Python爬蟲_獲取貼吧內容

參考http://cuiqingcai.com/993.html，寫的第一個比較完整的python爬蟲程序。

對正則表達式要有更加深刻的研究，本程序對百度貼吧使用，但是截取不了表情。如果想把所有頁面的內容都獲取下來不難，拓展一下即可。

# -*- coding:utf-8 -*-
import urllib
import urllib2
import re


#處理頁面標籤類
class Tool:
    #去除img標籤,7位長空格
    removeImg = re.compile('<img.*?>| {7}|')
    #刪除超鏈接標籤
    removeAddr = re.compile('<a.*?>|</a>')
    #把換行的標籤換爲\n
    replaceLine = re.compile('<tr>|<div>|</div>|</p>')
    #將表格製表<td>替換爲\t
    replaceTD= re.compile('<td>')
    #把段落開頭換爲\n加空兩格
    replacePara = re.compile('<p.*?>')
    #將換行符或雙換行符替換爲\n
    replaceBR = re.compile('<br><br>|<br>')
    #將其餘標籤剔除
    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()將前後多餘內容刪除
        return x.strip()


 
#百度貼吧爬蟲類
class BDTB:
 
    #初始化，傳入基地址，是否只看樓主的參數
    def __init__(self,baseUrl,seeLZ):
        self.baseURL = baseUrl
        self.seeLZ = '?see_lz='+str(seeLZ)
        self.tool = Tool()
        self.file = None
        self.defaultTitle = u"百度貼吧"
 
    #傳入頁碼，獲取該頁帖子的代碼
    def getPage(self,pageNum):
        try:
            url = self.baseURL+ self.seeLZ + '&pn=' + str(pageNum)
            request = urllib2.Request(url)
            response = urllib2.urlopen(request)
            content = response.read().decode('utf-8')
            #print content
            return content
        except urllib2.URLError, e:
            if hasattr(e,"reason"):
                print u"連接百度貼吧失敗,錯誤原因",e.reason
                return None
            
    def getTitle(self):
        page = self.getPage(1)
        pattern = re.compile('<h3 class="core_title_txt pull-left text-overflow.*?>(.*?)</h3>',re.S)
        #pattern = re.compile('<h1 class="core_title_txt.*?>(.*?)</h1>',re.S)
        #pattern = re.compile('<h3.*?>(.*?)</h3>',re.S)

        #_compile(pattern, flags).search(string)報錯就修改，加str
        #result = re.search(pattern,str(page))

        #findall得到的result是list結構的
        result = re.findall(pattern,page)
        if result:
            #print result.group(1)  #測試輸出
            #return result.group(1).strip()
            #print result.encode('utf-8')
            """
            因爲result是list，只有一維的
            for i in range(len(result)):
                for j in range(len(result[i])):
                    print result[i][j].encode('utf-8')

                  """
            for i in range(len(result)):   
                print '標題:'+ result[i].encode('utf-8') + '\n'
                self.file = open(result[i]+ ".txt","w+")
                self.file.writelines(result[i].encode('utf-8') + '\n')
            self.file.close()
            #print result        
            return result[0]
        else:
            return None
    

    #   獲取帖子一共有多少頁
    def getPageNum(self):
        page = self.getPage(1)
        pattern = re.compile('<li class="l_reply_num.*?</span>.*?<span class="red">(.*?)</span>',re.S)
        #result = re.search(pattern,page)
        result = re.findall(pattern,page)
        if result:
            #print result.group(1)  #測試輸出
            #return result.group(1).strip()
            #for i in range(len(result)):   
            #    print result[i].encode('utf-8')
            #print result        
            return result[0].encode('utf-8')
        else:
            return None

    #獲取每一層樓的內容,傳入頁面內容
    def getContent(self):
        page = self.getPage(1)
        #pattern = re.compile('<div id="post_content_.*?>(.*?)</div>',re.S)
        #l_post l_post_bright j_l_post clearfix  
        #pattern = re.compile('<div class="l_post l_post_bright j_l_post clearfix.*?>(.*?)</div>',re.S)
        #pattern = re.compile('<div id="post_content_.*?class="d_post_content j_d_post_content.*?img class=.*?>(.*?)</dic>',re.S)
        #pattern = re.compile('<div class="p_content ">(.*?)</div>',re.S)
        pattern = re.compile('<div id="post_content.*?>(.*?)</div>',re.S)
        
        items = re.findall(pattern,page)
        #print len(items)

        floor = 1
        #a表示追加模式寫入txt
        self.file = open(self.getTitle()+ ".txt","a")
        
        for i in range(len(items)):
            #print floor,u"樓---------------------------------------\n"
            self.file.write(str(floor)+ '樓---------------------------------------\n')
            floor += 1
            #print self.tool.replace(items[i].encode('utf-8'))
            self.file.write(self.tool.replace(items[i].encode('utf-8')) + '\n\n')
            print '正在寫入第'+str(floor-1)+'樓...'
            
        self.file.close()
 
#baseURL = 'http://tieba.baidu.com/p/3138733512'
#baseURL = 'http://tieba.baidu.com/p/4399969515'
#baseURL = 'http://tieba.baidu.com/p/4400019865'

baseURL = 'http://tieba.baidu.com/p/4075653034'

#下面參數0表示看所有信息，1表示只看樓主信息
bdtb = BDTB(baseURL,0)

#bdtb.getPage(1)
#print bdtb.getTitle()
print '該貼吧總共有'+ str(bdtb.getPageNum()) + '頁'
bdtb.getContent()