com.digitalpebble.storm.crawler.protocol.RobotRules Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of storm-crawler Show documentation

A collection of resources for building low-latency, scalable web crawlers on Apache Storm.

There is a newer version: 0.7

/**
 * Licensed to DigitalPebble Ltd under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * DigitalPebble licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package com.digitalpebble.storm.crawler.protocol;

import java.net.URL;

/**
 * This class holds the rules which were parsed from a robots.txt file, and can
 * test paths against those rules.
 */
public interface RobotRules {
    /**
     * Get expire time
     */
    public long getExpireTime();

    /**
     * Get Crawl-Delay, in milliseconds. This returns -1 if not set.
     */
    public long getCrawlDelay();

    /**
     * Returns false if the robots.txt file prohibits
     * us from accessing the given url, or true
     * otherwise.
     */
    public boolean isAllowed(URL url);

}