百度贴吧的内容的爬取，以一个NBA吧的实例，在python3.6上，IDE是pycharm，最新的正则。

import urllib import re from urllib import request #处理页面标签类 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() class BDTB: def __init__(self,baseUrl,seeLZ,floorTag): self.baseURL = baseUrl self.seeLZ = '?see_lz='+str(seeLZ) self.tool = Tool() self.file = None # 楼层标号，初始为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 def getPage(self,pageNum): try: url = self.baseURL+self.seeLZ+'&pn='+str(pageNum) request = urllib.request.Request(url) response = urllib.request.urlopen(request) #print(response.read().decode('utf-8')) content = response.read().decode('utf-8') return content except urllib.error.URLError as e: if hasattr(e, "reason"): print(u"连接百度贴吧失败,错误原因", e.reason) return None def getTitle(self, page): #print(page) pattern = re.compile('<h3 class="core_title_txt.*?>(.*?)</h3>', re.S) result = re.search(pattern, str(page)) if result: #print(result.group(1)) return result.group(1).strip() else: return None def getPageNum(self, indexPage): pattern = re.compile('<span class="red">(.*?)</span>', re.S) result = re.search(pattern, indexPage) if result: #print(result.group(1)) return result.group(1).strip() else: return None def getContent(self, page): pattern = re.compile('<div id="post_content_.*?>(.*?)</div>', re.S) items = re.findall(pattern, page) floor = 1 contents = [] #items_res = list() for item in items: content ='\n'+self.tool.replace(item)+'\n' contents.append(content) #print(floor,u'楼-----------------------------------------------------\n') #items_res.append(self.tool.replace(item)) #print(self.tool.replace(item)) floor += 1 return contents def write(self, contents): for item in contents: filename = 'tieba.txt' with open(filename, 'a') as file_object: if self.floorTag == '1': # 楼之间的分隔符 floorLine = "\n" + str( self.floor) + u"-----------------------------------------------------------------------------------------\n" file_object.write(floorLine) file_object.write(str(item)) self.floor += 1 def start(self): indexPage = self.getPage(1) #print(indexPage) pageNum = self.getPageNum(indexPage) title = self.getTitle(indexPage) 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.write(contents) except IOError as e: print("写入异常，原因" + e.message) finally: print("写入任务完成") # batb = BDTB(baseURL, 1,1) # print(batb.getPage(1)) # print(u'请输入帖子网址') # baseurl = input(u'请输入帖子网址:') # seeLZ = input("是否只获取楼主发言，是输入1，否输入0\n") # floorTag = input("是否写入楼层信息，是输入1，否输入0\n") # bdtb = BDTB(baseurl, seeLZ) # bdtb.start() #baseURL = 'https://tieba.baidu.com/p/' + str(input(u'https://tieba.baidu.com/p/')) baseURL = 'https://tieba.baidu.com/p/3138733512' seeLZ = input("是否只获取楼主发言，是输入1，否输入0\n") floorTag = input("是否写入楼层信息，是输入1，否输入0\n") bdtb = BDTB(baseURL,seeLZ,floorTag) bdtb.start()