python爬取贴吧_Python爬取贴吧（简洁版）

#encoding=utf-8

import urllib2,urllib

class tieba:

def tiebaSpider(self,name,starPage,endPage):

#要爬取得网络地址

url = "https://tieba.baidu.com/f?"

#要爬取得带关键字的地址

url = url+urllib.urlencode({"kw":name})+"&"

#循环起始位置到终止为止

for i in range(starPage,endPage+1):

pageNum = (i-1)*50

fullUrl = url+urllib.urlencode({"pn":pageNum})

html = self.loadPage(fullUrl,i)

self.writePage(html,i)

def loadPage(self,url,pageNum):

header = {"User-Agent":"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6"}

print "正在爬取第"+str(pageNum)+"页数据......"

request = urllib2.Request(url,headers=header)

response = urllib2.urlopen(request)

html = response.read()

return html

def writePage(self,html,pageNum):

filename = "di"+str(pageNum)+"ye.html"

print "正在写入"+filename

with open(filename,"w") as file:

file.writelines(html)

if __name__=='__main__':

name = raw_input("请输入要搜索的贴吧名：")

startPage = input("请输入起始页：")

endPage = input("请输入一个终止页：")

tieba = tieba()

tieba.tiebaSpider(name,startPage,endPage)

print "爬取结束！"