python 爬取CSDN博客阅读量排行

自学python有了一段时间，终于成功敲出了自己第一个用python抓取网站数据的代码（这里抓取的是自己博客的数据），特此记录

from urllib import request
import re

class Spider():
    """
    爬取网站信息
    """
    root_pattern = '<div class="article-item-box csdn-tracking-statistics"([\s\S]*?)</div>'
    url = 'https://blog.csdn.net/LT11hka?spm=1000.2115.3001.5343'
    title_pattern = '原创</span>([\s\S]*?)</a>'
    readNum_pattern = '<img src="https://csdnimg.cn/release/blogv2/dist/pc/img/readCountWhite.png" alt="">([\s\S]*?)</span>'
    def __fetch_content(self):
        """
        docstring
        """
        r = request.urlopen(Spider.url)
        htmls = r.read()
        htmls = str(htmls, encoding='utf-8')
        return htmls

    def __analysis(self,htmls):
        """
        对抓取的html页面数据进行正则匹配
        """
        datas = []
        root_html = re.findall(Spider.root_pattern,htmls)
        for html in root_html:
            title = re.findall(Spider.title_pattern,html)
            readNum = re.findall(Spider.readNum_pattern,html)
            data = {'title':title,'num':readNum}
            datas.append(data)
        return datas

    def __refine(self,datas):
        """
        将抓取的数据进行美化
        """
        l = lambda data: {
            'title':data['title'][0].strip() if len(data['title']) != 0 else '无标题',
            'num':data['num'][0]
            }
        return map(l,datas)

    def __sort(self,datas):
        """
        排序
        """
        datas = sorted(datas,key=self.__sort_seed,reverse=True)
        # datas = sorted(datas,key=lambda data: int(data['num'][0]),reverse=True)
        return datas

    def __sort_seed(self,data):
        """
        自定义排序方法
        """
        # r = re.findall(data['num'][0])
        number = int(data['num'])
        return number

    def __show(self,datas):
        """
        数据展示
        """
        for rank in range(0,len(datas)):
            print('排名:' + str(rank + 1)
            + '   博客：' + datas[rank]['title']
            + '   阅读量：' + datas[rank]['num'])

    def go(self):
        """
        调用正则匹配方法获取想要抓取的数据
        """
        htmls = self.__fetch_content()
        datas = self.__analysis(htmls)
        datas = list(self.__refine(datas))
        datas = self.__sort(datas)
        self.__show(datas)
        
#执行
spider = Spider()
spider.go()

效果如下：

做一条有梦想的咸鱼！！！奥利给！！！