爬虫获取列表是空列表

Question

from urllib import request

import re

class Spider():

    url = 'https://www.huya.com/g/lol'

    root_pattern = '<span class="txt">([\s\S]*?)</span>'

    name_pattern = ' <i class="nick" title="">[\s\S]</i>'

    number_pattern= '<span class="num">([\s\S])</span>'

    def __fetch_content(self):

        r = request.urlopen(Spid

er.url)

        htmls = r.read()

        htmls = str(htmls, encoding='utf-8')

        return htmls

    def __analysis(self,htmls):

        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}

            anchors.append(anchor)

        return anchors

    def __refine(self,anchors):

        l= lambda anchor: {

        'name':anchor['name'][0].strip(),

        'number':anchor['number'][0]

        }

        return map(l,anchors)

    def __soft(self,anchors):

        anchors = sorted(anchors,key=self.__soft_seed,reverse=True)

        return anchors

    def __soft_seed(self,anchor):

        r = re.findall('\d',anchor['number'])

        number = float(r[0])

        if '万' in anchor['number']:

            number *=10000

        return number

    def __show(self,anchors):

        for rank in range(0,len(anchors)):

            print('rank'+str(rank+1))

            +'  :  '+anchors[rank]['name']

            +'     '+anchors[rank]['number']

    def go(self):

        htmls = self.__fetch_content()

        anchors=self.__analysis(htmls)

        anchors =list(self.__refine(anchors))

        anchors = self.__soft(anchors)

        self.__show(anchors)

spider = Spider()

spider.go()

Answer 1

无非两个方面的错误：没有抓取到目标页面正则错误，不能匹配到目标内容