Python爬虫爬取百度贴吧的帖子

同样是参考网上教程，编写爬取贴吧帖子的内容，同时把爬取的帖子保存到本地文档：

#!/usr/bin/python
#_*_coding:utf-8_*_
import urllib
import urllib2
import re
import sys

reload(sys)
sys.setdefaultencoding("utf-8")
#处理页面标签,去除图片、超链接、换行符等
class Tool:
#去除img标签，7位长空格
removeImg = re.compile('<img.*?>| {7}|')
#删除超链接标签
removeAddr = re.compile('<a.*?>|</a>')
#把换行的标签替换为
replaceLine = re.compile('<tr>|<div>|</div>|</p>')
#把表格制表<td>替换为
replaceTD = re.compile('<td>')
#把段落开头换为 加两个空格
replacePara = re.compile('<p.*?>')
#把换行符或双换行符替换为
replaceBR = re.compile('<br><br>|<br>')
#将其余标签剔除
removeET = re.compile('<.*?>')

#去除匹配到Tool
def replace(self,x):
x = re.sub(self.removeImg,"",x)
x = re.sub(self.removeAddr,"",x)
#x = re.sub(self.replaceLine," ",x)
#x = re.sub(self.replaceTD," ",x)
#x = re.sub(self.replacePara," ",x)
#x = re.sub(self.replaceBR," ",x)
x = re.sub(self.removeET,"",x)
#strip()将前后多余内容删除
return x.strip().encode('utf-8')
#百度贴吧爬虫练习
class BDTB:

#初始化，传入地址，是否只看楼主的参数
def __init__(self,baseUrl,seeLz,floorTag):
#base链接地址
self.baseURL = baseUrl
#是否只看楼主
self.seeLZ = '?seelz=' + str(seeLz)
#HTML剔除标签工具Tool
self.tool = Tool()
#全局file变量，文件写入操作对象
self.file = None
#楼层标识，初始化为1
self.floor = 1
#默认的标题，如果没有成功获取到标题的话则会用这个标题
self.defaultTitle = u"百度贴吧"
#是否写入楼分隔符的标记
self.floorTag = floorTag

#传入页码，获取该页帖子的代码
def getPage(self,pageNum):
try:
url = self.baseURL + self.seeLZ + '&pn=' + str(pageNum)
request = urllib2.Request(url)
response = urllib2.urlopen(request)
tbPage = response.read().decode('utf-8')
#print tbPage
return tbPage
#链接报错的原因
except urllib2.URLError, e:
if hasattr(e,"reason"):
print u'链接百度贴吧失败，错误原因：',e.reason
return None

#获取帖子标题
def getTitle(self,page):
page = self.getPage(1)
#正则匹配贴吧标题
pattern = re.compile('<h3 class="core_title_txt.*?>(.*?)</h3>',re.S)
result = re.search(pattern,page)
if result:
#输出标题
#print result.group(1)
return result.group(1).strip()
else:
return None

#获取帖子一共有多少页
def getPageNum(self,page):
page = self.getPage(1)
#正则匹配帖子总共有多少页
pattern = re.compile('<li class="l_reply_num.*?</span>.*?<span.*?>(.*?)</span>',re.S)
result = re.search(pattern,page)
if result:
#输出页码数
#print result.group(1)
return result.group(1).strip()
else:
print None

#获取帖子每一个楼层的内容
def getContent(self,page):
#正则匹配每一个楼层的内容
pattern = re.compile('<div id="post_content.*?>(.*?)</div>',re.S)
items = re.findall(pattern,page)
#floor = 1
contents = []
for item in items:
#将文本进行去除标签处理，同时在前后加入换行符
content = " " + self.tool.replace(item) + " "
contents.append(content.encode('utf-8'))
#print floor,u"楼-----------------------"
#print content
#floor += 1
return contents

#设置文件的标题
def setFileTitle(self,title):
#如果标题不是None，即成功获取到标题
if title is not None:
self.file = open(title + ".txt","w+")
else:
self.file = open(self.defaultTitle + ".txt","w+")

#向文件写入每一楼层的信息
def writeData(self,contents):
#遍历楼层
for item in contents:
if self.floorTag == '1':
#楼之间使用的分隔符
floorLine = " --------------" + str(self.floor) + "楼----------------- "
self.file.write(unicode(floorLine,"utf-8"))
self.file.write(unicode(item,"utf-8"))
self.floor += 1

def start(self):
indexPage = self.getPage(1)
pageNum = self.getPageNum(indexPage)
title = self.getTitle(indexPage)
self.setFileTitle(title)
if pageNum == None:
print "URL已失效，请重试"
return
try:
print "该帖子共有" + str(pageNum) + "页"
for i in range(1,int(pageNum) + 1):
print "正在写入第" + str(i) + "页数据"
page = self.getPage(i)
contents = self.getContent(page)
self.writeData(contents)
except IOError,e:
print "写入异常，原因" + e.message
finally:
print "写入任务完成"
print u"请输入帖子代号"
baseURL = 'http://tieba.baidu.com/p/' + str(raw_input(u'http://tieba.baidu.com/p/'))
seeLZ = raw_input("是否只获取楼主发言，是输入1，否输入0 ")
floorTag = raw_input("是否写入楼层信息，是输入1，否输入0 ")
bdtb = BDTB(baseURL,seeLZ,floorTag)
bdtb.start()