python爬取小说

from urllib import request
import re
if __name__ == '__main__':
    urlList = list()
    f = open("D:\\xiaoshiuo.txt",'w')
    for i in range(1460216,1463703):
        url = "http://www.biquyun.com/2_2499/"+str(i)+".html"
        urlList.append(url)
    header = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36'}
    for item in urlList:
        res = request.Request(url=item,data=None,headers=header)
        try:
            rsp = request.urlopen(res)
            html = rsp.read().decode("gbk")
            #print(html)
            head = re.search(r'<div class="bookname">(.*)</div>',html,re.S)
            try:
                head = re.search(r'<h1>(.*)</h1>',head.group(),re.S)
                print(head.group(1))
                f.write(" "*10+head.group(1)+'\n')
                try:
                    text = re.search(r'<div id="content">(.*)</div>', html, re.S)
                    lineList = re.finditer(r'&nbsp;&nbsp;&nbsp;&nbsp;(.*)<br />', html, re.I)
                    for line in lineList:
                        #print(line.group(1))
                        f.write(line.group(1)+'\n')
                    # print(text.group())
                except Exception as e:
                    pass
            except Exception as e:
                pass

        except Exception as e:
            print(e)
    f.close()
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值