python 爬取百度贴吧数据存入execl

%%%%

#coding:utf-8
import  requests
from xlwt import Workbook
from  bs4 import  BeautifulSoup
import time
import datetime
import sys
reload(sys)
sys.setdefaultencoding('utf-8')

def baidu(url):
    response = requests.get(url)
    soup = BeautifulSoup(response.text,'html.parser')
    tiezilist = soup.find_all('li',class_=" j_thread_list clearfix")
    datalist = []
    for tiezi in tiezilist:
        huifu =  tiezi.span.string
        title = ''.join(tiezi.find('div',class_="threadlist_abs threadlist_abs_onlyline ").text.split())
        try:
            author = tiezi.find('span',class_="tb_icon_author ").text
        except:
            author = "None"
        createtime = tiezi.find('span',class_="pull-right is_show_create_time").string
        if ':' in createtime:
            date = datetime.datetime.now().strftime('%Y-%m-%d')
            createtime =date+' '+createtime
        try:
            endhuifuren = tiezi.find('span',class_="tb_icon_author_rely j_replyer")['title']
        except:
            endhuifuren ="None"
        try:
            endhuifurentime = ''.join(tiezi.find('span',class_="threadlist_reply_date pull_right j_reply_data").text.split())
        except:
            endhuifurentime = "None"
        data = [title,author,createtime,endhuifuren,endhuifurentime,huifu]
        datalist.append(data)
    return datalist


def saveToExecl(name,start,end):
    datalistnew = []
    book = Workbook(encoding='utf-8')  # 设置execl编码格式
    sheet1 = book.add_sheet('Sheet 1')  # 操做execl表格
    sheet1.write(0, 0, u'标题')
    sheet1.write(0, 1, u'发贴人')
    sheet1.write(0, 2, u'帖子建立时间')
    sheet1.write(0, 3, u'最后回复人')
    sheet1.write(0, 4, u'最后回复时间')
    sheet1.write(0, 5, u'回复数')
    startnew = int(start)*50
    endnew = int(end)*50
    for page in range(startnew,endnew, 50):
        url = "http://tieba.baidu.com/f?kw=%s&ie=utf-8&pn=%s"   % (name,page)
        try:
            print page/50
            datalist = baidu(url)
            time.sleep(1)
        except:
            print page
            time.sleep(10)
            datalist = baidu(url)
        datalistnew = datalistnew + datalist
    datalist = datalistnew
    execlNmae = name+'贴吧'+str(start)+'-'+str(end)+'页数据'+'.xls'
    try:
        for data in range(0, len(datalist)):  # 遍历数据列表，而后把数据写入表格中
            title = datalist[data][0]
            author = datalist[data][1]
            createtime = datalist[data][2]
            endhuifuren = datalist[data][3]
            endhuifurentime = datalist[data][4]
            huifu = datalist[data][5]
            sheet1.write(data + 1, 0, title)
            sheet1.write(data + 1, 1, author)
            sheet1.write(data + 1, 2, createtime)
            sheet1.write(data + 1, 3, endhuifuren)
            sheet1.write(data + 1, 4, endhuifurentime)
            sheet1.write(data + 1, 5, huifu)
        book.save(u"%s" % execlNmae)
    except:
        book.save(u"%s" % execlNmae)
        pass


if __name__=='__main__':
    print "*********************百度贴吧数据爬取软件*********************"
    baiduPostBar =raw_input("please input Baidu Post Bar Name:")
    start = raw_input("please input start page number: ")
    end = raw_input("please input end page number: ")
    saveToExecl(baiduPostBar,start,end)

%%%%