python实例：从excel读取股票代码，爬取股票信息写到代码后面的单元格中
关键词：爬虫、python、request、接口、excel处理、正则
思路：
1、首先准备好excel文档，把股票代码事先编辑进去。
2、脚本读取文档，依次读出股票代码到指定站点发起请求获取股票信息
3、将获取的股票信息简单处理，依次写入到指定的文档单元格中，完成整个实例过程
用到的python库：xlrd（读取excel）、requests（获取网页数据）、lxml（处理网页数据）、openpyyxl（对excel进行写入编辑）、re（正则）
具体步骤：
一，导入相关库
import xlrd #引入读取excel库 import requests #倒入requests库 from lxml import etree #倒入lxml 库（没有这个库，pip install lxml安装） import os import sys import openpyxl import re
二，读取excel内的股票代码，写入数组（共后面的函数调用）
#读取excel文档内的股票代码 def code(): wb = xlrd.open_workbook(path+'\\stock.xlsx')# 打开Excel文件 data = wb.sheet_by_name('Sheet1')#通过excel表格名称(rank)获取工作表 b=data.col_values(0)#获取第一列数据（数组） list=[] for c in b[1:]:#for循环，排除第一行数据 d=int(c) s="%06d" % d#股票代码一共有6位，常规打印无法打印出首位带0的代码的0部分，补齐缺失的0 #print(s) list.append(s) return(list) code=code()
三、循环读取股票代码查询股票信息，写入同一类数据的数组内（共后面写入excel）
#code函数获取的代码，循环爬取代码对应的股票数据，将股票数据写入对应的数组（同一类）中 def get(code): list_name=[]#股票名称 list_score=[]#综合评分 list_Short=[]#短期趋势 list_Metaphase=[]#中期趋势 list_Long=[]#长期趋势 list_comprehensive=[]#综合评判 list_day=[]#5日涨幅 list_mouth=[]#3个月涨幅 list_year=[]#1年涨幅 for num in code: url='http://stockpage.10jqka.com.cn/'+num+'/' headers = { 'Accept-Encoding': 'gzip, deflate', 'Accept-Language': 'zh-CN,zh;q=0.9', 'Upgrade-Insecure-Requests': '1', 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8', 'Referer': 'http://doctor.10jqka.com.cn/603160/', 'Connection': 'keep-alive', 'Cache-Control': 'max-age=0', } response = requests.get(url, headers=headers).text html = etree.HTML(response) b = html.xpath('//h1[@class = "m_logo fl"]/a/strong/text()') #print(b[0])#股票名称 c = html.xpath('//span[@class = "analyze-tips mt7"]/text()') #print(c[0])#综合评分 d = html.xpath('//div[@class = "analyze-txt fr"]/div/div[2]/text()') #print("短期趋势:",d[0])#短期趋势 e = html.xpath('//div[@class = "analyze-txt fr"]/div[2]/div[2]/text()') #print("中期趋势:",e[0])#中期趋势 f = html.xpath('//div[@class = "analyze-txt fr"]/div[3]/div[2]/text()') #print("远期趋势:",f[0])#远期趋势 g = html.xpath('//div[@class = "txt-phra"]/text()') h = html.xpath('//div[@class = "txt-phra"]/strong/text()') i = html.xpath('//div[@class = "txt-phra"]/text()[2]') #print(g[0],h[0],i[0])#综合评判 m=g[0]+h[0]+i[0] #j = html.xpath('//tr[@class = "even hot_cont"]/td[2]/text()') #k = html.xpath('//tr[@class = "even hot_cont"]/td[3]/text()') #l = html.xpath('//tr[@class = "even hot_cont"]/td[4]/text()') tr_content = re.findall('<tr class="even hot_cont">(.*?)</tr', response, re.S)[0] td_content = re.findall('<td.*?>(.*?)</td', tr_content, re.S)#正则获取周期涨幅 #print("5日涨幅:",j[0])#5日涨幅 #print("3个月涨幅:",k[0])#3个月涨幅 #print("1年涨幅:",l[0])#1年涨幅 list_name.append(b[0])#股票名称数组 list_score.append(c[0])#综合评分 list_Short.append(d[0])#短期趋势 list_Metaphase.append(e[0])#中期趋势 list_Long.append(f[0])#长期趋势 list_comprehensive.append(m)#综合评判 list_day.append(td_content[1])#5日涨幅 list_mouth.append(td_content[2])#3个月涨幅 list_year.append(td_content[3])#1年涨幅 return(list_name,list_score,list_Short,list_Metaphase, list_Long,list_comprehensive,list_day,list_mouth,list_year) get=get(code)
