爬虫实例十二 沪深证券股票全站数据爬取

先上代码

import requests
from lxml import etree
import openpyxl
import time
import random

#新建workbook对象
wb=openpyxl.Workbook()
#创建正在操作的表
sheet = wb.active
#设置表头
sheet.append(['股票名称','股票代码','最新价','涨跌幅','涨跌额','成交量','成交额','今开','昨收','最高','最低'])

#遍历全站单页链接并解析数据
for p in range(0,100):
   url="https://hq.gucheng.com/HSinfo/XSHE/?en_hq_type_code=XSHE&sort_field_name=px_change_rate&sort_type=desc&page="+str(p)
   headers={
      "User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36"
   }
   html=requests.get(url=url,headers=headers).text
   time.sleep(random.randint(1,3))
   tree=etree.HTML(html)
   GP_name=tree.xpath("//tbody/tr/td[1]/a/text()")
   GP_number=tree.xpath("//tbody/tr/td[2]/a/text()")
   NEW_price=tree.xpath("//tbody/tr/td[3]/text()")
   UP_DOWN=tree.xpath("//tbody/tr/td[4]/text()")
   Rise_fall=tree.xpath("//tbody/tr/td[5]/text()")
   Turnover_one=tree.xpath("//tbody/tr/td[6]/text()")
   Turnover_two=tree.xpath("//tbody/tr/td[7]/text()")
   day=tree.xpath("//tbody/tr/td[8]/text()")
   yesterday=tree.xpath("//tbody/tr/td[9]/text()")
   hightly=tree.xpath("//tbody/tr/td[10]/text()")
   lowly=tree.xpath("//tbody/tr/td[11]/text()")
   # 将数据添加进列表
   datas=[]
   for j in range(0,len(UP_DOWN)):
      data=[GP_name[j],GP_number[j],NEW_price[j],UP_DOWN[j],Rise_fall[j],
            Turnover_one[j],Turnover_two[j],day[j],yesterday[j],hightly[j],lowly[j]]
      datas.append(data)
   for s in datas:
      sheet.append(s)
   wb.save('100页股票数据.xlsx')

目标网址：
https://hq.gucheng.com/HSinfo/XSHE/?en_hq_type_code=XSHE&sort_field_name=px_change_rate&sort_type=desc&page=3

这个网站跟房产排行一样也是没有动态加载，所以也是没啥难度，但数据用来做大数据练习还是不错的