Day 5 python 原生爬虫

尝试获取某知名直播平台姓名以及热度数据---需要更加熟练

import re
from urllib import request


# 端点调试
class Spider():
    url = 'https://www.huya.com/g/wzry'

    root_pattern = '<li class="game-live-item"> ([\s\S]*?) </li>'
    # name_pattern = '<i class="nick"> ([\s\S]*?) </i>'
    # num_pattern = '<i class="js-num"> ([\s\S]*?) </i>'


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


    def __analysis(self, htmls):
        root_html = re.findall(Spider.root_pattern, htmls)
        print(root_html[0])
        # anchors = []
        # for html in root_html:
        #     name=re.findall(Spider.name_pattern,html)
        #     number=re.findall(Spider.num_pattern,html)
        #     anchor = {'name':name,'number':number}
        #     anchors.append(anchor)
        # print(anchors[0])
        a = 1

    def go(self):
        htmls = self.__fetch_content()
        self.__analysis(htmls)
spider = Spider()
spider.go()