IO流-综合练习

1，爬取-在网址中爬取数据并返回字符串

public class paquxing {
    public static void main(String[] args) throws IOException {
        String familyname = "https://so.gushiwen.cn/guwen/book_46653FD803893E4FE03CBAE75DE61AB8.aspx";
        String s = webCrawler(familyname);
        String regex = "(.(4))(, | .)";
        getData(s,regex,0);

    }
//获取网页内容并用正则表达式筛选
    private static ArrayList<String> getData(String s, String regex, int i) {
        ArrayList<String> list = new ArrayList<>();
        Pattern pattern = Pattern.compile(regex);
        Matcher matcher = pattern.matcher(s);
        while(matcher.find()){
            String group = matcher.group(i);
            list.add(group);
        }
        return list;
    }
//获取网页内容
    public static String webCrawler(String net) throws IOException {
        StringBuilder sb = new StringBuilder();
        URL url = new URL(net);
        URLConnection uc = url.openConnection();
        InputStreamReader isr = new InputStreamReader(uc.getInputStream());
        int ch;
        while((ch = isr.read()) != -1){
            sb.append(ch);
        }
        isr.close();
        return sb.toString();
    }
}