四、将写入数组的股票数据，依次写入到对应股票代码后的单元格中
#读取get函数生成的股票数据，依次写入到excel文档中 xfile = openpyxl.load_workbook(path+'\\stock.xlsx')#加载文件 sheet1 = xfile.worksheets[0] #excel中单元格为B2开始，即第2列，第2行 for i in range(len(get[0])):#股票名称 sheet1.cell(i+2, 2).value=get[0][i] for i in range(len(baidu[0])):#当前价格 sheet1.cell(i+2, 3).value=baidu[0][i] for i in range(len(baidu[1])):#当前市值 sheet1.cell(i+2, 4).value=baidu[1][i] for i in range(len(get[1])):#综合评分 sheet1.cell(i+2, 5).value=get[1][i] for i in range(len(get[2])):#短期趋势 sheet1.cell(i+2, 6).value=get[2][i] for i in range(len(get[3])):#中期趋势 sheet1.cell(i+2, 7).value=get[3][i] for i in range(len(get[4])):#长期趋势 sheet1.cell(i+2, 8).value=get[4][i] for i in range(len(get[5])):#综合评判 sheet1.cell(i+2, 9).value=get[5][i] for i in range(len(get[6])):#5日涨幅 sheet1.cell(i+2, 10).value=get[6][i] for i in range(len(get[7])):#3个月涨幅 sheet1.cell(i+2, 11).value=get[7][i] for i in range(len(get[8])):#1年涨幅 sheet1.cell(i+2, 12).value=get[8][i] xfile.save(path+'\\stock.xlsx')
直接后的文档内容
全部代码
#本脚本主要实现循环爬取数据后： # 1、同一类数据统一写入到同一个数组中， # 2、读取数组数据写入指定的excel列中，实现最终数据爬取 import xlrd #引入读取excel库 import requests #倒入requests库 from lxml import etree #倒入lxml 库（没有这个库，pip install lxml安装） import os import sys import openpyxl import re path = os.path.abspath(os.path.dirname(sys.argv[0])) #读取excel文档内的股票代码 def code(): wb = xlrd.open_workbook(path+'\\stock.xlsx')# 打开Excel文件 data = wb.sheet_by_name('Sheet1')#通过excel表格名称(rank)获取工作表 b=data.col_values(0)#获取第一列数据（数组） list=[] for c in b[1:]:#for循环，排除第一行数据 d=int(c) s="%06d" % d#股票代码一共有6位，常规打印无法打印出首位带0的代码的0部分，补齐缺失的0 #print(s) list.append(s) return(list) code=code() #code函数获取的代码，循环爬取代码对应的股票数据，将股票数据写入对应的数组（同一类）中 def get(code): list_name=[]#股票名称 list_score=[]#综合评分 list_Short=[]#短期趋势 list_Metaphase=[]#中期趋势 list_Long=[]#长期趋势 list_comprehensive=[]#综合评判 list_day=[]#5日涨幅 list_mouth=[]#3个月涨幅 list_year=[]#1年涨幅 for num in code: url='http://stockpage.10jqka.com.cn/'+num+'/' headers = { 'Accept-Encoding': 'gzip, deflate', 'Accept-Language': 'zh-CN,zh;q=0.9', 'Upgrade-Insecure-Requests': '1', 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8', 'Referer': 'http://doctor.10jqka.com.cn/603160/', 'Connection': 'keep-alive', 'Cache-Control': 'max-age=0', } response = requests.get(url, headers=headers).text