室友在学python数据分析，但是却不会爬取数据

python爬取股市信息–千股千评

一切得从我的爬虫代码说起

1. 那天室友突然找我要爬虫源代码，我说你要什么样子的，他说随便：
   然后我就想起的我的lsp代码
   
2. 哈哈哈，万万没想到他说这个不行，他说要做数据分析，只有图片还不够，不过还好我一年前写了几个python爬虫代码应该能派上用场。
   
3. 本来用豆瓣信息的话刚好，能满足他的要求，但是又万万没想到的是，豆瓣的反爬虫升级了（直接就把我的ip给封了，麻了）
   但是我又想起之前有用过股市信息，觉得这个不错挺合适，于是就有了今日代码，爬取股市信息。据说他们数据处理，还要对数据清洗，我没学，就只能把数据存到excel文件中了。剩下了就交给他自己了，毕竟爸爸也不能一直帮他

import xlwt
import requests
from lxml import etree
import json
import demjson
url = "http://dcfm.eastmoney.com/em_mutisvcexpandinterface/api/js/get?callback=datatable5593272&type=QGQP_LB&token=70f12f2f4f091e459a279469fe49eca5&cmd=&st=Code&sr=1&p={}&ps=50&js=(%7Bpages%3A(tp)%2Cdata%3A(x)%2Cfont%3A(font)%7D)&filter=&_=1622642424445"
headers = {
     "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36"}
def get_information(url,n):
    r = requests.get(url,headers = headers)
    data = r.content.decode()
    data = data[28:]
    data = data[:-58]
    data = "{"+data+"}"
    data = data.replace("\'","\"")
    data = demjson.decode(data,encoding='utf-8')
    AllData = data["data"]
    #print(AllData)
    k=n
    for currentdata in AllData:
            #时间
            TDate = currentdata["TDate"]
            print("时间:{}".format(TDate))
            #代号
            Code = currentdata["Code"]
            print("代号:{}".format(Code))
            #名字
            Name = currentdata["Name"]
            print("名字:{}".format(Name))
            #最新价
            New = currentdata["New"]
            print("最新价:{}".format(New))
            #涨跌幅
            ChangePercent = currentdata["ChangePercent"]
            print("涨跌幅:{}".format(ChangePercent))
            #换手率
            TurnoverRate = currentdata["TurnoverRate"]
            print("换手率:{}".format(TurnoverRate))
            #市盈率
            PERation = currentdata["PERation"]
            print("市盈率:{}".format(PERation))
            #主力成本
            ZLCB = currentdata["ZLCB"]
            print("主力成本:{}".format(ZLCB))
            #机构参与度
            JGCYD = currentdata["JGCYD"]
            print("机构参与度:{}".format(JGCYD))
            #综合得分
            TotalScore = currentdata["TotalScore"]
            print("综合得分:{}".format(TotalScore))
            #上升排名
            RankingUp = currentdata["RankingUp"]
            print("上升排名:{}".format(RankingUp))
            #目前排名
            Ranking = currentdata["Ranking"]
            print("目前排名:{}".format(Ranking))
            #关注指数
            Focus = currentdata["Focus"]
            print("关注指数:{}".format(Focus))
            sheet1.write(k,0,TDate)
            sheet1.write(k,1,Code)
            sheet1.write(k,2,Name)
            sheet1.write(k,3,New)
            sheet1.write(k,4,ChangePercent)
            sheet1.write(k,5,TurnoverRate)
            sheet1.write(k,6,PERation)
            sheet1.write(k,7,ZLCB)
            sheet1.write(k,8,JGCYD)
            sheet1.write(k,9,TotalScore)
            sheet1.write(k,10,RankingUp)
            sheet1.write(k,11,Ranking)
            sheet1.write(k,12,Focus)
            k=k+1
if __name__ == "__main__":
    file_path = "./a.xls"
    f = xlwt.Workbook()
    sheet1 = f.add_sheet(u'sheet1',cell_overwrite_ok=True) #创建sheet
    sheet1.write(0,0,"时间")
    sheet1.write(0,1,"代号")
    sheet1.write(0,2,"名字")
    sheet1.write(0,3,"最新价")
    sheet1.write(0,4,"涨跌幅")
    sheet1.write(0,5,"换手率")
    sheet1.write(0,6,"市盈率")
    sheet1.write(0,7,"主力成本")
    sheet1.write(0,8,"机构参与度")
    sheet1.write(0,9,"综合得分")
    sheet1.write(0,10,"上升排名")
    sheet1.write(0,11,"目前排名")
    sheet1.write(0,12,"关注指数")
    #循环操作
    x=1
    for n in range(1,92):
        urlx = url.format(n)
        get_information(urlx,x) 
        x=n*50+1
    f.save(file_path)
    print("爬取完成，信息存储在{}中".format(file_path))

文件保存到当前目录下的a.xls中

需要pip的部分：pip install xlwt
pip install demjson
pip install lxml