.apkパッケージ内のAndroidManifest.xmlファイルを解析する方法

Question

このファイルはバイナリXML形式のようです。この形式とは何ですか？また、SDKのaaptダンプツールを使用するのではなく、プログラムでどのように解析できますか？

このバイナリ形式は、ドキュメントでは説明されていません here 。

注：Android環境の外部、できればJavaからこの情報にアクセスしたいです。

Answer 1

Android-apktoolを使用する

Apkファイルを読み取り、XMLをほぼ元の形式にデコードするアプリケーションがあります。

使用法：

apktool d Gmail.apk && cat Gmail/AndroidManifest.xml

詳細については、 Android-apktool を確認してください

Answer 2

Android上で実行されるこのJavaメソッドは、.apkパッケージ内のAndroidManifest.xmlファイルのバイナリ形式（私が解釈したもの）を文書化します。 2番目のコードボックスは、decompressXMLを呼び出す方法と、デバイスのアプリパッケージファイルからbyte []をロードする方法を示しています。 （目的がわからないフィールドがあります。それらの意味がわかっていれば、教えてください、情報を更新します。）

// decompressXML -- Parse the 'compressed' binary form of Android XML docs 
// such as for AndroidManifest.xml in .apk files
public static int endDocTag = 0x00100101;
public static int startTag =  0x00100102;
public static int endTag =    0x00100103;
public void decompressXML(byte[] xml) {
// Compressed XML file/bytes starts with 24x bytes of data,
// 9 32 bit words in little endian order (LSB first):
//   0th Word is 03 00 08 00
//   3rd Word SEEMS TO BE:  Offset at then of StringTable
//   4th Word is: Number of strings in string table
// WARNING: Sometime I indiscriminently display or refer to Word in 
//   little endian storage format, or in integer format (ie MSB first).
int numbStrings = LEW(xml, 4*4);

// StringIndexTable starts at offset 24x, an array of 32 bit LE offsets
// of the length/string data in the StringTable.
int sitOff = 0x24;  // Offset of start of StringIndexTable

// StringTable, each string is represented with a 16 bit little endian 
// character count, followed by that number of 16 bit (LE) (Unicode) chars.
int stOff = sitOff + numbStrings*4;  // StringTable follows StrIndexTable

// XMLTags, The XML tag tree starts after some unknown content after the
// StringTable.  There is some unknown data after the StringTable, scan
// forward from this point to the flag for the start of an XML start tag.
int xmlTagOff = LEW(xml, 3*4);  // Start from the offset in the 3rd Word.
// Scan forward until we find the bytes: 0x02011000(x00100102 in normal int)
for (int ii=xmlTagOff; ii<xml.length-4; ii+=4) {
  if (LEW(xml, ii) == startTag) { 
    xmlTagOff = ii;  break;
  }
} // end of hack, scanning for start of first start tag

// XML tags and attributes:
// Every XML start and end tag consists of 6 32 bit words:
//   0th Word: 02011000 for startTag and 03011000 for endTag 
//   1st Word: a flag?, like 38000000
//   2nd Word: Line of where this tag appeared in the original source file
//   3rd Word: FFFFFFFF ??
//   4th Word: StringIndex of NameSpace name, or FFFFFFFF for default NS
//   5th Word: StringIndex of Element Name
//   (Note: 01011000 in 0th Word means end of XML document, endDocTag)

// Start tags (not end tags) contain 3 more words:
//   6th Word: 14001400 meaning?? 
//   7th Word: Number of Attributes that follow this tag(follow Word 8th)
//   8th Word: 00000000 meaning??

