昨天晚上为了下载保存某位csdn大牛的全部博文，写了一个爬虫来自动抓取文章并保存到txt文本，当然也可以 保存到html网页中。这样就可以不用Ctrl+C 和Ctrl+V了，，非常方便，抓取别的网站也是大同小异。
为了解析抓取的网页，用到了第三方模块，BeautifulSoup，这个模块对于解析html文件非常有用，当然也可以自己使用正则表达式去解析，但是比较麻烦。
由于csdn网站的robots.txt文件中显示禁止任何爬虫，所以必须把爬虫伪装成浏览器，而且不能频繁抓取，得sleep一会再抓，使用频繁会被封ip的，但可以使用代理ip。
#-*- encoding: utf-8 -*-'''Created on 2014-09-18 21:10:39@author: Mangoer@email: 2395528746@qq.com'''import urllib2import refrom bs4 import BeautifulSoupimport randomimport timeclass CSDN_Blog_Spider:def __init__(self,url):print '\n'print('已启动网络爬虫。。。')print '网页地址： ' + urluser_agents = ['Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11','Opera/9.25 (Windows NT 5.1; U; en)','Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)','Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Kubuntu)','Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12','Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9',"Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.7 (KHTML, like Gecko) Ubuntu/11.04 Chromium/16.0.912.77 Chrome/16.0.912.77 Safari/535.7","Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:10.0) Gecko/20100101 Firefox/10.0 ",]# use proxy ip# ips_list = ['60.220.204.2:63000','123.150.92.91:80','121.248.150.107:8080','61.185.21.175:8080','222.216.109.114:3128','118.144.54.190:8118',#'1.50.235.82:80','203.80.144.4:80']# ip = random.choice(ips_list)# print '使用的代理ip地址： ' + ip# proxy_support = urllib2.ProxyHandler({'http':''+ip})# opener = urllib2.build_opener(proxy_support)# urllib2.install_opener(opener)agent = random.choice(user_agents)req = urllib2.Request(url)req.add_header('User-Agent',agent)req.add_header('Host','blog.csdn.net')req.add_header('Accept','*/*')req.add_header('Referer','?viewmode=list')req.add_header('GET',url)html = urllib2.urlopen(req)page = html.read().decode('gbk','ignore').encode('utf-8')self.page = pageself.title = self.getTitle()self.content = self.getContent()self.saveFile()def printInfo(self):print('文章标题是： '+self.title + '\n')print('内容已经存储到out.txt文件中！')def getTitle(self):rex = re.compile('<title>(.*?)</title>',re.DOTALL)match = rex.search(self.page)if match:return match.group(1)return 'NO TITLE'def getContent(self):bs = BeautifulSoup(self.page)html_content_list = bs.findAll('div',{'id':'article_content','class':'article_content'})html_content = str(html_content_list[0])rex_p = re.compile(r'(?:.*?)>(.*?)<(?:.*?)',re.DOTALL)p_list = rex_p.findall(html_content)content = ''for p in p_list:if p.isspace() or p == '':continuecontent = content + preturn contentdef saveFile(self):outfile = open('out.txt','a')outfile.write(self.content)def getNextArticle(self):bs2 = BeautifulSoup(self.page)html_nextArticle_list = bs2.findAll('li',{'class':'prev_article'})# print str(html_nextArticle_list[0])html_nextArticle = str(html_nextArticle_list[0])# print html_nextArticlerex_link = re.compile(r'<a href=\&;(.*?)\&;',re.DOTALL)link = rex_link.search(html_nextArticle)# print link.group(1)if link:next_url = '' + link.group(1)return next_urlreturn Noneclass Scheduler:def __init__(self,url):self.start_url = urldef start(self):spider = CSDN_Blog_Spider(self.start_url)spider.printInfo()while True:if spider.getNextArticle():spider = CSDN_Blog_Spider(spider.getNextArticle())spider.printInfo()elif spider.getNextArticle() == None:print 'All article haved been downloaded!'breaktime.sleep(10)#url = input('请输入CSDN博文地址：')url = ""Scheduler(url).start()程序中有个问题一直不能解决：不能使用标题去命名文件，所以所有的文章全部放在一个out.txt中，说的编码的问题，希望大神可以解决这个问题。
偶尔为街头独特的风景驻足，
