All Downloads are FREE. Search and download functionalities are using the official Maven repository.

com.goikosoft.crawler4j.crawler.CrawlController Maven / Gradle / Ivy

Go to download

crawler4j: Open Source Web Crawler for Java. Modified by Dario Goikoetxea to add POST capabilities

There is a newer version: 4.5.11
Show newest version
/**
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF 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.goikosoft.crawler4j.crawler;

import com.goikosoft.crawler4j.fetcher.PageFetcherInterface;
import com.goikosoft.crawler4j.parser.Parser;
import com.goikosoft.crawler4j.robotstxt.RobotstxtServer;
import com.goikosoft.crawler4j.url.TLDList;

/**
 * The controller that manages a crawling session. This class creates the
 * crawler threads and monitors their progress.
 *
 * Modified by Dario Goikoetxea to be just a concrete implementation of GenericCrawlController
 *
 * @author Yasser Ganjisaffar
 */

public class CrawlController extends GenericCrawlController {

    public CrawlController(CrawlConfig config, PageFetcherInterface pageFetcher, Parser parser,
            RobotstxtServer robotstxtServer, TLDList tldList, String docIdDbName, String pendingDbName,
            String inProcessDbName) throws Exception {
        super(config, pageFetcher, parser, robotstxtServer, tldList, docIdDbName, pendingDbName, inProcessDbName);
    }

    public CrawlController(CrawlConfig config, PageFetcherInterface pageFetcher, Parser parser,
            RobotstxtServer robotstxtServer, TLDList tldList, String docIdDbName, String pendingDbName)
            throws Exception {
        super(config, pageFetcher, parser, robotstxtServer, tldList, docIdDbName, pendingDbName);
    }

    public CrawlController(CrawlConfig config, PageFetcherInterface pageFetcher, Parser parser,
            RobotstxtServer robotstxtServer, TLDList tldList) throws Exception {
        super(config, pageFetcher, parser, robotstxtServer, tldList);
    }

    public CrawlController(CrawlConfig config, PageFetcherInterface pageFetcher, RobotstxtServer robotstxtServer,
            TLDList tldList) throws Exception {
        super(config, pageFetcher, robotstxtServer, tldList);
    }

    public CrawlController(CrawlConfig config, PageFetcherInterface pageFetcher, RobotstxtServer robotstxtServer)
            throws Exception {
        super(config, pageFetcher, robotstxtServer);
    }

}




© 2015 - 2025 Weber Informatics LLC | Privacy Policy