使用 Jsoup 提取 JavaScript 数据

Created: November-22, 2018

在此示例中，我们将尝试查找包含 backgroundColor:'#FFF'的 JavaScript 数据。然后，我们将更改 backgroundColor'#FFF'⇨'#ddd'的值。此代码使用 getWholeData() 和 setWholeData() 方法来处理 JavaScript 数据。或者，html() 方法可用于获取 JavaScript 的数据。

// create HTML with JavaScript data
    StringBuilder html = new StringBuilder();
    html.append("<!DOCTYPE html> <html> <head> <title>Hello Jsoup!</title>");
    html.append("<script>");
    html.append("StackExchange.docs.comments.init({");
    html.append("highlightColor: '#F4A83D',");
    html.append("backgroundColor:'#FFF',");
    html.append("});");
    html.append("</script>");
    html.append("<script>");
    html.append("document.write(<style type='text/css'>div,iframe { top: 0; position:absolute; }</style>');");
    html.append("</script>\n");
    html.append("</head><body></body> </html>");

    // parse as HTML document
    Document doc = Jsoup.parse(html.toString());

    String defaultBackground = "backgroundColor:'#FFF'";
    // get <script>
    for (Element scripts : doc.getElementsByTag("script")) {
        // get data from <script>
        for (DataNode dataNode : scripts.dataNodes()) {
            // find data which contains backgroundColor:'#FFF'
            if (dataNode.getWholeData().contains(defaultBackground)) {
                // replace '#FFF' -> '#ddd'
                String newData = dataNode.getWholeData().replaceAll(defaultBackground, "backgroundColor:'#ddd'");
                // set new data contents
                dataNode.setWholeData(newData);
            }
        }
    }
    System.out.println(doc.toString());

输出

<script>StackExchange.docs.comments.init({highlightColor: '#F4A83D',backgroundColor:'#ddd',});</script>