爬虫实践--CBA历年比赛数据

球队,第一节,第二节,第三节,第四节,总比分
广州,33,37,36,27,133
北控,23,18,17,34,92
2019-01-1619:35:00轮次：31场序309开始比赛　　比赛已结束
首发,球员,出场时间,两分球,三分球,罚球,进攻,篮板,助攻,失误,抢断,犯规,盖帽,得分
,张永鹏,25.8,7-9,0-0,1-1,4,8,3,0,0,1,0,15
,鞠明欣,19.1,2-4,1-2,0-0,2,5,2,2,0,1,0,7
,西热力江,25.5,1-1,4-8,0-0,1,2,4,1,3,1,0,14
,郭凯,15.5,2-2,0-0,0-0,2,3,0,2,0,2,0,4
,凯尔·弗格,38.1,5-9,5-9,11-11,0,10,12,2,2,4,0,36
,姚天一,12.3,0-1,1-4,0-0,0,1,5,0,0,0,0,3
,科里·杰弗森,24.0,4-4,2-4,3-4,0,6,0,1,0,1,1,17
,陈盈骏,22.6,1-1,2-7,1-1,0,2,4,2,1,2,0,9
,司坤,19.0,2-2,0-2,0-0,0,5,1,0,1,4,0,4
,孙鸣阳,20.6,2-3,0-0,3-3,1,4,1,2,3,4,0,7
,谷玥灼,7.4,1-1,1-2,0-0,0,0,2,0,0,0,0,5
,郑准,10.1,3-4,2-3,0-0,0,2,0,0,0,1,0,12
,总计,240.0,30-41(73.2%),18-41(43.9%),19-20(95.0%),10,48,34,12,10,21,1,133
首发,球员,出场时间,两分球,三分球,罚球,进攻,篮板,助攻,失误,抢断,犯规,盖帽,得分
,于梁,20.8,1-3,0-1,0-0,0,0,2,0,1,5,0,2
,于澍龙,17.9,0-1,1-3,0-0,0,2,1,2,0,1,0,3
,许梦君,46.2,1-3,5-12,0-0,1,6,2,1,0,3,0,17
,托马斯·罗宾逊,43.4,9-20,0-2,9-14,3,11,5,2,1,3,1,27
,杨敬敏,16.0,3-4,0-3,0-0,0,0,0,2,0,1,0,6
,孙贺男,2.8,0-0,0-0,0-0,0,0,0,1,0,1,0,0
,刘大鹏,28.0,1-1,3-5,0-0,1,4,3,2,2,3,0,11
,张铭浩,8.5,0-0,0-0,1-2,0,0,0,0,1,1,0,1
,张帆,27.5,5-7,1-3,0-0,0,1,6,4,1,2,0,13
,王征,23.3,3-3,0-0,6-8,0,2,0,0,1,1,1,12
,常亚松,5.6,0-0,0-1,0-0,0,1,0,1,2,0,0,0
,总计,240.0,23-42(54.8%),10-30(33.3%),16-24(66.7%),5,27,19,15,9,21,2,92

 1package com.fun
 2
 3import com.fun.frame.Save
 4import com.fun.frame.httpclient.FanLibrary
 5import com.fun.utils.Regex
 6import com.fun.utils.WriteRead
 7
 8class sd extends FanLibrary {
 9
10    public static void main(String[] args) {
11        int i = 1
12        def total = []
13        range(300, 381).forEach {x ->
14            total.addAll test(x)
15        }
16        Save.saveStringList(total, "total4.csv")
17        testOver()
18    }
19
20
21    static def test(int i) {
22        if (new File(LONG_Path + "${i}.csv").exists()) return WriteRead.readTxtFileByLine(LONG_Path + "${i}.csv")
23        String url = "http://cbadata.sports.sohu.com/game/content/2017/${i}"
24
25        def get = getHttpGet(url)
26
27        def response = getHttpResponse(get)
28
29
30        def string = response.getString("content").replaceAll("\\s", EMPTY)
31//        output(string)
32        def all = Regex.regexAll(string, "<tr.*?<\\/tr>")
33        def list = []
34        all.forEach {x ->
35            def info = x.replaceAll("</*?tr.*?>", EMPTY).replaceAll("</t(d|h)>", ",")
36            info = info.replaceAll("<.*?>", EMPTY)
37
38            info = info.charAt(info.length() - 1) == ',' ? info.substring(0, info.length() - 1) : info
39            if (info.startsWith("总计")) info = "," + info
40            list << info
41            output(info)
42
43        }
44        Save.saveStringList(list, "${i}.csv")
45        return list
46    }
47
48}