# -*- coding:utf-8 -*-

import urllib2

import re

def load_Page(url,begin_page,end_page):

'''

加載貼吧信息

'''

for i in range(begin_page,end_page+1):

pn = 50*(i-1)

my_url = url+str(pn)

html = Get_Html(my_url)

title = GetMainInfo(html)

sumTxt = ""

for item in title:

sumTxt = sumTxt + item

print "--------第 %d 頁數(shù)據(jù)開始收集-------" % (i)

# filename = "第"+str(i)+"頁數(shù)據(jù).html"

SaveToTxt(str(i) + ".html", sumTxt)

print "--------第 %d 頁數(shù)據(jù)收集完畢--------" % (i)

def Get_Html(url):

"""

抓取網(wǎng)頁信息并返回

"""

User_Agent = "Mozilla/5.0 (X11; U; Linux i686)Gecko/20071127 Firefox/2.0.0.11"

Accept = "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8"

headers = {"User-Agent": User_Agent, "Accept": Accept}

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

response = urllib2.urlopen(request)

html = response.read()

return html

def SaveToTxt(filename,txt):

f = open(filename,'a')

f.write(txt)

f.close()

def GetMainInfo(html):

regex = re.compile("

(.*)", re.S)

return regex.findall(html)

#mian

if __name__ == "__main__":

print "請輸入貼吧地址"

url = raw_input()

print "請輸入起始頁碼"

begin_page = int(raw_input())

print "請輸入結(jié)束頁碼"

end_page = int(raw_input())

load_Page(url,begin_page,end_page)

總結(jié)

以上是生活随笔為你收集整理的python模拟手写_python-自己手写的贴吧爬虫的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。