JavaでGoogle PageRank(PR)を取得する方法

JavaでGoogle PageRank(PR)を取得する方法

google pagerank

この例では、JavaでGoogle PageRank(PR)を取得する方法を示します。 「example.com」のPageRankをリクエストするには、次のHTTPリクエストを送信する必要があります。

http://toolbarqueries.google.com/tbr?client=navclient-auto&hl=en&ch=6236440745
&ie=UTF-8&oe=UTF-8&features=Rank&q=info:example.com

P.S Above URL is used by Google toolbar plugin.

トリッキーな部分はハッシュ値を追跡することです:

ch=6236440745

GoogleはBobJenkinsハッシュアルゴリズム[1] [2]を使用してURLをハッシュし、上記の「ch」値を生成しています。

1. PageRank(PR)+ Javaの例

ウェブサイト「example.com」のGooglePRを入手してください。

GoogleSeoHelper.java

package com.example;

import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;
import com.example.hash.JenkinsHash;

public class GoogleSeoHelper {

  public static void main(String[] args) {

    GoogleSeoHelper obj = new GoogleSeoHelper();
    System.out.println(obj.getPR("example.com"));

  }

  public int getPR(String domain) {

    String result = "";

    JenkinsHash jenkinsHash = new JenkinsHash();
    long hash = jenkinsHash.hash(("info:" + domain).getBytes());

    //Append a 6 in front of the hashing value.
    String url = "http://toolbarqueries.google.com/tbr?client=navclient-auto&hl=en&"
       + "ch=6" + hash + "&ie=UTF-8&oe=UTF-8&features=Rank&q=info:" + domain;

    System.out.println("Sending request to : " + url);

    try {
        URLConnection conn = new URL(url).openConnection();

        BufferedReader br = new BufferedReader(new InputStreamReader(
            conn.getInputStream()));

        String input;
        while ((input = br.readLine()) != null) {

            // What Google returned? Example : Rank_1:1:9, PR = 9
            System.out.println(input);

            result = input.substring(input.lastIndexOf(":") + 1);
        }

    } catch (Exception e) {
        System.out.println(e.getMessage());
    }

    if ("".equals(result)) {
        return 0;
    } else {
        return Integer.valueOf(result);
    }

  }

}

出力–URL「example.com」のPageRankは5です。

Sending request to : http://toolbarqueries.google.com/tbr?client=navclient-auto
&hl=en&ch=6236440745&ie=UTF-8&oe=UTF-8&features=Rank&q=info:example.com
Rank_1:1:5
5

2. Jenkins完全ハッシュアルゴリズム

JenkinsハッシュJavaポートの例を次に示します。

JenkinsHash.java

package com.example.hash;

/**
 * Hash algorithm by Bob Jenkins, 1996.
 *
 * You may use this code any way you wish, private, educational, or commercial.
 * It's free. See: http://burtleburtle.net/bob/hash/doobs.html
 *
 */
public class JenkinsHash {

    // max value to limit it to 4 bytes
    private static final long MAX_VALUE = 0xFFFFFFFFL;

    // internal variables used in the various calculations
    long a;
    long b;
    long c;

    /**
     * Convert a byte into a long value without making it negative.
     */
    private long byteToLong(byte b) {
        long val = b & 0x7F;
        if ((b & 0x80) != 0) {
            val += 128;
        }
        return val;
    }

    /**
     * Do addition and turn into 4 bytes.
     */
    private long add(long val, long add) {
        return (val + add) & MAX_VALUE;
    }

    /**
     * Do subtraction and turn into 4 bytes.
     */
    private long subtract(long val, long subtract) {
        return (val - subtract) & MAX_VALUE;
    }

    /**
     * Left shift val by shift bits and turn in 4 bytes.
     */
    private long xor(long val, long xor) {
        return (val ^ xor) & MAX_VALUE;
    }

    /**
     * Left shift val by shift bits. Cut down to 4 bytes.
     */
    private long leftShift(long val, int shift) {
        return (val << shift) & MAX_VALUE;
    }

