本文整理了Java中edu.uci.ics.crawler4j.url.WebURL.getDocid()方法的一些代码示例，展示了WebURL.getDocid()的具体用法。这些代码示例主要来源于Github/Stackoverflow/Maven等平台，是从一些精选项目中提取出来的代码，具有较强的参考意义，能在一定程度帮忙到你。WebURL.getDocid()方法的具体详情如下：
包路径：edu.uci.ics.crawler4j.url.WebURL
类名称：WebURL
方法名：getDocid

WebURL.getDocid介绍

暂无

代码示例

代码示例来源：origin: yasserg/crawler4j

protected static DatabaseEntry getDatabaseEntryKey(WebURL url) {
  byte[] keyData = new byte[6];
  keyData[0] = url.getPriority();
  keyData[1] = ((url.getDepth() > Byte.MAX_VALUE) ? Byte.MAX_VALUE : (byte) url.getDepth());
  Util.putIntInByteArray(url.getDocid(), keyData, 2);
  return new DatabaseEntry(keyData);
}

代码示例来源：origin: yasserg/crawler4j

@Override
  public void objectToEntry(WebURL url, TupleOutput output) {
    output.writeString(url.getURL());
    output.writeInt(url.getDocid());
    output.writeInt(url.getParentDocid());
    output.writeString(url.getParentUrl());
    output.writeShort(url.getDepth());
    output.writeByte(url.getPriority());
    output.writeString(url.getAnchor());
  }
}

代码示例来源：origin: yasserg/crawler4j

int maxCrawlDepth = myController.getConfig().getMaxDepthOfCrawling();
for (WebURL webURL : parseData.getOutgoingUrls()) {
  webURL.setParentDocid(curURL.getDocid());
  webURL.setParentUrl(curURL.getURL());
  int newdocid = docIdServer.getDocId(webURL.getURL());

代码示例来源：origin: biezhi/java-library-examples

@Override
  public void visit(Page page) {
    int    docid       = page.getWebURL().getDocid();
    String url         = page.getWebURL().getURL();
    int    parentDocid = page.getWebURL().getParentDocid();

    logger.debug("Docid: {}", docid);
    logger.info("URL: {}", url);
    logger.debug("Docid of parent page: {}", parentDocid);

    if (page.getParseData() instanceof HtmlParseData) {
      HtmlParseData htmlParseData = (HtmlParseData) page.getParseData();
      String        text          = htmlParseData.getText();
      String        html          = htmlParseData.getHtml();
      Set<WebURL>   links         = htmlParseData.getOutgoingUrls();

      logger.debug("Text length: {}", text.length());
      logger.debug("Html length: {}", html.length());
      logger.debug("Number of outgoing links: {}", links.size());
    }

    logger.debug("=============");
  }
}

代码示例来源：origin: biezhi/java-library-examples

@Override
  public void visit(Page page) {
    int    docid       = page.getWebURL().getDocid();
    String url         = page.getWebURL().getURL();
    int    parentDocid = page.getWebURL().getParentDocid();

    logger.debug("Docid: {}", docid);
    logger.info("URL: {}", url);
    logger.debug("Docid of parent page: {}", parentDocid);

    if (page.getParseData() instanceof HtmlParseData) {
      HtmlParseData htmlParseData = (HtmlParseData) page.getParseData();
      String        text          = htmlParseData.getText();
      String        html          = htmlParseData.getHtml();
      Set<WebURL>   links         = htmlParseData.getOutgoingUrls();

      logger.debug("Text length: {}", text.length());
      logger.debug("Html length: {}", html.length());
      logger.debug("Number of outgoing links: {}", links.size());
    }

    logger.debug("=============");
  }
}

代码示例来源：origin: biezhi/java-library-examples

int docid = page.getWebURL().getDocid();
String url = page.getWebURL().getURL();
String domain = page.getWebURL().getDomain();

代码示例来源：origin: edu.uci.ics/crawler4j

protected static DatabaseEntry getDatabaseEntryKey(WebURL url) {
  byte[] keyData = new byte[6];
  keyData[0] = url.getPriority();
  keyData[1] = ((url.getDepth() > Byte.MAX_VALUE) ? Byte.MAX_VALUE : (byte) url.getDepth());
  Util.putIntInByteArray(url.getDocid(), keyData, 2);
  return new DatabaseEntry(keyData);
}

代码示例来源：origin: edu.uci.ics/crawler4j

@Override
  public void objectToEntry(WebURL url, TupleOutput output) {
    output.writeString(url.getURL());
    output.writeInt(url.getDocid());
    output.writeInt(url.getParentDocid());
    output.writeString(url.getParentUrl());
    output.writeShort(url.getDepth());
    output.writeByte(url.getPriority());
    output.writeString(url.getAnchor());
  }
}

代码示例来源：origin: edu.uci.ics/crawler4j

int maxCrawlDepth = myController.getConfig().getMaxDepthOfCrawling();
for (WebURL webURL : parseData.getOutgoingUrls()) {
  webURL.setParentDocid(curURL.getDocid());
  webURL.setParentUrl(curURL.getURL());
  int newdocid = docIdServer.getDocId(webURL.getURL());