python爬取NBA湖人队球星的数据，并且用Excel保存

前言

本文章教你如何爬取NBA湖人球队的球员信息

一、使用步骤

1.1引入库

import xlwt
import requests
import re
from bs4 import BeautifulSoup
import time

1.2引入代码

def main():
    url = 'https://nba.hupu.com/players/lakers'#解析数据
    datalist = get_data(url)
    saveData(datalist)
def get_data(url):
    datalist = []
    datatitle = []
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.96 Safari/537.36 Edg/88.0.705.56'
    }
    html = requests.get(url,headers).text #
    bs = BeautifulSoup(html,'html.parser')
    for item in bs.find_all('tr'):
        data = []
        for items in item.find_all('td'):
            data.append(items.string)
        datalist.append(data)
    return datalist
def saveData(datalist):
    workbook = xlwt.Workbook(encoding='utf-8')
    worksheet = workbook.add_sheet('sheet1')
    for i in range(0,len(datalist[0])-3):
        worksheet.write(0,i,datalist[0][i+2])
    for k in range(0,len(datalist)-1):
        for j in range(0,5):
            worksheet.write(k+1,j,datalist[k+1][j+2])
    workbook.save('球星数据.xls')

1.3引入完整代码

import xlwt
import requests
import re
from bs4 import BeautifulSoup
import time


def main():
    url = 'https://nba.hupu.com/players/lakers'#解析数据
    datalist = get_data(url)
    saveData(datalist)
def get_data(url):
    datalist = []
    datatitle = []
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.96 Safari/537.36 Edg/88.0.705.56'
    }
    html = requests.get(url,headers).text #
    bs = BeautifulSoup(html,'html.parser')
    for item in bs.find_all('tr'):
        data = []
        for items in item.find_all('td'):
            data.append(items.string)
        datalist.append(data)
    return datalist
def saveData(datalist):
    workbook = xlwt.Workbook(encoding='utf-8')
    worksheet = workbook.add_sheet('sheet1')
    for i in range(0,len(datalist[0])-3):
        worksheet.write(0,i,datalist[0][i+2])
    for k in range(0,len(datalist)-1):
        for j in range(0,5):
            worksheet.write(k+1,j,datalist[k+1][j+2])
    workbook.save('球星数据.xls')

1.4总结

1.首先引入函数库，定义主函数main()
2.再获取网页，然后再解析网页,定义getData()函数
3.再就是通过find()函数来查找标签
4.最后就是保存数据啦，千万记得save()末尾一定要加.xls才能保存是Excel的文件