很喜欢李狗嗨，四重奏，海女，就做了一个日剧豆瓣评分9.0以上的爬虫，很小的程序，仅供娱乐。

import re
import urllib2
class DouBanSpider() :
    def __init__(self) :    #这里是初始化参数，两个英文下划线
        self.number=1
        self.page = 1
        self.cur_url = "https://www.douban.com/doulist/3116346/?start={page}&sort=seq&sub_type="
        self.title = []
        self.score=  []
        self.info=[]
        self._top_num = 1
        self. filePath ="D:\demo\douban.txt"
        print "豆瓣爬虫准备就绪, 准备爬取数据..."

    def get_page(self, cur_page) :
        url = self.cur_url
        try :
            my_page = urllib2.urlopen(url.format(page = (cur_page - 1) * 25)).read()
        except urllib2.URLError, e :
            if hasattr(e, "code"):
                print "The server couldn't fulfill the request."
                print "Error code: %s" % e.code
            elif hasattr(e, "reason"):
                print "We failed to reach a server. Please check your url and read the Reason"
                print "Reason: %s" % e.reason
        return my_page

    def find_title(self, my_page) :#爬日剧名字
        pattern=re. compile(ur'<a href="https://movie.douban.com/subject/\d+/" target="_blank">\s*([\s\S]*?)\s', re.S)
        movie_items=pattern.findall(my_page)
        for movie in movie_items:
            if movie!='<img':
                self.title. append(movie)

    def find_score(self, my_page):#爬日剧评分
        pattern = re.compile(ur'</span>(\d.\d)', re.S)
        movie_items = pattern.findall(my_page)
        for score in movie_items:
            self.score.append(score)

    def find_info(self,my_page):#爬日剧信息                    
         pattern = re.compile(ur'<div class="abstract">\s*(.*?)</div>',re.S)
         movie_items = pattern.findall(my_page)
         for info in movie_items:
             self.info.append(info.replace('<br />',''))


    def write(self):#保存到文本文件
        f = open(self.filePath, 'w')
        for movie,score,info in zip(self.title,self.score,self.info):
            f.write('Top' +str(self.number)+'：'+ movie+ '\n')
            f.write('评分：'+score+'\n')
            f.write(info+'\n'+'\n')
            self.number+=1
        print"文件写入成功"
        f.close()


    def start_spider(self) :
        """
        爬虫入口, 并控制爬虫抓取页面的范围
        """
        while self.page <=3:
            my_page = self.get_page(self.page)
            self.find_title(my_page)
            self.find_score(my_page)
            self.find_info(my_page)
            self.page += 1




if __name__=="__main__":   #这里是主程序入口，两个英文下划线

    myspider = DouBanSpider()
    myspider.start_spider()
    myspider.write()

    print "豆瓣爬虫爬取结束..."

结果显示：

Paste_Image.png

Paste_Image.png