小編給大家分享一下如何使用Python實(shí)現(xiàn)爬蟲爬取NBA數(shù)據(jù)功能，希望大家閱讀完這篇文章之后都有所收獲，下面讓我們一起去探討吧！
具體如下：
爬取的網(wǎng)站為：stat-nba.com，這里爬取的是NBA2016-2017賽季常規(guī)賽至2017年1月7日的數(shù)據(jù)
改變url_header和url_tail即可爬取特定的其他數(shù)據(jù)。
源代碼如下：
重慶分公司
重慶分公司
#coding=utf-8
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
import requests
import time
import urllib
from bs4 import BeautifulSoup
import re
from pyExcelerator import *
def getURLLists(url_header,url_tail,pages):
"""
獲取所有頁面的URL列表
"""
url_lists = []
url_0 = url_header+'0'+url_tail
print url_0
url_lists.append(url_0)
for i in range(1,pages+1):
url_temp = url_header+str(i)+url_tail
url_lists.append(url_temp)
return url_lists
def getNBAAllData(url_lists):
"""
獲取所有2017賽季NBA常規(guī)賽數(shù)據(jù)
"""
datasets = ['']
for item in url_lists:
data1 = getNBASingleData(item)
datasets.extend(data1)
#去掉數(shù)據(jù)里的空元素
for item in datasets[:]:
if len(item) == 0:
datasets.remove(item)
return datasets
def getNBASingleData(url):
"""
獲取1個頁面NBA常規(guī)賽數(shù)據(jù)
"""
# url = 'http://stat-nba.com/query_team.php?QueryType=game&order=1&crtcol=date_out&GameType=season&PageNum=3000&Season0=2016&Season1=2017'
# html = requests.get(url).text
html = urllib.urlopen(url).read()
# print html
soup = BeautifulSoup(html)
data = soup.html.body.find('tbody').text
list_data = data.split('\n')
# with open('nba_data.txt','a') as fp:
# fp.write(data)
# for item in list_data[:]:
# if len(item) == 0:
# list_data.remove(item)
return list_data
def saveDataToExcel(datasets,sheetname,filename):
book = Workbook()
sheet = book.add_sheet(sheetname)
sheet.write(0,0,u'序號')
sheet.write(0,1,u'球隊(duì)')
sheet.write(0,2,u'時(shí)間')
sheet.write(0,3,u'結(jié)果')
sheet.write(0,4,u'主客')
sheet.write(0,5,u'比賽')
sheet.write(0,6,u'投籃命中率')
sheet.write(0,7,u'命中數(shù)')
sheet.write(0,8,u'出手?jǐn)?shù)')
sheet.write(0,9,u'三分命中率')
sheet.write(0,10,u'三分命中數(shù)')
sheet.write(0,11,u'三分出手?jǐn)?shù)')
sheet.write(0,12,u'罰球命中率')
sheet.write(0,13,u'罰球命中數(shù)')
sheet.write(0,14,u'罰球出手?jǐn)?shù)')
sheet.write(0,15,u'籃板')
sheet.write(0,16,u'前場籃板')
sheet.write(0,17,u'后場籃板')
sheet.write(0,18,u'助攻')
sheet.write(0,19,u'搶斷')
sheet.write(0,20,u'蓋帽')
sheet.write(0,21,u'失誤')
sheet.write(0,22,u'犯規(guī)')
sheet.write(0,23,u'得分')
num = 24
row_cnt = 0
data_cnt = 0
data_len = len(datasets)
print 'data_len:',data_len
while(data_cnt< data_len):
row_cnt += 1
print '序號:',row_cnt
for col in range(num):
# print col
sheet.write(row_cnt,col,datasets[data_cnt])
data_cnt += 1
book.save(filename)
def writeDataToTxt(datasets):
fp = open('nba_data.txt','w')
line_cnt = 1
for i in range(len(datasets)-1):
#球隊(duì)名稱對齊的操作：如果球隊(duì)名字過短或者為76人隊(duì)是 球隊(duì)名字后面加兩個table 否則加1個table
if line_cnt % 24 == 2 and len(datasets[i]) < 5 or datasets[i] == u'費(fèi)城76人':
fp.write(datasets[i]+'\t\t')
else:
fp.write(datasets[i]+'\t')
line_cnt += 1
if line_cnt % 24 == 1:
fp.write('\n')
fp.close()
if __name__ == "__main__":
pages = int(1132/150)
url_header = 'http://stat-nba.com/query_team.php?page='
url_tail = '&QueryType=game&order=1&crtcol=date_out&GameType=season&PageNum=3000&Season0=2016&Season1=2017#label_show_result'
url_lists = getURLLists(url_header,url_tail,pages)
datasets = getNBAAllData(url_lists)
writeDataToTxt(datasets)
sheetname = 'nba normal data 2016-2017'
str_time = time.strftime('%Y-%m-%d',time.localtime(time.time()))
filename = 'nba_normal_data'+str_time+'.xls'
saveDataToExcel(datasets,sheetname,filename)看完了這篇文章，相信你對“如何使用Python實(shí)現(xiàn)爬蟲爬取NBA數(shù)據(jù)功能”有了一定的了解，如果想了解更多相關(guān)知識，歡迎關(guān)注創(chuàng)新互聯(lián)成都網(wǎng)站設(shè)計(jì)公司行業(yè)資訊頻道，感謝各位的閱讀！
另外有需要云服務(wù)器可以了解下創(chuàng)新互聯(lián)scvps.cn，海內(nèi)外云服務(wù)器15元起步，三天無理由+7*72小時(shí)售后在線，公司持有idc許可證，提供“云服務(wù)器、裸金屬服務(wù)器、高防服務(wù)器、香港服務(wù)器、美國服務(wù)器、虛擬主機(jī)、免備案服務(wù)器”等云主機(jī)租用服務(wù)以及企業(yè)上云的綜合解決方案，具有“安全穩(wěn)定、簡單易用、服務(wù)可用性高、性價(jià)比高”等特點(diǎn)與優(yōu)勢，專為企業(yè)上云打造定制，能夠滿足用戶豐富、多元化的應(yīng)用場景需求。