// Attributes consist of 5 words: 
//   0th Word: StringIndex of Attribute Name's Namespace, or FFFFFFFF
//   1st Word: StringIndex of Attribute Name
//   2nd Word: StringIndex of Attribute Value, or FFFFFFF if ResourceId used
//   3rd Word: Flags?
//   4th Word: str ind of attr value again, or ResourceId of value

// TMP, dump string table to tr for debugging
//tr.addSelect("strings", null);
//for (int ii=0; ii<numbStrings; ii++) {
//  // Length of string starts at StringTable plus offset in StrIndTable
//  String str = compXmlString(xml, sitOff, stOff, ii);
//  tr.add(String.valueOf(ii), str);
//}
//tr.parent();

// Step through the XML tree element tags and attributes
int off = xmlTagOff;
int indent = 0;
int startTagLineNo = -2;
while (off < xml.length) {
  int tag0 = LEW(xml, off);
  //int tag1 = LEW(xml, off+1*4);
  int lineNo = LEW(xml, off+2*4);
  //int tag3 = LEW(xml, off+3*4);
  int nameNsSi = LEW(xml, off+4*4);
  int nameSi = LEW(xml, off+5*4);

  if (tag0 == startTag) { // XML START TAG
    int tag6 = LEW(xml, off+6*4);  // Expected to be 14001400
    int numbAttrs = LEW(xml, off+7*4);  // Number of Attributes to follow
    //int tag8 = LEW(xml, off+8*4);  // Expected to be 00000000
    off += 9*4;  // Skip over 6+3 words of startTag data
    String name = compXmlString(xml, sitOff, stOff, nameSi);
    //tr.addSelect(name, null);
    startTagLineNo = lineNo;

    // Look for the Attributes
    StringBuffer sb = new StringBuffer();
    for (int ii=0; ii<numbAttrs; ii++) {
      int attrNameNsSi = LEW(xml, off);  // AttrName Namespace Str Ind, or FFFFFFFF
      int attrNameSi = LEW(xml, off+1*4);  // AttrName String Index
      int attrValueSi = LEW(xml, off+2*4); // AttrValue Str Ind, or FFFFFFFF
      int attrFlags = LEW(xml, off+3*4);  
      int attrResId = LEW(xml, off+4*4);  // AttrValue ResourceId or dup AttrValue StrInd
      off += 5*4;  // Skip over the 5 words of an attribute

      String attrName = compXmlString(xml, sitOff, stOff, attrNameSi);
      String attrValue = attrValueSi!=-1
        ? compXmlString(xml, sitOff, stOff, attrValueSi)
        : "resourceID 0x"+Integer.toHexString(attrResId);
      sb.append(" "+attrName+"=\""+attrValue+"\"");
      //tr.add(attrName, attrValue);
    }
    prtIndent(indent, "<"+name+sb+">");
    indent++;

  } else if (tag0 == endTag) { // XML END TAG
    indent--;
    off += 6*4;  // Skip over 6 words of endTag data
    String name = compXmlString(xml, sitOff, stOff, nameSi);
    prtIndent(indent, "</"+name+">  (line "+startTagLineNo+"-"+lineNo+")");
    //tr.parent();  // Step back up the NobTree

  } else if (tag0 == endDocTag) {  // END OF XML DOC TAG
    break;

  } else {
    prt("  Unrecognized tag code '"+Integer.toHexString(tag0)
      +"' at offset "+off);
    break;
  }
} // end of while loop scanning tags and attributes of XML tree
prt("    end at offset "+off);
} // end of decompressXML


public String compXmlString(byte[] xml, int sitOff, int stOff, int strInd) {
  if (strInd < 0) return null;
  int strOff = stOff + LEW(xml, sitOff+strInd*4);
  return compXmlStringAt(xml, strOff);
}


public static String spaces = "                                             ";
public void prtIndent(int indent, String str) {
  prt(spaces.substring(0, Math.min(indent*2, spaces.length()))+str);
}


// compXmlStringAt -- Return the string stored in StringTable format at
// offset strOff.  This offset points to the 16 bit string length, which 
// is followed by that number of 16 bit (Unicode) chars.
public String compXmlStringAt(byte[] arr, int strOff) {
  int strLen = arr[strOff+1]<<8&0xff00 | arr[strOff]&0xff;
  byte[] chars = new byte[strLen];
  for (int ii=0; ii<strLen; ii++) {
    chars[ii] = arr[strOff+2+ii*2];
  }
  return new String(chars);  // Hack, just use 8 byte chars
} // end of compXmlStringAt


