Python抓取熊猫TV分类下的主播人气排名

抓取LOL分类下的主播人气排名情况:

"""
抓取熊猫TV当前分类主播人气排名
"""
import re
from urllib import request

class Spider():
    url = 'https://www.panda.tv/cate/lol'
    # 正则匹配，匹配两个div之间所有的字符(包含主播昵称和主播人气)，并且是非贪婪(因为后面有很多个</div>，所以用非贪婪模式)
    root_pattern = '<div class="video-info">([\s\S]*?)</div>'
    # 匹配主播昵称
    name_pattern = '</i>([\s\S]*?)</span>'
    # 匹配主播人气
    number_pattern = '<span class="video-number">([\s\S]*?)</span>'

    def __fetch_content(self):
        r = request.urlopen(Spider.url)
        htmls = r.read()
        # 转成字符串
        htmls = str(htmls, encoding='utf-8')
        return htmls

    def __analusis(self, htmls):
        """
        正则提取数据
        :param htmls:
        :return:
        """
        root_html = re.findall(spider.root_pattern, htmls)

        anchors = []
        for html in root_html:
            name = re.findall(spider.name_pattern, html)
            number = re.findall(spider.number_pattern, html)
            anchor = {'name': name, 'number': number}
            anchors.append(anchor)

        return anchors


    def __refine(self, anchors):
        """
        数据精炼，将一些不需要的数据给清除，数据结构再处理
        内置函数strip去除换行符
        :param anchors:
        :return:
        """
        l = lambda anchor: {
            'name': anchor['name'][0].strip(),
            'number': anchor['number'][0]
        }

        return map(l, anchors)


    def __sort(self, anchors):
        """
        数据进行排序处理,按照倒序(reverse=True)排序，
        :param anchors:
        :return: 返回倒序后的结果
        """
        anchors = sorted(anchors, key=self.__sort_seed, reverse=True)
        return anchors

    def __sort_seed(self, anchor):
        """
        返回一个可以进行比较运算的元素
        :param anchor:
        :return:
        """
        r = re.findall('\d*', anchor['number'])
        number = float(r[0])
        if '万' in anchor['number']:
            number *= 10000
        return number

    def __show(self, anchors):
        """
        展示数据
        :param anchors:
        :return:
        """
        for rank in range(0, len(anchors)):
            print('rank ' + str(rank + 1)
                  + '  : ' + anchors[rank]['name']
                  + '    ' + anchors[rank]['number'] + '人')

    def go(self):
        htmls = self.__fetch_content()
        anchors = self.__analusis(htmls)
        anchors = list(self.__refine(anchors))
        anchors = self.__sort(anchors)
        self.__show(anchors)


spider = Spider()
result = spider.go()

尽量少一点嵌套函数，平级函数好点
代码的行数控制在10-20行直接，最多尽量不要超过20行
了解BeautifulSoup，和Scrapy框架