html = etree.HTML(response) b = html.xpath('//h1[@class = "m_logo fl"]/a/strong/text()') #print(b[0])#股票名称 c = html.xpath('//span[@class = "analyze-tips mt7"]/text()') #print(c[0])#综合评分 d = html.xpath('//div[@class = "analyze-txt fr"]/div/div[2]/text()') #print("短期趋势:",d[0])#短期趋势 e = html.xpath('//div[@class = "analyze-txt fr"]/div[2]/div[2]/text()') #print("中期趋势:",e[0])#中期趋势 f = html.xpath('//div[@class = "analyze-txt fr"]/div[3]/div[2]/text()') #print("远期趋势:",f[0])#远期趋势 g = html.xpath('//div[@class = "txt-phra"]/text()') h = html.xpath('//div[@class = "txt-phra"]/strong/text()') i = html.xpath('//div[@class = "txt-phra"]/text()[2]') #print(g[0],h[0],i[0])#综合评判 m=g[0]+h[0]+i[0] #j = html.xpath('//tr[@class = "even hot_cont"]/td[2]/text()') #k = html.xpath('//tr[@class = "even hot_cont"]/td[3]/text()') #l = html.xpath('//tr[@class = "even hot_cont"]/td[4]/text()') tr_content = re.findall('<tr class="even hot_cont">(.*?)</tr', response, re.S)[0] td_content = re.findall('<td.*?>(.*?)</td', tr_content, re.S)#正则获取周期涨幅 #print("5日涨幅:",j[0])#5日涨幅 #print("3个月涨幅:",k[0])#3个月涨幅 #print("1年涨幅:",l[0])#1年涨幅 list_name.append(b[0])#股票名称数组 list_score.append(c[0])#综合评分 list_Short.append(d[0])#短期趋势 list_Metaphase.append(e[0])#中期趋势 list_Long.append(f[0])#长期趋势 list_comprehensive.append(m)#综合评判 list_day.append(td_content[1])#5日涨幅 list_mouth.append(td_content[2])#3个月涨幅 list_year.append(td_content[3])#1年涨幅 return(list_name,list_score,list_Short,list_Metaphase, list_Long,list_comprehensive,list_day,list_mouth,list_year) get=get(code) def baidu(code): list_Price=[] list_market=[] for num in code: cookies = { 'BIDUPSID': '90EF3BD78F53BC8C96DF84CD3854CA2D', 'PSTM': '1578233930', 'BD_UPN': '12314753', 'BAIDUID': '885754C8E6BD7B1A771802631815CC6D:FG=1', 'BDORZ': 'B490B5EBF6F3CD402E515D22BCDA1598', 'BDUSS': 'mxYdVpwOEx0eGJsT3VUYTJXbkZJYWhKSGpQWnlqaVBwMlExTWNNRkR4cWtabHRlSVFBQUFBJCQAAAAAAAAAAAEAAACRJsY-cGlwacnxu7AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAKTZM16k2TNeV', 'COOKIE_SESSION': '7_0_5_3_11_3_0_0_4_2_1_0_73199_0_169_0_1580456363_0_1580456194%7C9%23622712_32_1580376248%7C6', 'cflag': '13%3A3', 'BD_HOME': '1', 'BDRCVFR[feWj1Vr5u3D]': 'I67x6TjHwwYf0', 'delPer': '0', 'BD_CK_SAM': '1', 'PSINO': '3', 'H_PS_PSSID': '1438_21104_26350', 'H_PS_645EC': '29b8ZVy4WP7OUTz6%2FjeON9IexqLhOnMXkLTzhD5NfPu4fH%2FPZmThFknleY0LwzNQZ8j8', 'BDSVRTM': '121', 'WWW_ST': '1580466352318', } headers = { 'is_xhr': '1', 'Accept-Encoding': 'gzip, deflate, br', 'Accept-Language': 'zh-CN,zh;q=0.9', 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36', 'is_pbs': num, 'Accept': '*/*', 'Referer': 