python编写网络爬虫程序

    工作了，需要抓取一些特定的资源进行分析。没有高速海量数据那么大的需求。所以想到用python直接写一个简单的爬虫，之后再编写模板进行定向解析，就解决问题了。毕竟我们的时间要求和数量级要求不是很高。

    在网上搜索了一些python编写爬虫的文档，下载下来试试，看看效果。虽然我的这篇文章标明是原创，但是文章中也有一部分是参考了别人的信息，请谅解。因为我是想参考别人的精华，组合重构，来实现我需要的系统。

    先是从网上下载一个别人编写的爬虫试试效果，网址如下：http://blog.csdn.net/cashey1991/article/details/6262704

Test.py

# -*- coding: utf-8 -*-
import WebCrawler

url = raw_input('设置入口url(例-->http://www.baidu.com): \n')
thNumber = int(raw_input('设置线程数:'))    #之前类型未转换出bug
Maxdepth = int(raw_input('最大搜索深度：'))

wc = WebCrawler.WebCrawler(thNumber, Maxdepth)
wc.Craw(url)

WebCrawler.py

# -*- coding: utf-8 -*-
import threading
import GetUrl
import urllib

g_mutex = threading.Lock()
g_pages = []      #线程下载页面后，将页面内容添加到这个list中
g_dledUrl = []    #所有下载过的url
g_toDlUrl = []    #当前要下载的url
g_failedUrl = []  #下载失败的url
g_totalcount = 0  #下载过的页面数

class WebCrawler:
    def __init__(self,threadNumber,Maxdepth):
        self.threadNumber = threadNumber
        self.threadPool = []
        self.Maxdepth = Maxdepth
        self.logfile = file('#log.txt','w')                                   ##

    def download(self, url, fileName):
        Cth = CrawlerThread(url, fileName)
        self.threadPool.append(Cth)
        Cth.start()

    def downloadAll(self):
        global g_toDlUrl
        global g_totalcount
        i = 0
        while i < len(g_toDlUrl):
            j = 0
            while j < self.threadNumber and i + j < len(g_toDlUrl):
                g_totalcount += 1    #进入循环则下载页面数加1
                self.download(g_toDlUrl[i+j],str(g_totalcount)+'.htm')
                print 'Thread started:',i+j,'--File number = ',g_totalcount
                j += 1
            i += j
            for th in self.threadPool:
                th.join(30)     #等待线程结束，30秒超时
            self.threadPool = []    #清空线程池
        g_toDlUrl = []    #清空列表

    def updateToDl(self):
        global g_toDlUrl
        global g_dledUrl
        newUrlList = []
        for s in g_pages:
            newUrlList += GetUrl.GetUrl(s)   #######GetUrl要具体实现
        g_toDlUrl = list(set(newUrlList) - set(g_dledUrl))    #提示unhashable
                
    def Craw(self,entryUrl):    #这是一个深度搜索，到g_toDlUrl为空时结束
        g_toDlUrl.append(entryUrl)
        self.logfile.write('>>>Entry:\n')                                      ##
        self.logfile.write(entryUrl)                                           ##
        depth = 0
        while len(g_toDlUrl) != 0 and depth <= self.Maxdepth:
            depth += 1
            print 'Searching depth ',depth,'...\n\n'
            self.downloadAll()
            self.updateToDl()
            content = '\n>>>Depth ' + str(depth)+':\n'                         ##
            self.logfile.write(content)                                        ##
            i = 0                                                              ##
            while i < len(g_toDlUrl):                                          ##
                content = str(g_totalcount + i + 1) + '->' + g_toDlUrl[i] + '\n'#   ##
                self.logfile.write(content)                                    ##
                i += 1                                                         ##
         
class CrawlerThread(threading.Thread):
    def __init__(self, url, fileName):
        threading.Thread.__init__(self)
        self.url = url    #本线程下载的url
        self.fileName = fileName

    def run(self):    #线程工作-->下载html页面
        global g_mutex
        global g_failedUrl
        global g_dledUrl
        try:
            f = urllib.urlopen(self.url)
            s = f.read()
            fout = file(self.fileName, 'w')
            fout.write(s)
            fout.close()
        except:
            g_mutex.acquire()    #线程锁-->锁上
            g_dledUrl.append(self.url)
            g_failedUrl.append(self.url)
            g_mutex.release()    #线程锁-->释放
            print 'Failed downloading and saving',self.url
            return None    #记着返回!
        
        g_mutex.acquire()    #线程锁-->锁上
        g_pages.append(s)
        g_dledUrl.append(self.url)
        g_mutex.release()    #线程锁-->释放

GetUrl.py

# -*- coding: cp936 -*- 
urlSep = ['<','>','//','(',')', r'"', r"'", ' ', '\t', '\n']
urlTag = ['http://']

def is_sep(ch):
    for c in urlSep:
        if c == ch:
            return True
    return False

def find_first_sep(i,s):
    while i < len(s):
        if is_sep(s[i]):
            return i
        i+=1
    return len(s)

def GetUrl(strPage):
    rtList = []
    for tag in urlTag:
        i = 0
        i = strPage.find(tag, i, len(strPage))
        while i != -1:
            begin = i
            end = find_first_sep(begin+len(tag),strPage)
            rtList.append(strPage[begin:end])
            i = strPage.find(tag, end, len(strPage))

    return rtList