来自URL的页面标题转储到文件

Question

我有一个文本文档，其中可能有50个网址，我想要页面标题。 I've been trying to use some code that does do that，但编译器似乎在扫描器与字符串参数上绊倒。理想情况下，我想接收URL的文本文档并将相应的页面标题转储到另一个文档。

import java.io.*;
import java.util.*;
import java.net.URL;
import java.net.URLConnection;
import java.nio.charset.Charset;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

//code from: http://www.gotoquiz.com/web-coding/programming/java-programming/how-to-extract-titles-from-web-pages-in-java/

public class TitleExtractor {
    /* the CASE_INSENSITIVE flag accounts for
     * sites that use uppercase title tags.
     * the DOTALL flag accounts for sites that have
     * line feeds in the title text */
    private static final Pattern TITLE_TAG =
        Pattern.compile("\\<title>(.*)\\</title>", Pattern.CASE_INSENSITIVE|Pattern.DOTALL);

    /**
     * @param x the HTML page
     * @return title text (null if document isn't HTML or lacks a title tag)
     * @throws IOException
     */
    public static String getPageTitle(String url) throws IOException {
        URL u = new URL(url);
        URLConnection conn = u.openConnection();

        // ContentType is an inner class defined below
        ContentType contentType = getContentTypeHeader(conn);
        if (!contentType.contentType.equals("text/html"))
            return null; // don't continue if not HTML
        else {
            // determine the charset, or use the default
            Charset charset = getCharset(contentType);
            if (charset == null)
                charset = Charset.defaultCharset();

            // read the response body, using BufferedReader for performance
            InputStream in = conn.getInputStream();
            BufferedReader reader = new BufferedReader(new InputStreamReader(in, charset));
            int n = 0, totalRead = 0;
            char[] buf = new char[1024];
            StringBuilder content = new StringBuilder();

            // read until EOF or first 8192 characters
            while (totalRead < 8192 && (n = reader.read(buf, 0, buf.length)) != -1) {
                content.append(buf, 0, n);
                totalRead += n;
            }
            reader.close();

            // extract the title
            Matcher matcher = TITLE_TAG.matcher(content);
            if (matcher.find()) {
                /* replace any occurrences of whitespace (which may
                 * include line feeds and other uglies) as well
                 * as HTML brackets with a space */
                return matcher.group(1).replaceAll("[\\s\\<>]+", " ").trim();
            }
            else
                return null;
        }
    }

    /**
     * Loops through response headers until Content-Type is found.
     * @param conn
     * @return ContentType object representing the value of
     * the Content-Type header
     */
    private static ContentType getContentTypeHeader(URLConnection conn) {
        int i = 0;
        boolean moreHeaders = true;
        do {
            String headerName = conn.getHeaderFieldKey(i);
            String headerValue = conn.getHeaderField(i);
            if (headerName != null && headerName.equals("Content-Type"))
                return new ContentType(headerValue);

            i++;
            moreHeaders = headerName != null || headerValue != null;
        }
        while (moreHeaders);

        return null;
    }

    private static Charset getCharset(ContentType contentType) {
        if (contentType != null && contentType.charsetName != null && Charset.isSupported(contentType.charsetName))
            return Charset.forName(contentType.charsetName);
        else
            return null;
    }

    /**
     * Class holds the content type and charset (if present)
     */
    private static final class ContentType {
        private static final Pattern CHARSET_HEADER = Pattern.compile("charset=([-_a-zA-Z0-9]+)", Pattern.CASE_INSENSITIVE|Pattern.DOTALL);

        private String contentType;
        private String charsetName;
        private ContentType(String headerValue) {
            if (headerValue == null)
                throw new IllegalArgumentException("ContentType must be constructed with a not-null headerValue");
            int n = headerValue.indexOf(";");
            if (n != -1) {
                contentType = headerValue.substring(0, n);
                Matcher matcher = CHARSET_HEADER.matcher(headerValue);
                if (matcher.find())
                    charsetName = matcher.group(1);
            }
            else
                contentType = headerValue;
        }
    }


    public class readfile{

        private Scanner x;

        public void openFile(){

            try{
                x = new Scanner(new File("urls.txt"));
            }
            catch(Exception e){
                System.out.println("could not find file");
            }

        }

        public void readFile() throws IOException{

            while(x.hasNext()){
                //String title = TitleExtractor.getPageTitle(x);
                String a = x.next();
                String title = TitleExtractor.getPageTitle(a);
                System.out.printf("%s\n",title);
                }
        }

        public void closeFile(){
            x.close();
        }



    }


    public static void main(String[] args) throws IOException{


        readfile r = new readfile();
        r.openFile();
        r.readFile();
        r.closeFile();



        }


}

我在readfile上遇到编译错误r = new readfile（）;位：

＆＃34;无法访问类型为TitleExtractor的封闭实例。必须使用TitleExtractor＆＃34;

类型的封闭实例限定分配

我不太确定代码在扫描程序和字符串变量之间的混淆程度。

Answer 1

readfile是一个非静态内部类，因此无需引用TitleExtractor的实例即可实例化它。最简单的解决方案是将类声明更改为public static class readfile。