1. 頁面分析

• ① 獲取每支球員頁面的url；
• ② 利用Python代碼獲取每個網(wǎng)頁中的數(shù)據(jù)；
• ③ 將獲取到的數(shù)據(jù)，存儲至不同的數(shù)據(jù)庫；

# 76人
https://nba.stats.qq.com/player/list.htm#teamId=20

# 火箭
https://nba.stats.qq.com/player/list.htm#teamId=10

# 熱火
https://nba.stats.qq.com/player/list.htm#teamId=14

部分截圖如下

2. 數(shù)據(jù)爬取

from selenium import webdriver

# 創(chuàng)建瀏覽器對象，該操作會自動幫我們打開Google瀏覽器窗口
browser = webdriver.Chrome()

# 調(diào)用瀏覽器對象，向服務(wù)器發(fā)送請求。該操作會打開Google瀏覽器，并跳轉(zhuǎn)到“百度”首頁
browser.get("https://nba.stats.qq.com/player/list.htm#teamId=20")

# 最大化窗口
browser.maximize_window()

# 獲取球員中文名
chinese_names = browser.find_elements_by_xpath('//div[@class="players"]//tr[@class="show"]/td[2]/a')
chinese_names_list  = [i.text for i in chinese_names]

# 獲取球員英文名
english_names = browser.find_elements_by_xpath('//div[@class="players"]//tr[@class="show"]/td[3]/a')
english_names_list = [i.get_attribute('title') for i in english_names] # 獲取屬性

# 獲取球員號碼
numbers = browser.find_elements_by_xpath('//div[@class="players"]//tr[@class="show"]/td[4]')
numbers_list = [i.text for i in numbers]

# 獲取球員位置
locations = browser.find_elements_by_xpath('//div[@class="players"]//tr[@class="show"]/td[5]')
locations_list = [i.text for i in locations]

# 獲取球員身高
heights = browser.find_elements_by_xpath('//div[@class="players"]//tr[@class="show"]/td[6]')
heights_list = [i.text for i in heights]

# 獲取球員體重
weights = browser.find_elements_by_xpath('//div[@class="players"]//tr[@class="show"]/td[7]')
weights_list = [i.text for i in weights]

# 獲取球員年齡
ages = browser.find_elements_by_xpath('//div[@class="players"]//tr[@class="show"]/td[8]')
ages_list = [i.text for i in ages_list]

# 獲取球員球齡
qiu_lings = browser.find_elements_by_xpath('//div[@class="players"]//tr[@class="show"]/td[9]')
qiu_lings_list = [i.text for i in qiu_lings_list]

3. 存儲至txt

for i in zip(chinese_names_list,english_names_list,numbers_list,locations_list,heights_list,weights_list,ages_list,qiu_lings_list):
    with open("NBA.txt","a+",encoding="utf-8") as f:
        # zip函數(shù)，得到的是一個元組，我們需要將它轉(zhuǎn)換為一個字符串
        f.write(str(i)[1:-1])
        # 自動換行，好寫入第2行數(shù)據(jù)
        f.write("\n")
        f.write("\n")

4. 存儲至excel

import pandas as pd

# 一定要學(xué)會組織數(shù)據(jù)
df = pd.DataFrame({"中文名": chinese_names_list,
                   "英文名": english_names_list,
                   "球員號碼": numbers_list,
                   "位置": locations_list,
                   "身高": heights_list,
                   "體重": weights_list,
                   "年齡": ages_list,
                   "球齡": qiu_lings_list})
 
# to_excel()函數(shù)
df.to_excel("NBA.xlsx",encoding="utf-8",index=None)

5. 存儲至mysql

① 創(chuàng)建一個表nba

import pymysql

# 1. 連接數(shù)據(jù)庫
db = pymysql.connect(host='localhost',user='root', password='123456',port=3306, db='demo', charset='utf8')

# 2. 創(chuàng)建一個表
# 創(chuàng)建一個游標(biāo)對象；
cursor = db.cursor()
 
# 建表語句；
sql = """
        create table NBA(
            chinese_names_list varchar(20),
            english_names_list varchar(20),
            numbers_list varchar(20),
            locations_list varchar(20),
            heights_list varchar(20),
            weights_list varchar(20),
            ages_list varchar(20),
            qiu_lings_list varchar(20)
        )charset=utf8
      """
# 執(zhí)行sql語句；
cursor.execute(sql)

# 斷開數(shù)據(jù)庫的連接；
db.close()

② 往表nba中插入數(shù)據(jù)

import pymysql

# 1. 組織數(shù)據(jù)
data_list = []
for i in zip(chinese_names_list,english_names_list,numbers_list,locations_list,heights_list,weights_list,ages_list,qiu_lings_list):
    data_list.append(i)

# 2. 連接數(shù)據(jù)庫
db = pymysql.connect(host='localhost',user='root', password='123456',port=3306, db='demo', charset='utf8')

# 創(chuàng)建一個游標(biāo)對象；
cursor = db.cursor()

# 3. 插入數(shù)據(jù)
sql = 'insert into nba(chinese_names_list,english_names_list,numbers_list,locations_list,heights_list,weights_list,ages_list,qiu_lings_list) values(%s,%s,%s,%s,%s,%s,%s,%s)'

try:
    cursor.executemany(sql,data_list)
    db.commit()
    print("插入成功")
except:
    print("插入失敗")
    db.rollback()
db.close()