安卓WebView -> Display WebArchive

Question

从API级别11开始，安卓的WebView就有了这个saveWebArchive方法：http://developer.android.com/。

它可以将整个网站保存为网络存档，这很棒！但是我怎样才能把下载的内容放回get视图呢？我试过了

webview.loadUrl(Uri.fromFile(mywebarchivefile));

但这只会在屏幕上显示xml。

Answer 1

2014年2月21日更新

我下面的答案不适用于保存在Android 4.4 KitKat和更新版本下的网络存档文件。在Android4.4 "KitKat“(可能是更新的版本)下的WebView的saveWebArchive()方法不能保存这个阅读器代码发布在下面的XML代码中的网页存档。相反，它以MHT (MHTML)格式保存页面。回读.mht文件很容易-只需使用：

webView.loadUrl("file:///my_dir/mySavedWebPage.mht");

这就是全部，比前面的方法简单得多，并且与其他平台兼容。

以前发布的内容

我自己也需要它，无论我在哪里搜索，都有像这样的未回答的问题。所以我必须自己解决这个问题。下面是我的小WebArchiveReader类和如何使用它的示例代码。请注意，尽管安卓文档宣称shouldInterceptRequest()是在API11 (Honeycomb)中添加到WebViewClient中的，但这段代码可以正常工作，并且在API8 (Froyo)的安卓仿真器中测试成功。下面是所有需要的代码，我还将完整的项目上传到了https://github.com/gregko/WebArchiveReader上的GitHub存储库

文件WebArchiveReader.java：

package com.hyperionics.war_test;

import android.util.Base64;
import android.webkit.WebResourceResponse;
import android.webkit.WebView;
import android.webkit.WebViewClient;
import org.w3c.dom.*;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import java.io.ByteArrayInputStream;
import java.io.InputStream;
import java.util.ArrayList;

public abstract class WebArchiveReader {
    private Document myDoc = null;
    private static boolean myLoadingArchive = false;
    private WebView myWebView = null;
    private ArrayList<String> urlList = new ArrayList<String>();
    private ArrayList<Element> urlNodes = new ArrayList<Element>();

    abstract void onFinished(WebView webView);

    public boolean readWebArchive(InputStream is) {
        DocumentBuilderFactory builderFactory =
                DocumentBuilderFactory.newInstance();
        DocumentBuilder builder = null;
        myDoc = null;
        try {
            builder = builderFactory.newDocumentBuilder();
        } catch (ParserConfigurationException e) {
            e.printStackTrace();
        }
        try {
            myDoc = builder.parse(is);
            NodeList nl = myDoc.getElementsByTagName("url");
            for (int i = 0; i < nl.getLength(); i++) {
                Node nd = nl.item(i);
                if(nd instanceof Element) {
                    Element el = (Element) nd;
                    // siblings of el (url) are: mimeType, textEncoding, frameName, data
                    NodeList nodes = el.getChildNodes();
                    for (int j = 0; j < nodes.getLength(); j++) {
                        Node node = nodes.item(j);
                        if (node instanceof Text) {
                            String dt = ((Text)node).getData();
                            byte[] b = Base64.decode(dt, Base64.DEFAULT);
                            dt = new String(b);
                            urlList.add(dt);
                            urlNodes.add((Element) el.getParentNode());
                        }
                    }
                }
            }
        } catch (Exception e) {
            e.printStackTrace();
            myDoc = null;
        }
        return myDoc != null;
    }

    private byte [] getElBytes(Element el, String childName) {
        try {
            Node kid = el.getFirstChild();
            while (kid != null) {
                if (childName.equals(kid.getNodeName())) {
                    Node nn = kid.getFirstChild();
                    if (nn instanceof Text) {
                        String dt = ((Text)nn).getData();
                        return Base64.decode(dt, Base64.DEFAULT);
                    }
                }
                kid = kid.getNextSibling();
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
        return null;
    }

    public boolean loadToWebView(WebView v) {
        myWebView = v;
        v.setWebViewClient(new WebClient());
        WebSettings webSettings = v.getSettings();
        webSettings.setDefaultTextEncodingName("UTF-8");

        myLoadingArchive = true;
        try {
            // Find the first ArchiveResource in myDoc, should be <ArchiveResource>
            Element ar = (Element) myDoc.getDocumentElement().getFirstChild().getFirstChild();
            byte b[] = getElBytes(ar, "data");

