段子
        """
        for item in content_list:
            item = item.replace('<p>', '').replace('</p>',''.replace('<br>', '')).replace("<br />", '')
#             print(itme)
            self.writePage(item)
            
    def writePage(self, item):
        """
                    把每条段子写入到文件里
        """
        with open('duanzi.txt', 'a') as f:
            f.write(item)
        
    def startWork(self):
        """
                     控制爬虫的运行
        """
        while self.switch:
            self.loadPage()
            command = raw_input('如果继续爬去，请按回车(退出输入q)')
            if command == 'q':
                self.switch = False
            self.page += 1
        print('finish!')
        
if __name__ == '__main__':
    duanziSpider = Spider()
    duanziSpider.startWork()