python如何爬取豆瓣各分类书单 - 大数据

pachon2.5.py      # -- coding: utf-8 --import urllibimport urllib2import reimport sys
reload(sys)
sys.setdefaultencoding('utf-8')
class book:     #豆瓣书籍的类    def init(self, types, page):        self.baseUrl = 'http://www.douban.com/tag/'        self.types = types        self.filename = 'doubanbook.txt'        self.page = page

def getContents(self): #爬取源代码    try:        #if self.page == 0:        url = self.baseUrl + self.types + '/book'        #else:        #   url = self.baseUrl + self.types + '/book?start=' + str(self.page)        user_agent = 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.65 Safari/537.36'        headers = { 'User-Agent' : user_agent}        request = urllib2.Request(url,headers = headers)        response = urllib2.urlopen(request)        content = response.read()  #.decode('utf-8')        pattern = re.compile('<a href=.*?class="title".*?target="_blank">(.*?)</a>.*?>(.*?)</div>',re.S)        items = re.findall(pattern,content)        return items    except urllib2.URLError, e:        if hasattr(e, "reason"):            print u"豆瓣链接错误，错误原因", e.reason            return None
def writetext(self, items): #写入txt    for item in items:        print item[0],item[1]        files = open(self.filename,'a')        files.write(item[0])        files.write(item[1])        files.write('\n')        files.close()
def strat(self): #启动函数    self.writetext(self.getContents())    print u"""出现乱码为正常现象，在与本脚本相同的文件夹下会多出一个,        doubanbook.txt的文件里面有所爬书籍，如你把本脚本放在桌面,文件便会出现在桌面"""        print u"结束输入 'O' , 联系作者输入 'A'"        end = raw_input('>')        if end == 'A':            print u"QQ邮箱:1021644861@qq.com"            raw_input('>')        else:            print "over"