老师我抓取的全部直播这个页面 由于推荐位的关系 前面几个抓取的人数是空的列表“【】”

下面是代码

import re

from urllib import request

# 断点调试

class Spider():

url = 'https://www.douyu.com/directory/all'

root = '<div class="mes">([\s\S]*?)</p>'

root_name = '<span class="dy-name ellipsis fl">([\s\S]*?)</span>'

root_number = '<span class="dy-num fr">([\w\W]*?)</span>'

def __fetch_content(self):

headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'

}

req = request.Request(url = Spider.url, headers=headers)

htmls = request.urlopen(req).read()

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

a = 1

return htmls

def __analysis(self,htmls):

root_html = re.findall(Spider.root,htmls)

anchors = []

for html in root_html:

name = re.findall(Spider.root_name,html)

number = re.findall(Spider.root_number,html)

anchor = {'name':name,'number':number}

anchors.append(anchor)

return anchors

def __refine(self,anchors):

x = lambda anchor:{'name':anchor['name'][0],

'number':anchor['number'][0]}

return map(x,anchors)

def __sort(self,anchors):

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

return anchors

def __sort_seed(send,anchor):

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

number = float(r[0])

if '万' in anchor['number']:

number *=10000

return number

def __sort_show(self,anchors):

for anchor in anchors:

print(anchor['name']+'..........'+anchor['number'])

def go(self):

htmls = self.__fetch_content()

anchors = self.__analysis(htmls)

anchors = list(self.__refine(anchors))

anchors = self.__sort(anchors)

self.__sort_show(anchors)

spider = Spider()

spider.go()