python怎么爬取excel_python爬取简单数据写入EXCEL

#大盘采集导入Excle#使用py3实现#指数名称：name最新价：price 涨跌额：limit 涨跌幅：rate 时间：time

importurllib.requestimportxlwt3importre

wbk=xlwt3.Workbook() #新建一个EXECL文件

sheet = wbk.add_sheet('大盘',True) #EXCEL文件中建立一个工作表

defurlRead(url):

url_read= urllib.request.urlopen(url).read().decode('gb2312')returnurl_readdefreadData(url_read):

name= re.findall(r"name:'(\w+)",url_read)

price= re.findall(r"price:'(\d{1,9}|\d{1,9}\.\d{1,9})'",url_read)

limit= re.findall(r"limit:'(\d{1,9}|[-]\d{1,9}|\d{1,9}\.\d{1,9}|[-]\d{1,9}\.\d{1,9})'",url_read)

rate= re.findall(r"rate:'(\d{1,9}|[-]\d{1,9}|\d{1,9}\.\d{1,9}|[-]\d{1,9}\.\d{1,9})'",url_read)

time= re.findall(r"time:'(\d{1,2}\:\d{1,2})'",url_read)returnname,price,limit,rate,time

url= 'http://quote.hexun.com/Global/datalistall.aspx?callback=hxbase_json14022917871451'read=urlRead(url)

lists=readData(read)

name_list=lists[0]

name_leng=len(name_list)for i in range(1,name_leng+1):

sheet.write(i,0,name_list[i-1]) #在EXCEL的表中写入数据：行，列，数据

price_list= lists[1]

price_leng=len(price_list)for i in range(1,price_leng+1):

sheet.write(i,1,price_list[i-1])

limit_list= lists[2]

limit_leng=len(limit_list)for i in range(1,limit_leng+1):

sheet.write(i,2,limit_list[i-1]/100)

rate_list= lists[3]

rate_leng=len(rate_list)for i in range(1,rate_leng+1):

sheet.write(i,3,rate_list[i-1])

time_list= lists[4]

time_leng=len(time_list)for i in range(1,time_leng+1):

sheet.write(i,4,time_list[i-1])

wbk.save('zzz.xls') #保存文件并命名为：zzz.xls

'''url = 'http://quote.hexun.com/Global/datalistall.aspx?callback=hxbase_json14022917871451'

url_read = urllib.request.urlopen(url).read().decode('gb2312')

price = re.findall(r"price:'(\d{1,9}|\d{1,9}\.\d{1,9})'",url_read)

name = re.findall(r"name:'(\w+)",url_read)

limit = re.findall(r"limit:'(\d{1,9}|[-]\d{1,9}|\d{1,9}\.\d{1,9}|[-]\d{1,9}\.\d{1,9})'",url_read)

rate = re.findall(r"rate:'(\d{1,9}|[-]\d{1,9}|\d{1,9}\.\d{1,9}|[-]\d{1,9}\.\d{1,9})'",url_read)

time = re.findall(r"time:'(\d{1,2}\:\d{1,2})'",url_read)

#alln = re.findall(r"name:'(\w+).price:'(\d{1,9}|\d{1,9}\.\d{1,9})'.+limit:'(\d{1,9}|\d{1,9}\.\d{1,9}|[-]\d{1,9}\.\d{1,9})'.+rate:'(\d{1,9}|\d{1,9}\.\d{1,9}|[-]\d{1,9}\.\d{1,9})'",url_read)

#alln = re.findall(r"name:'(\w+).+price:'(\d{1,9}|\d{1,9}\.\d{1,9})',\s+l",url_read)

print(time)

print(len(time))'''