爬虫，爬取句子迷《龙族》

Posted 2020-10-19 112226

踩了很多坑，主要是python2编码的问题和正则不熟

直接上脚本

# -*- coding: gbk -*-
import re
import urllib2
import time



class spider:
    """
龙族  句子迷
    """


    def __init__(self):
        self.enable = True
        self.page = 1
    def load_page(self,page):
        url = ‘http://www.juzimi.com/article/113093?page=‘+str(page)
        user_agent=‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/55.0.2883.87 Safari/537.36‘
        headers = {"User-Agent":user_agent}
        req = urllib2.Request(url,headers = headers)
        response = urllib2.urlopen(req)
        html = response.read()
        new_html = html.decode(‘utf-8‘)
        # print new_html
        

        #正则过滤得到句子
        pattern = re.compile(r‘class="xlistju">(.*?)</a>‘,re.S)
        item_list=pattern.findall(new_html)
        # print item_list
        return item_list

    def deal_one_page(self,item_list,page):
        print ‘第%d页‘ %(page)
        for item in item_list:
            item = item.replace("<br />", "")
            item = item.replace("<br/>","")
            self.write_to_file(item)
        print ‘%d‘ %(page)

    def write_to_file(self,txt):
        f=open(‘F:\py\longzu.txt‘,‘a‘)
        f.write(txt.encode(‘utf-8‘))
        f.write(‘\n\n‘)
        f.close()

    def do_work(self):
        while self.enable:
            for i in range(1,34):
                item_list = self.load_page(self.page)
                self.deal_one_page(item_list,self.page)
                time.sleep(5)
                self.page += 1
                if i==33 :
                    print ‘结束‘
                    self.enable = False
                    break
                
if __name__ == "__main__":
    longspider = spider()
    longspider.do_work()