            // Find out the web page charset encoding
            String charset = null;
            String topHtml = new String(b).toLowerCase();
            int n1 = topHtml.indexOf("<meta http-equiv=\"content-type\"");
            if (n1 > -1) {
                int n2 = topHtml.indexOf('>', n1);
                if (n2 > -1) {
                    String tag = topHtml.substring(n1, n2);
                    n1 = tag.indexOf("charset");
                    if (n1 > -1) {
                        tag = tag.substring(n1);
                        n1 = tag.indexOf('=');
                        if (n1 > -1) {
                            tag = tag.substring(n1+1);
                            tag = tag.trim();
                            n1 = tag.indexOf('\"');
                            if (n1 < 0)
                                n1 = tag.indexOf('\'');
                            if (n1 > -1) {
                                charset = tag.substring(0, n1).trim();
                            }
                        }
                    }
                }
            }

            if (charset != null)
                topHtml = new String(b, charset);
            else
                topHtml = new String(b);
            String baseUrl = new String(getElBytes(ar, "url"));
            v.loadDataWithBaseURL(baseUrl, topHtml, "text/html", "UTF-8", null);
        } catch (Exception e) {
            e.printStackTrace();
            return false;
        }
        return true;
    }

    private class WebClient extends WebViewClient {
        @Override
        public WebResourceResponse shouldInterceptRequest(WebView view, String url) {
            if (!myLoadingArchive)
                return null;
            int n = urlList.indexOf(url);
            if (n < 0)
                return null;
            Element parentEl = urlNodes.get(n);
            byte [] b = getElBytes(parentEl, "mimeType");
            String mimeType = b == null ? "text/html" : new String(b);
            b = getElBytes(parentEl, "textEncoding");
            String encoding = b == null ? "UTF-8" : new String(b);
            b = getElBytes(parentEl, "data");
            return new WebResourceResponse(mimeType, encoding, new ByteArrayInputStream(b));
        }

        @Override
        public void onPageFinished(WebView view, String url)
        {
            // our WebClient is no longer needed in view
            view.setWebViewClient(null);
            myLoadingArchive = false;
            onFinished(myWebView);
        }
    }
}

下面是如何使用这个类，示例MyActivity.java类：

package com.hyperionics.war_test;

import android.app.Activity;
import android.os.Bundle;
import android.webkit.WebView;
import android.webkit.WebViewClient;
import java.io.IOException;
import java.io.InputStream;

public class MyActivity extends Activity {

    // Sample WebViewClient in case it was needed...
    // See continueWhenLoaded() sample function for the best place to set it on our webView
    private class MyWebClient extends WebViewClient {
        @Override
        public void onPageFinished(WebView view, String url)
        {
            Lt.d("Web page loaded: " + url);
        }
    }

    @Override
    public void onCreate(Bundle savedInstanceState) {
        super.onCreate(savedInstanceState);
        setContentView(R.layout.main);
        WebView webView = (WebView) findViewById(R.id.webView);
        try {
            InputStream is = getAssets().open("TestHtmlArchive.xml");
            WebArchiveReader wr = new WebArchiveReader() {
                void onFinished(WebView v) {
                    // we are notified here when the page is fully loaded.
                    continueWhenLoaded(v);
                }
            };
            // To read from a file instead of an asset, use:
            // FileInputStream is = new FileInputStream(fileName);
            if (wr.readWebArchive(is)) {
                wr.loadToWebView(webView);
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    void continueWhenLoaded(WebView webView) {
        Lt.d("Page from WebArchive fully loaded.");
        // If you need to set your own WebViewClient, do it here,
        // after the WebArchive was fully loaded:
        webView.setWebViewClient(new MyWebClient());
        // Any other code we need to execute after loading a page from a WebArchive...
    }
}

为了让事情变得完整，下面是我的调试输出的小Lt.java类：

package com.hyperionics.war_test;

import android.util.Log;

public class Lt {
    private static String myTag = "war_test";
    private Lt() {}
    static void setTag(String tag) { myTag = tag; }
    public static void d(String msg) {
        // Uncomment line below to turn on debug output
        Log.d(myTag, msg == null ? "(null)" : msg);
    }
    public static void df(String msg) {
        // Forced output, do not comment out - for exceptions etc.
        Log.d(myTag, msg == null ? "(null)" : msg);
    }
}

希望这能对你有所帮助。

更新: 2013年7月19日

一些网页没有指定文本编码的meta标签，因此我们上面显示的代码不能正确显示字符。在这段代码的GitHub版本中，我现在添加了字符集检测算法，它可以在这种情况下猜测编码。同样，请参阅https://github.com/gregko/WebArchiveReader

格雷格

Answer 2

我发现了一种阅读保存的网络存档的无文档方法。只需这样做：

String raw_data = (read the mywebarchivefile as a string)

然后调用

webview.loadDataWithBaseURL(mywebarchivefile, raw_data, "application/x-webarchive-xml", "UTF-8", null);

参考资料：http://androidxref.com/4.0.4/xref/external/webkit/Source/WebCore/loader/archive/ArchiveFactory.cpp

可从Android 3.0 api level 11获得。