    /**
     * Convert 4 bytes from the buffer at offset into a long value.
     */
    private long fourByteToLong(byte[] bytes, int offset) {
        return (byteToLong(bytes[offset + 0])
        + (byteToLong(bytes[offset + 1]) << 8)
        + (byteToLong(bytes[offset + 2]) << 16) + (byteToLong(bytes[offset + 3]) << 24));
    }

    /**
     * Mix up the values in the hash function.
     */
    private void hashMix() {
        a = subtract(a, b);
        a = subtract(a, c);
        a = xor(a, c >> 13);
        b = subtract(b, c);
        b = subtract(b, a);
        b = xor(b, leftShift(a, 8));
        c = subtract(c, a);
        c = subtract(c, b);
        c = xor(c, (b >> 13));
        a = subtract(a, b);
        a = subtract(a, c);
        a = xor(a, (c >> 12));
        b = subtract(b, c);
        b = subtract(b, a);
        b = xor(b, leftShift(a, 16));
        c = subtract(c, a);
        c = subtract(c, b);
        c = xor(c, (b >> 5));
        a = subtract(a, b);
        a = subtract(a, c);
        a = xor(a, (c >> 3));
        b = subtract(b, c);
        b = subtract(b, a);
        b = xor(b, leftShift(a, 10));
        c = subtract(c, a);
        c = subtract(c, b);
        c = xor(c, (b >> 15));
    }

    /**
     * Hash a variable-length key into a 32-bit value. Every bit of the key
     * affects every bit of the return value. Every 1-bit and 2-bit delta
     * achieves avalanche. The best hash table sizes are powers of 2.
     *
     * @param buffer
     *            Byte array that we are hashing on.
     * @param initialValue
     *            Initial value of the hash if we are continuing from a previous
     *            run. 0 if none.
     * @return Hash value for the buffer.
     */
    public long hash(byte[] buffer, long initialValue) {
        int len, pos;

        // set up the internal state
        // the golden ratio; an arbitrary value
        a = 0x09e3779b9L;
        // the golden ratio; an arbitrary value
        b = 0x09e3779b9L;
        // the previous hash value

        //c = initialValue;
        c = 0x0E6359A60L;

        // handle most of the key
        pos = 0;
        for (len = buffer.length; len >= 12; len -= 12) {
            a = add(a, fourByteToLong(buffer, pos));
            b = add(b, fourByteToLong(buffer, pos + 4));
            c = add(c, fourByteToLong(buffer, pos + 8));
            hashMix();
            pos += 12;
        }

        c += buffer.length;

        // all the case statements fall through to the next on purpose
        switch (len) {
        case 11:
            c = add(c, leftShift(byteToLong(buffer[pos + 10]), 24));
        case 10:
            c = add(c, leftShift(byteToLong(buffer[pos + 9]), 16));
        case 9:
            c = add(c, leftShift(byteToLong(buffer[pos + 8]), 8));
            // the first byte of c is reserved for the length
        case 8:
            b = add(b, leftShift(byteToLong(buffer[pos + 7]), 24));
        case 7:
            b = add(b, leftShift(byteToLong(buffer[pos + 6]), 16));
        case 6:
            b = add(b, leftShift(byteToLong(buffer[pos + 5]), 8));
        case 5:
            b = add(b, byteToLong(buffer[pos + 4]));
        case 4:
            a = add(a, leftShift(byteToLong(buffer[pos + 3]), 24));
        case 3:
            a = add(a, leftShift(byteToLong(buffer[pos + 2]), 16));
        case 2:
            a = add(a, leftShift(byteToLong(buffer[pos + 1]), 8));
        case 1:
            a = add(a, byteToLong(buffer[pos + 0]));
            // case 0: nothing left to add
        }
        hashMix();

        return c;
    }

    /**
     * See hash(byte[] buffer, long initialValue)
     *
     * @param buffer
     *            Byte array that we are hashing on.
     * @return Hash value for the buffer.
     */
    public long hash(byte[] buffer) {
        return hash(buffer, 0);
    }
}