'https://www.baidu.com/s?wd='+num+'&rsv_spt=1&rsv_iqid=0xa5a17c8700013159&issp=1&f=8&rsv_bp=1&rsv_idx=2&ie=utf-8&rqlang=cn&tn=baiduhome_pg&rsv_enter=0&rsv_dl=tb&oq='+num+'&rsv_t=29b8ZVy4WP7OUTz6%2FjeON9IexqLhOnMXkLTzhD5NfPu4fH%2FPZmThFknleY0LwzNQZ8j8&rsv_pq=b379448d00013935', 'X-Requested-With': 'XMLHttpRequest', 'Connection': 'keep-alive', 'is_referer': 'https://www.baidu.com/s?wd='+num+'&rsv_spt=1&rsv_iqid=0xa5a17c8700013159&issp=1&f=8&rsv_bp=1&rsv_idx=2&ie=utf-8&tn=baiduhome_pg&rsv_enter=1&rsv_dl=tb&rsv_n=2&rsv_sug3=1&rsv_sug1=1&rsv_sug7=100&rsv_sug2=0&inputT=359&rsv_sug4=359', } params = ( ('ie', ['utf-8', 'utf-8']), ('newi', '1'), ('mod', '1'), ('isbd', '1'), ('isid', 'b379448d00013935'), ('wd', num), ('rsv_spt', '1'), ('rsv_iqid', '0xa5a17c8700013159'), ('issp', '1'), ('f', '8'), ('rsv_bp', '1'), ('rsv_idx', '2'), ('rqlang', 'cn'), ('tn', 'baiduhome_pg'), ('rsv_enter', '0'), ('rsv_dl', 'tb'), ('oq', num), ('rsv_t', '29b8ZVy4WP7OUTz6/jeON9IexqLhOnMXkLTzhD5NfPu4fH/PZmThFknleY0LwzNQZ8j8'), ('rsv_pq', 'b379448d00013935'), ('bs', num), ('rsv_sid', '1438_21104_26350'), ('_ss', '1'), ('clist', ''), ('hsug', ''), ('f4s', '1'), ('csor', '6'), ('_cr1', '29647'), ) response = requests.get('https://www.baidu.com/s', headers=headers, params=params, cookies=cookies).text html = etree.HTML(response) a = html.xpath('//span[@class = "op-stockdynamic-moretab-cur-num c-gap-right-small"]/text()') #print('当前价格:',a[0])#当前价格 b = html.xpath('//ul[@class = "op-stockdynamic-moretab-info"]/li[8]/span[2]/text()') #print('当前市值:',b[0])#当前市值 list_Price.append(a[0])#当前价格 list_market.append(b[0])#当前市值 return(list_Price,list_market) baidu=baidu(code) #读取get函数生成的股票数据，依次写入到excel文档中 xfile = openpyxl.load_workbook(path+'\\stock.xlsx')#加载文件 sheet1 = xfile.worksheets[0] #excel中单元格为B2开始，即第2列，第2行 for i in range(len(get[0])):#股票名称 sheet1.cell(i+2, 2).value=get[0][i] for i in range(len(baidu[0])):#当前价格 sheet1.cell(i+2, 3).value=baidu[0][i] for i in range(len(baidu[1])):#当前市值 sheet1.cell(i+2, 4).value=baidu[1][i] for i in range(len(get[1])):#综合评分 sheet1.cell(i+2, 5).value=get[1][i] for i in range(len(get[2])):#短期趋势 sheet1.cell(i+2, 6).value=get[2][i] for i in range(len(get[3])):#中期趋势 sheet1.cell(i+2, 7).value=get[3][i] for i in range(len(get[4])):#长期趋势 sheet1.cell(i+2, 8).value=get[4][i] for i in range(len(get[5])):#综合评判 sheet1.cell(i+2, 9).value=get[5][i] for i in range(len(get[6])):#5日涨幅 sheet1.cell(i+2, 10).value=get[6][i] for i in range(len(get[7])):#3个月涨幅 sheet1.cell(i+2, 11).value=get[7][i] for i in range(len(get[8])):#1年涨幅 sheet1.cell(i+2, 12).value=get[8][i] xfile.save(path+'\\stock.xlsx') print("爬取完成")
