python 爬取 某平台 LOL主播姓名+加人气，然后进行排序

import re

from urllib import request

class Spider():

#<div class="video-info">主播姓名+观看人数</div>

#<span class="video-nickname" title="">主播姓名</span>

#<span class="video-number">1704</span>

url = 'https://www.panda.tv/cate/lol'

root_pattern = '<div class="video-info">([\s\S]*?)</div>'

name_pattern = '</i>([\s\S]*?)</span>'

number_pattern = '<span class="video-number">([\s\S]*?)</span>'

#私有方法

def _fetch_content(self):

r = request.urlopen(Spider.url)

htmls = r.read()

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

return htmls

#实例方法

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, 'number':number}

anchors.append(anchor)

return anchors

a = 1

#私有方法数据精炼

def _refine(self,anchors):

l = lambda anchor:{

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

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

}

return map(l,anchors)

def _sort_seed(self,anchor):

#提取数字

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

number = float(r[ 0])

if '万' in anchor[ 'number']:

number *= 10000

return number

#按人气排序

def _sort(self,anchors):

#filter

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

return anchors

#展现数据

def _show(self,anchors):

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

print( 'rank ' + str(rank + 1)

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

+ ' ' + anchors[rank][ 'number'] + '人')

#入口,总控方法

def go(self):

htmls = self._fetch_content()

anchors = self._analysis(htmls)

anchors = list(self._refine(anchors))

anchors = self._sort(anchors)

self._show(anchors)

#实例化

spoder = Spider()

spoder.go()