bs4爬虫:获取百度贴吧的内容

一、 环境
   (1) windws 10
   (2)  python 2.7
   (3)  pycharm

二、详细代码

   (1)日志分析类 

import logging
import getpass
import sys


#### 定义MyLog类
class MyLog(object):
#### 类MyLog的构造函数
	def __init__(self):
		self.user = getpass.getuser()
		self.logger = logging.getLogger(self.user)
		self.logger.setLevel(logging.DEBUG)

####  日志文件名
		self.logFile = sys.argv[0][0:-3] + '.log'
		self.formatter = logging.Formatter('%(asctime)-12s %(levelname)-8s %(name)-10s %(message)-12s\r\n')

####  日志显示到屏幕上并输出到日志文件内
		self.logHand = logging.FileHandler(self.logFile, encoding='utf8')
		self.logHand.setFormatter(self.formatter)
		self.logHand.setLevel(logging.DEBUG)

		self.logHandSt = logging.StreamHandler()
		self.logHandSt.setFormatter(self.formatter)
		self.logHandSt.setLevel(logging.DEBUG)

		self.logger.addHandler(self.logHand)
		self.logger.addHandler(self.logHandSt)

####  日志的5个级别对应以下的5个函数
	def debug(self,msg):
		self.logger.debug(msg)

	def info(self,msg):
		self.logger.info(msg)

	def warn(self,msg):
		self.logger.warn(msg)

	def error(self,msg):
		self.logger.error(msg)

	def critical(self,msg):
		self.logger.critical(msg)

if __name__ == '__main__':
	mylog = MyLog()
	mylog.debug(u"I'm debug 测试中文")
	mylog.info("I'm info")
	mylog.warn("I'm warn")
	mylog.error(u"I'm error 测试中文")
	mylog.critical("I'm critical")

     (2)爬取的主类

import urllib2
from bs4 import BeautifulSoup
from mylog import MyLog as mylog


class Item(object):
    title = None    #帖子标题
    firstAuthor = None  #帖子创建者
    firstTime = None   #帖子创建时间
    reNum = None    #总回复数
    content = None  #最后回复内容
    lastAuthor = None   #最后回复者
    lastTime = None #最后回复时间
    

class GetTiebaInfo(object):
    def __init__(self,url):
        self.url = url
        self.log = mylog()
        self.pageSum = 5
        self.urls = self.getUrls(self.pageSum)
        self.items = self.spider(self.urls)
        self.pipelines(self.items)
        
    def getUrls(self,pageSum):
        urls = []
        pns = [str(i*50) for i in range(pageSum)]
        ul = self.url.split('=')
        for pn in pns:
            ul[-1] = pn
            url = '='.join(ul)
            urls.append(url)
        self.log.info(u'获取URLS成功')
        return urls

    def spider(self, urls):
        items = []
        for url in urls:
            htmlContent = self.getResponseContent(url)
            soup = BeautifulSoup(htmlContent, 'lxml')
            tagsli = soup.find_all('li',attrs={'class':' j_thread_list clearfix'})
            for tag in tagsli:
                item = Item()
                item.title = tag.find('a', attrs={'class':'j_th_tit'}).get_text().strip()
                item.firstAuthor = tag.find('span', attrs={'class':'frs-author-name-wrap'}).a.get_text().strip()
                item.firstTime = tag.find('span', attrs={'title':u'创建时间'.encode('utf8')}).get_text().strip()
                item.reNum = tag.find('span', attrs={'title':u'回复'.encode('utf8')}).get_text().strip()
                item.content = tag.find('div', attrs={'class':'threadlist_abs threadlist_abs_onlyline '}).get_text().strip()
                item.lastAuthor = tag.find('span', attrs={'class':'tb_icon_author_rely j_replyer'}).a.get_text().strip()
                item.lastTime = tag.find('span', attrs={'title':u'最后回复时间'.encode('utf8')}).get_text().strip()
                items.append(item)
                self.log.info(u'获取标题为<<%s>>的项成功 ...' %item.title)
        return items
    
    def pipelines(self, items):
        fileName = u'百度贴吧_权利的游戏.txt'.encode('GBK')
        with open(fileName, 'w') as fp:
            for item in items:
                fp.write('title:%s \t author:%s \t firstTime:%s \n content:%s \n return:%s \n lastAuthor:%s \t lastTime:%s \n\n\n\n' 
                         %(item.title.encode('utf8'),item.firstAuthor.encode('utf8'),item.firstTime.encode('utf8'),item.content.encode('utf8'),item.reNum.encode('utf8'),item.lastAuthor.encode('utf8'),item.lastTime.encode('utf8')))
                self.log.info(u'标题为<<%s>>的项输入到"%s"成功' %(item.title, fileName.decode('GBK')))

    def getResponseContent(self, url):
        '''这里单独使用一个函数返回页面返回值，是为了后期方便的加入proxy和headers等
        '''
        try:
            response = urllib2.urlopen(url.encode('utf8'))
        except:
            self.log.error(u'Python 返回URL:%s  数据失败' %url)
        else:
            self.log.info(u'Python 返回URUL:%s  数据成功' %url)
            return response.read()
    

if __name__ == '__main__':
    url = u'http://tieba.baidu.com/f?kw=权利的游戏&ie=utf-8&pn=50'
    GTI = GetTiebaInfo(url)

三、结果显示