python 写的一个爬虫程序源码

#-*- coding:utf-8 -*-
#!/usr/local/bin/python
import sys, time, os,string
import mechanize
import urlparse
from BeautifulSoup import BeautifulSoup
import re
import MySQLdb
import logging
import cgi
from optparse import OptionParser
#----------------------------------------------------------------------------#
# Name:    TySpider.py                              #
# Purpose:   WebSite Spider Module                     #
# Author:   刘天斯                                   #
# Email:    liutiansi@gamil.com                         #
# Created:   2010/02/16                              #
# Copyright:  (c) 2010                                #
#----------------------------------------------------------------------------#


"""
|--------------------------------------------------------------------------
| 定义 loging class;
|--------------------------------------------------------------------------
|
| 功能：记录系统相关日志信息。
| 
|
"""
class Pubclilog():
  def __init__(self):
    self.logfile = 'website_log.txt'

  def iniLog(self):
    logger = logging.getLogger()
    filehandler = logging.FileHandler(self.logfile)
    streamhandler = logging.StreamHandler()
    fmt = logging.Formatter('%(asctime)s, %(funcName)s, %(message)s')
    logger.setLevel(logging.DEBUG) 
    logger.addHandler(filehandler) 
    logger.addHandler(streamhandler)
    return [logger,filehandler]


"""
|--------------------------------------------------------------------------
| 定义 tySpider class;
|--------------------------------------------------------------------------
|
| 功能：抓取分类、标题等信息
| 
|
"""
class BaseTySpider:

  #初始化相关成员方法
  def __init__(self,X,log_switch):

    #数据库连接
    self.conn = MySQLdb.connect(db='dbname',host='192.168.0.10', user='dbuser',passwd='SDFlkj934y5jsdgfjh435',charset='utf8')

    #分类及标题页面Community
    self.CLASS_URL = 'http://test.abc.com/aa/CommTopicsPage""

    #self.bodySoup对象
    self.soup=None

    #发表回复页下载内容变量
    self.Contentbody=""

    #发表回复页内容self.ContentbodySoup对象
    self.Contentsoup=None

    #日志开关
    self.log_switch=log_switch


  #======================获取名称及分类方法==========================
  def _SpiderClass(self,nextpage=None):
    if nextpage==None:
      FIXED_QUERY = 'cmm='+str(self.X)
    else:
      FIXED_QUERY = nextpage[1:]

    try:
      rd = mechanize.Browser()
      rd.addheaders = [("User-agent", "Tianya/2010 (compatible; MSIE 6.0;Windows NT 5.1)")]
      rd.open(self.CLASS_URL + FIXED_QUERY)
      self.body=rd.response().read()
      #rd=mechanize.Request(self.CLASS_URL + FIXED_QUERY)
      #response = mechanize.urlopen(rd)
      #self.body=response.read()

    except Exception,e:
      if self.log_switch=="on":
        logapp=Pubclilog()
        logger,hdlr = logapp.iniLog()
        logger.info(self.CLASS_URL + FIXED_QUERY+str(e))
        hdlr.flush()
        logger.removeHandler(hdlr)
        return
    self.soup = BeautifulSoup(self.body)
    NextPageObj= self.soup("a", {'class' : re.compile("fs-paging-item fs-paging-next")})
    self.cursor = self.conn.cursor()
    if nextpage==None:
      try:
        Ttag=str(self.soup.table)
        #print Ttag

        """
        ------------------分析结构体-----------------
        <table cellspacing="0" cellpadding="0">
          <tr>
            <td>
              <h1 title="Dunhill">Dunhill</h1>
            </td>
            <td valign="middle">
              <div class="fs-comm-cat">
                <span class="fs-icons fs-icon-cat"> </span> <a href="TopByCategoryPage">中国</a> » <a href="TopByCategoryPage">人民</a>
              </div>
            </td>
          </tr>
        </table>
        """

        soupTable=BeautifulSoup(Ttag)

        #定位到第一个h1标签
        tableh1 = soupTable("h1")
        #print self.X
        #print "Name:"+tableh1[0].string.strip().encode('utf-8')

