爬虫笔记12完结篇实例：股票

最新推荐文章于 2024-03-01 23:47:59 发布

新川宝宝

最新推荐文章于 2024-03-01 23:47:59 发布

阅读量509

点赞数

本文链接：https://blog.csdn.net/weixin_44382711/article/details/104847758

版权

在这里插入图片描述

在这里插入图片描述

1.实例编写

在这里插入图片描述

并没有说这个页面是怎么找到的，2020.3.14需要加下划线
https://quote.eastmoney.com/stock_list.html
当查找雪球网的时候：比如sh501007
https://xueqiu.com/k?q=sh501007
点击进入页面后
https://xueqiu.com/S/SH501007
这里大小写都可以
在这里插入图片描述

请求头
真第麻烦：爬取成功，但出了一大堆问题，css选择器查不到对应标签【我还以为是我写错了，但最后查标签name都查不到（只能查到一部分标签，想要的查不到）】，等问题解决再补吧

# -*- coding: utf-8 -*-
import scrapy
import re



class StocksSpider(scrapy.Spider):
    name = 'stocks'
    allowed_domains = ['xueqiu.com']
    start_urls = ['https://quote.eastmoney.com/stock_list.html']

    def parse(self, response):
        
        for href in response.css('a::attr(href)').extract():
            try:
                stock=re.findall(r"[s][hz]\d{6}",href)[0]
                url ='https://xueqiu.com/k?q='+stock
                #变成生成器
                #当查找雪球网的时候：比如sh501007
                #https: // xueqiu.com/k?q = sh501007
                #点击进入页面后
                #https: // xueqiu.com/S/SH501007
                #这里大小写都可以
                headers = {
                    'cookie': 'miid=1296267545453648768; t=b4d385e2145f596a67961e4dd08e9a8f; cna=pqwcFXxbJjACAXWIA7AFEfA8; thw=cn; tracknick=tb487881011; lgc=tb487881011; _cc_=UIHiLt3xSw%3D%3D; tg=0; enc=%2FTqA3gAexHOKU0cyPYbSWM1pGS8vgnlEK3EMnkYd2T%2BlB%2BJh18hxryREG48c%2BYmdk7yfvbSMCBDQExP23eUm3w%3D%3D; hng=CN%7Czh-CN%7CCNY%7C156; x=e%3D1%26p%3D*%26s%3D0%26c%3D0%26f%3D0%26g%3D0%26t%3D0%26__ll%3D-1%26_ato%3D0; cookie2=19ef67fdfc3f433776e5e9cafaf6a8ea; v=0; _tb_token_=08b7e3e7e183; _m_h5_tk=62383241b06635c64b07942e50e47d9d_1562004576179; _m_h5_tk_enc=0465da475a8335f8fd8d9ef6bb280a71; unb=4235284520; sg=101; _l_g_=Ug%3D%3D; skt=c571ae590b7580cb; cookie1=AnQIvxj44XbyESoVNTVtwfJRB8W%2BbAPV%2BVZMWhAghjk%3D; csg=23f40375; uc3=vt3=F8dBy34cs3fc7ebsEqk%3D&id2=Vy67WD1MZomrsw%3D%3D&nk2=F5RBzeKtOazPVJc%3D&lg2=UtASsssmOIJ0bQ%3D%3D; existShop=MTU2MTk5NTE3MQ%3D%3D; dnk=tb487881011; _nk_=tb487881011; cookie17=Vy67WD1MZomrsw%3D%3D; mt=ci=21_1; uc1=cookie14=UoTaGdT0tHdY5w%3D%3D&lng=zh_CN&cookie16=VT5L2FSpNgq6fDudInPRgavC%2BQ%3D%3D&existShop=false&cookie21=VFC%2FuZ9aj3yE&tag=8&cookie15=UIHiLt3xD8xYTw%3D%3D&pas=0; whl=-1%260%260%261561995222497; isg=BHNzJqpkKgCWtOesccf13ZRUAnddACwkF8iwAyUQzxLJJJPGrXiXutG23hRvn19i; l=bBMxcfBPv539-OTkBOCanurza77OSIRYYuPzaNbMi_5K-6T_2qQOkAuQFF96Vj5Rs4YB4G2npwJ9-etkq',
                    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36'
                }
                yield scrapy.Request(url,callback=self.parse_stock,headers=headers)
                #callback给出了一个处理函数
            except:
                continue
    
    def parse_stock(self,response):
        #最终要返回信息给item_pipline
        infoDict={}
        #找到拥有 股票所拥有 的属性 的区域
        #  
        #stockInfo = response.css('.container-sm.float-left.stock__main')
        #
        #self.log(str(stockInfo))
        name =response.css('span::text').extract()
        name2=response.css('p::text').extract()
        fname='Xueqiu.txt'
        with open(fname,'a') as f:
            f.write(str(response)+'\n')
            f.write('span'+str(name)+'\n')
            f.write('p'+str(name2)+'\n')
            f.close()
        self.log('Saved file %s.' % str(response))
       # self.log(str(keyList))