Python爬虫之抓取静态网页并保存到excel

分析

很简单，获取网页的文本，然后通过re正则表达式找到需要的内容，并把内容存储到excel

import urllib.request
import re
import xlwt

#获取网页数据
def GetData(url):
#    url='http://www.risfond.com/case/fmcg/26700'
    response = urllib.request.urlopen(url)
    page=response.read().decode("UTF-8")
    context=re.findall("
.*?(.*?)
",page)
    return context

#获取26700-26719的数据
def SearchAllPage():
    contextall=[]
    for i in range(26700,26720):
        url='http://www.risfond.com/case/fmcg/'+str(i)
        contextall+=GetData(url)
#    print(contextall)
    return contextall

#将数据存储到excel
def ExcelRestore(contextall):
    workbook=xlwt.Workbook(encoding='UtF-8')
    worksheet=workbook.add_sheet("mysheet")

    #表头设置
    str_list=["职位名称","工作地点","案例日期","所在行业","职位周期","上岗人数","顾问团队"]
    style = xlwt.XFStyle()
    style.font.bold = True
    for i in range(7):
        worksheet.write(0,i,str_list[i],style)

    #内容设置
    count=0
    colum=0
    row=1
    while count<len(contextall) :
        if colum>6 :
            colum=0
            row+=1
        worksheet.write(row,colum,contextall[count])
        colum+=1
        count+=1

    workbook.save("python.xls")

ExcelRestore(SearchAllPage())