Jsuop进行链接提取

// 检索WebContent中的图片和附件
Document doc = Jsoup.parse(info.getWebc().getWebContent());
// 当前页中的图片
Elements srcLinks = doc.select("img[src]");
String imagesPath = "";
for (Element link : srcLinks) {
    // 剔除标签，只剩链接路径
    String imagesPaths = link.attr("src");
    String ht = imagesPaths.substring(0, 4);
    String htt = imagesPaths.substring(0, 1);
    if (!ht.equals("http") && htt.equals("/")) {
        imagesPath = imagesPaths.trim().replaceAll(ContextPath, "");
        imagesPath = imagesPath.substring(imagesPath.lastIndexOf("/") + 1);
    } else {
        imagesPath = "";
    }
    //System.out.println("---导入WebContent中的图片---" + imagesPath);
    if (!imagesPath.equals("")) {
        importCopy("/html/"+strSiteID+"/"+strColumnID+"/"+keyID+"/"+imagesPath, path, strInfoID,"/html/"+strSiteID+"/"+strColumnID+"/"+keyID+"/");
    }
}
// 提取所有的href连接
String filePaths = "";
Elements linehrefs = doc.select("a[href]");
for (Element link : linehrefs) {
    filePaths = link.attr("href").trim().replaceAll(ContextPath, "");
    filePaths = filePaths.substring(filePaths.lastIndexOf("/") + 1);
    //System.out.println("---导入WebContent中的文件---" + filePaths);
    if (!filePaths.equals("")) {
        importCopy("/html/"+strSiteID+"/"+strColumnID+"/"+keyID+"/"+filePaths, path, strInfoID,"/html/"+strSiteID+"/"+strColumnID+"/"+keyID+"/");
    }
}