爬取斗鱼直播(博主姓名和热度)
from urllib import request
import requests
from bs4 import BeautifulSoup
import re
class Spider():
url='https://www.douyu.com/g_LOL'
headers={
'User-Agent': 'Mozilla/5.0 (Windows NT'
' 10.0; Win64; x64) AppleWebKi'
't/537.36 (KHTML, like Gecko) '
'Chrome/64.0.3282.140 Safari/537.3'
'6 Edge/18.17763'}
root_pattern='<div class="DyListCover' \
'-info">[\s\S]*?</h2></div>'
name_pattern='<use xlink:href="#icon-user_c95a' \
'cf8"></use></svg>(.*?)</h2></div>'
number_pattern='<use xlink:href="#icon-hot_8a57f0b"></' \
'use></svg>(.*?)</span>'
def __fetch_content(self):
htmls=requests.get(Spider.url,headers=Spider.headers)
htmls=htmls.text
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,'number':number}
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 __sort(self,anchors):
anchors=sorted(anchors,key=self.__sort_seed,reverse=True)
return anchors
def __sort_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=self.__refine(anchors)
anchors=self.__sort(anchors)
self.__show(anchors)
spider=Spider()
spider.go()