【python学习】网络爬虫——爬百度贴吧帖子内容

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

#import urllib
import urllib2
import re

#功能性类，过滤掉html标签的类
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>')
#把换行的标签换为\n
replaceLine = re.compile('<tr>|<div>|</div>|</p>')
#将表格制表<td>替换为\t
replaceTD = re.compile('<td>')
#把段落开头换为\n加空两格
replacePara = re.compile('<p.*?>')
#将换行符或双换行符替换为\n
replaceBR = re.compile('<br><br>|<br>')
#将其余标签剔除
removeExtraTag = re.compile('<.*?>')
def replace(self, x):
x = re.sub(self.removeImg, "", x)
x = re.sub(self.removeAddr, "", x)
x = re.sub(self.replaceLine, "\n", x)
x = re.sub(self.replaceTD, "\t", x)
x = re.sub(self.replacePara, "\n    ", x)
x = re.sub(self.replaceBR, "\n", x)
x = re.sub(self.removeExtraTag, "", x)
#strip()将前后多余内容删除
return x.strip()

#百度贴吧爬虫类
class BDTB:
#初始化，传入网址，只看楼主的参数，传入1就只看楼主
def __init__(self, baseUrl, seeLZ):
self.baseURL = baseUrl
self.seeLZ = '?see_lz=' + str(seeLZ)
self.tool = Tool()

def getPage(self, pageNum):
try:
url = self.baseURL + self.seeLZ + '&pn=' + str(pageNum)
request = urllib2.Request(url)
response = urllib2.urlopen(request)
return response.read().decode('utf-8')
except urllib2.URLError, e:
if hasattr(e, "reason"):
print u"连接百度贴吧失败.错误原因", e.reason
return None

#获取帖子标题
def getTile(self):
print '获取帖子标题开始'
page = self.getPage(1)
pattern = re.compile('<h3 class="core_title_txt.*?>(.*?)</h3>', re.S)
result = re.search(pattern, page)
if result:
print result.group(1).strip()
print '获取帖子标题结束'

#提取帖子页数
#获取帖子一共有多少页
def getPageNum(self):
print '获取帖子页数一共有多少页开始'
page = self.getPage(1)
pattern = re.compile('<li class="l_reply_num.*?</span>.*?<span.*?>(.*?)</span>', re.S)
result = re.search(pattern, page)
if result:
print  result.group(1).strip()
print '获取帖子页数一共有多少页结束'
return result.group(1).strip()

#提取单页帖子内容
def getPageContent(self, page):
pattern = re.compile('<div id="post_content_.*?>(.*?)</div>', re.S)
items = re.findall(pattern, page)
for item in items:
print self.tool.replace(item)

#汇总所有帖子内容
def getAllContent(self):
print '获取正文内容开始------>'
for i in range(int(self.getPageNum())):
self.getPageContent(self.getPage(i+1))
print '<------获取正文内容结束'

baseURL = 'http://tieba.baidu.com/p/4452150954'
bdtb = BDTB(baseURL, 1)
bdtb.getTile()
bdtb.getAllContent()