首页 > 代码库 > Python爬虫——抓取贴吧帖子
Python爬虫——抓取贴吧帖子
抓取百度贴吧帖子
按照这个学习教程,一步一步写出来,中间遇到很多的问题,一一列举
首先, 获得 标题 和 贴子总数
# -*- coding:utf-8 -*- #!/user/bin/python import urllib import urllib2 import re class BDTB: #初始化,传入基地址,是否只看楼主的参数 def __init__(self, baseUrl, seeLZ): self.baseURL = baseUrl self.seeLZ = ‘?see_lz=‘ + str(seeLZ) #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) return response.read() 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 def getTitle(self): 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) return result.group(1).strip() else: return None #得到帖子页数 def getPageNum(self): page = self.getPage(1) pattern = re.compile(‘<li class="l_reply_num.*?<span.*?>(.*?)</span‘,re.S) result = re.search(pattern, page) if result: print "回复个数:" print result.group(1) return result.group(1).strip() else: return None baseURL = ‘http://tieba.baidu.com/p/3138733512‘ bdtb = BDTB(baseURL, 1) bdtb.getTitle() bdtb.getPageNum()
PS:我用的火狐浏览器,查看网页源代码,鼠标右击查看 获得 快捷键 Ctrl-U
接下来 抓取 楼层的内容,写好的 程序如下
import urllib import urllib2 import re class BDTB: #初始化,传入基地址,是否只看楼主的参数 def __init__(self, baseUrl, seeLZ): self.baseURL = baseUrl self.seeLZ = ‘?see_lz=‘ + str(seeLZ) #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) return response.read() 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 def getTitle(self): 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) return result.group(1).strip() else: return None #得到帖子页数 def getPageNum(self): page = self.getPage(1) pattern = re.compile(‘<li class="l_reply_num.*?<span.*?>(.*?)</span‘,re.S) result = re.search(pattern, page) if result: print "回复个数:" print result.group(1) return result.group(1).strip() else: return None def getContent(self,page): pattern = re.compile(‘<div id="post_content_.*? class="d_post_content j_d_post_content ">(.*?)</div>‘,re.S) items = re.findall(pattern,page) for item in items: print item baseURL = ‘http://tieba.baidu.com/p/3138733512‘ bdtb = BDTB(baseURL, 1) bdtb.getTitle() bdtb.getPageNum() bdtb.getContent(1)
但是运行之后一直报错,如下图:
检查代码无数次后,终于.....发现 getContent中 没有获取页码 T_T 在这个函数首句加上
page = self.getPage(1)
即可!!!
终于得到了内容部分,用一下工具类 可将乱七八糟的图片什么的代码去掉
#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()
最后最后,就是这样的了..
# -*- coding:utf-8 -*- #!/user/bin/python import urllib import urllib2 import re #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: #初始化,传入基地址,是否只看楼主的参数 def __init__(self, baseUrl, seeLZ, floorTag): self.baseURL = baseUrl self.seeLZ = ‘?see_lz=‘ + str(seeLZ) self.tool = Tool() #全局file变量,文件写入操作对象 self.file = None #楼层标号, 初始化为1 self.floor = 1 #默认标题 self.defaultTitle = u"百度某某贴吧" #是否写入楼层分隔符标记 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) 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 #获得帖子标题 def getTitle(self,page): 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) return result.group(1).strip() else: return None #得到帖子页数 def getPageNum(self,page): page = self.getPage(1) pattern = re.compile(‘<li class="l_reply_num.*?<span.*?>(.*?)</span‘,re.S) result = re.search(pattern, page) if result: #print "回复个数:" #print result.group(1) return result.group(1).strip() else: return None #获得帖子的内容 def getContent(self,page): page = self.getPage(1) pattern = re.compile(‘<div id="post_content_.*?>(.*?)</div>‘,re.S) items = re.findall(pattern,page) contents = [] floor = 1 for item in items: content = "\n" + self.tool.replace(item) + "\n" contents.append(content.encode(‘utf-8‘)) #print self.tool.replace(item) #floor += 1 return contents def setFileTitle(self,title): if title is not None: self.file = open(title + ".txt", "w+") else: self.file = open(self.defaultTitle + ".txt", "w+") def writeData(self,contents): for item in contents: if self.floorTag == ‘1‘: floorline = "\n" + str(self.floor) + u"-------------------------------------\n" self.file.write(floorline) self.file.write(item) 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 "Succeed~" print u"请输入帖子代码" baseURL = ‘http://tieba.baidu.com/p/‘ + str(raw_input(u‘http://tieba.baidu.com/p/‘)) seeLZ = raw_input("是否只看楼主,是输入1,否输入0\\n") floorTag = raw_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()
关于decode和encode知识,查看 这个
关于raw_input, 查看 这个
Python爬虫——抓取贴吧帖子
声明:以上内容来自用户投稿及互联网公开渠道收集整理发布,本网站不拥有所有权,未作人工编辑处理,也不承担相关法律责任,若内容有误或涉及侵权可进行投诉: 投诉/举报 工作人员会在5个工作日内联系你,一经查实,本站将立刻删除涉嫌侵权内容。