python爬取NBA数据

import requests
from lxml import etree

1.地址,获取headers

url="https://nba.hupu.com/stats/players"
headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36'}

2.发送请求

resp=requests.get(url,headers=headers)

3.处理结果

e = etree.HTML(resp.text)


nos=e.xpath('//table[@class="players_table"]//tr//td[1]//text()')
names=e.xpath('//table[@class="players_table"]//tr/td[2]/a/text()')
teams=e.xpath('//table[@class="players_table"]//tr/td[3]/a/text()')
scores=e.xpath('//table[@class="players_table"]//tr/td[4]/text()') #注意这里是没有a标签的

4.解析响应数据,并保存

with open("nba.txt",mode="w",encoding="utf-8") as f:
    i=0;
    for no, name, team, score in zip(nos[1:], names, teams, scores[1:]):



        # print(f'名次:{no}  姓名:{name}  球队:{team}  分数:{score}')

 	f.write(f'名次:{no}  姓名:{name}  球队:{team}  分数:{score}\n')