HtmlExtractor由2個子專案構成，html-extractor和html-extractor-web。
html-extractor實現了資料抽取邏輯，是從節點，html-extractor-web提供web介面來維護抽取規則，是主節點。
html-extractor是一個jar包，可通過maven引用：
<dependency>
    <groupId>org.apdplat</groupId>
    <artifactId>html-extractor</artifactId>
    <version>1.0</version>
</dependency>
html-extractor-web是一個war包，需要部署到Servlet/Jsp容器上。
 

單機集中式使用方法：

//1、構造抽取規則

List<UrlPattern> urlPatterns = new ArrayList<>();
//1.1、構造URL模式
UrlPattern urlPattern = new UrlPattern();
urlPattern.setUrlPattern("http://money.163.com/\\d{2}/\\d{4}/\\d{2}/[0-9A-Z]{16}.html");
//1.2、構造HTML模板
HtmlTemplate htmlTemplate = new HtmlTemplate();
htmlTemplate.setTemplateName("網易財經頻道");
htmlTemplate.setTableName("finance");
//1.3、將URL模式和HTML模板建立關聯
urlPattern.addHtmlTemplate(htmlTemplate);
//1.4、構造CSS路徑
CssPath cssPath = new CssPath();
cssPath.setCssPath("h1");
cssPath.setFieldName("title");
cssPath.setFieldDescription("標題");
//1.5、將CSS路徑和模板建立關聯
htmlTemplate.addCssPath(cssPath);
//1.6、構造CSS路徑
cssPath = new CssPath();
cssPath.setCssPath("div#endText");
cssPath.setFieldName("content");
cssPath.setFieldDescription("正文");
//1.7、將CSS路徑和模板建立關聯
htmlTemplate.addCssPath(cssPath);
//可象上面那樣構造多個URLURL模式
urlPatterns.add(urlPattern);

//2、獲取抽取規則物件
ExtractRegular extractRegular = ExtractRegular.getInstance(urlPatterns);
//注意：可通過如下3個方法動態地改變抽取規則
//extractRegular.addUrlPatterns(urlPatterns);
//extractRegular.addUrlPattern(urlPattern);
//extractRegular.removeUrlPattern(urlPattern.getUrlPattern());

//3、獲取HTML抽取工具
HtmlExtractor htmlExtractor = HtmlExtractor.getInstance(extractRegular);

//4、抽取網頁
String url = "http://money.163.com/08/1219/16/4THR2TMP002533QK.html";
List<ExtractResult> extractResults = htmlExtractor.extract(url, "gb2312");

//5、輸出結果
int i = 1;
for (ExtractResult extractResult : extractResults) {
    System.out.println((i++) + "、網頁 " + extractResult.getUrl() + " 的抽取結果");
    for(ExtractResultItem extractResultItem : extractResult.getExtractResultItems()){
        System.out.print("\t"+extractResultItem.getField()+" = "+extractResultItem.getValue());              
    }
    System.out.println("\tdescription = "+extractResult.getDescription());
    System.out.println("\tkeywords = "+extractResult.getKeywords());
}
 

多機分散式使用方法：