Python3简单的爬虫项目 爬取虎牙主播名字 人气

代码

from urllib import request
import re

class Spider():

    url='https://www.huya.com/g/wzry'
    #正则
    root_pattern='<span class="txt">([\s\S]*?)</div>'
    name_pattern='<i class="nick" title="([\s\S]*?)">([\s\S]*?)</i>'
    number_pattern='<i class="js-num">([\s\S]*?)</i>'

    #获取要爬取的html
    def __fetch_content(self):
        r=request.urlopen(Spider.url)
        #bytes
        htmls=r.read()
        htmls=str(htmls,encoding='utf-8')
        return htmls

    #正则匹配
    def __analysis(self,htmls):
        root_html=re.findall(Spider.root_pattern,htmls)
        #列表
        anchors=[]
        for html in root_html:
            name=re.findall(Spider.name_pattern,html)
            number=re.findall(Spider.number_pattern,html)
            #字典
            anchor={'name':name[0],'number':number}
            anchors.append(anchor)
        print(anchors[0])
        return anchors

    #过滤空格以及换行符
    def __refine(self,anchors):
        #lambda表达式 简化函数
        l=lambda anchor:{
            'name':anchor['name'][0],
            'number':anchor['number'][0]
        }
        #映射函数，依次作用
        return map(l,anchors)
    def __sort(self,anchors):
        #filter,对列表进行迭代排序,指定number进行排序
        anchors=sorted(anchors,key=self.__sort_seed)
        return anchors

    def __sort_seed(self,anchor):
        return anchor['number']

    #迭代遍历
    def __show(self,anchors):
        for anchor in anchors:
            print(anchor['name']+'----'+anchor['number'])

          
 
    #入口函数 其他带有__开头的函数均为私有函数
    def go(self):
        htmls=self.__fetch_content()
        anchors=self.__analysis(htmls)
        anchors=list(self.__refine(anchors))
        anchors=self.__sort(anchors)
        self.__show(anchors)
spider=Spider()
spider.go()

爬取的HTML参考

结果