        #处理无类型的
        try:
          #定位到表格中符合规则“^TopByCategory”A链接块，tablea[0]为第一个符合条件的连接文字，tablea[1]...
          tablea = soupTable("a", {'href' : re.compile("^TopByCategory")})
          if tablea[0].string.strip()=="":
            pass
          #print "BigCLass:"+tablea[0].string.strip().encode('utf-8')
          #print "SubClass:"+tablea[1].string.strip().encode('utf-8')
        except Exception,e:
          if self.log_switch=="on":
            logapp=Pubclilog()
            logger,hdlr = logapp.iniLog()
            logger.info("[noClassInfo]"+str(self.X)+str(e))
            hdlr.flush()
            logger.removeHandler(hdlr)
          self.cursor.execute("insert into baname"+str(self.mod)+" values('%d','%d','%s')" %(self.X,-1,tableh1[0].string.strip().encode('utf-8')))
          self.conn.commit() 
          self._SpiderTitle()
          if NextPageObj:
            NextPageURL=NextPageObj[0]['href']
            self._SpiderClass(NextPageURL)
            return
          else:
            return


        #获取链接二对象的href值
        classlink=tablea[1]['href']
        par_dict=cgi.parse_qs(urlparse.urlparse(classlink).query)
        #print "CID:"+par_dict["cid"][0]
        #print "SubCID:"+par_dict["subcid"][0]
        #print "---------------------------------------"
        
        #插入数据库
        self.cursor.execute("insert into class values('%d','%s')" %(int(par_dict["cid"][0]),tablea[0].string.strip().encode('utf-8')))
        self.cursor.execute("insert into subclass values('%d','%d','%s')" %(int(par_dict["subcid"][0]),int(par_dict["cid"][0]),tablea[1].string.strip().encode('utf-8'))) 
        self.cursor.execute("insert into baname"+str(self.mod)+" values('%d','%d','%s')" %(self.X,int(par_dict["subcid"][0]),tableh1[0].string.strip().encode('utf-8')))
        self.conn.commit() 
        
        self._SpiderTitle()
        if NextPageObj:
          NextPageURL=NextPageObj[0]['href']
          self._SpiderClass(NextPageURL)

        self.body=None
        self.soup=None
        Ttag=None
        soupTable=None
        table=None
        table1=None
        classlink=None
        par_dict=None
      except Exception,e:
        if self.log_switch=="on":
          logapp=Pubclilog()
          logger,hdlr = logapp.iniLog()
          logger.info("[ClassInfo]"+str(self.X)+str(e))
          hdlr.flush()
          logger.removeHandler(hdlr)
    else:
      self._SpiderTitle()
      if NextPageObj:
        NextPageURL=NextPageObj[0]['href']
        self._SpiderClass(NextPageURL)




  #====================获取标题方法=========================
  def _SpiderTitle(self):
    #查找标题表格对象(table)
    soupTitleTable=self.soup("table", {'class' : "fs-topic-list"})
    
    #查找标题行对象(tr)
    TitleTr = soupTitleTable[0]("tr", {'onmouseover' : re.compile("^this\.className='fs-row-hover'")})
    """
    -----------分析结构体--------------
    <tr class="fs-alt-row" onmouseover="this.className='fs-row-hover'" onmouseout="this.className='fs-alt-row'">
      <td valign="middle" class="fs-hot-topic-dots-ctn">
        <div class="fs-hot-topic-dots" style="background-position:0 -0px" title="点击量：12"></div>
      </td>
      <td valign="middle" class="fs-topic-name">
        <a href="CommMsgsPage" id="a53" title="【新人报到】欢迎美国人民加入" target="_blank">【新人报到】欢迎美国人民加入</a>
        <span class="fs-meta">
        <span class="fs-icons fs-icon-mini-reply"> </span>0
         /
         <span class="fs-icons fs-icon-pageview"> </span>12</span>
      </td>
      <td valign="middle">
        <a class="fs-tiny-user-avatar umhook " href="ProfilePage" title="中国人"><img src="/UploadFiles/2021-04-08/s.jpg">