// LEW -- Return value of a Little Endian 32 bit Word from the byte array
//   at offset off.
public int LEW(byte[] arr, int off) {
  return arr[off+3]<<24&0xff000000 | arr[off+2]<<16&0xff0000
    | arr[off+1]<<8&0xff00 | arr[off]&0xFF;
} // end of LEW

このメソッドは、AndroidManifestを処理のためにbyte []に​​読み取ります。

public void getIntents(String path) {
  try {
    JarFile jf = new JarFile(path);
    InputStream is = jf.getInputStream(jf.getEntry("AndroidManifest.xml"));
    byte[] xml = new byte[is.available()];
    int br = is.read(xml);
    //Tree tr = TrunkFactory.newTree();
    decompressXML(xml);
    //prt("XML\n"+tr.list());
  } catch (Exception ex) {
    console.log("getIntents, ex: "+ex);  ex.printStackTrace();
  }
} // end of getIntents

ほとんどのアプリは/ system/appに保存されますが、これはルートEmyがなくても読み取り可能であり、他のアプリは/ data/appにあります。上記の「パス」引数は次のようになります。「/ system/app/Weather.apk」

Answer 3

Android Asset Packaging Tool（aapt）を使用して、Android SDKからPythonへ（または何でも）スクリプト？

実際、aapt（ http://elinux.org/Android_aapt ）を介して、。apkパッケージとそのAndroidManifest.xmlファイル。特に、。apkパッケージの個々の要素の値を抽出するには、 'dump'サブコマンドを使用します。たとえば、AndroidManifest.xmlファイル内の内のuser-permissionsを抽出できます）.apkパッケージ：

$ aapt dump permissions package.apk

package.apkは。apkパッケージです。

さらに、Unix pipeコマンドを使用して出力を消去できます。例えば：

$ aapt dump permissions package.apk | sed 1d | awk '{ print $NF }'

ここにPythonスクリプトがあります。

import os
import subprocess

#Current directory and file name:
curpath = os.path.dirname( os.path.realpath(__file__) )
filepath = os.path.join(curpath, "package.apk")

#Extract the AndroidManifest.xml permissions:
command = "aapt dump permissions " + filepath + " | sed 1d | awk '{ print $NF }'"
process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=None, Shell=True)
permissions = process.communicate()[0]

print permissions

同様に、他の情報を抽出できます（例（package、app nameなど...）のAndroidManifest.xml：

#Extract the APK package info:
shellcommand = "aapt dump badging " + filepath
process = subprocess.Popen(shellcommand, stdout=subprocess.PIPE, stderr=None, Shell=True)
apkInfo = process.communicate()[0].splitlines()

for info in apkInfo:
    #Package info:
    if string.find(info, "package:", 0) != -1:
        print "App Package: " + findBetween(info, "name='", "'")
        print "App Version: " + findBetween(info, "versionName='", "'")
        continue

    #App name:
    if string.find(info, "application:", 0) != -1:
        print "App Name: " + findBetween(info, "label='", "'")
        continue


def findBetween(s, prefix, suffix):
    try:
        start = s.index(prefix) + len(prefix)
        end = s.index(suffix, start)
        return s[start:end]
    except ValueError:
        return ""

代わりに、AndroidManifest XMLツリー全体を解析する場合は、xmltreeコマンドを使用して同様の方法で解析できます。

aapt dump xmltree package.apk AndroidManifest.xml

以前と同様にPythonを使用します。

#Extract the AndroidManifest XML tree:
shellcommand = "aapt dump xmltree " + filepath + " AndroidManifest.xml"
process = subprocess.Popen(shellcommand, stdout=subprocess.PIPE, stderr=None, Shell=True)
xmlTree = process.communicate()[0]

print "Number of Activities: " + str(xmlTree.count("activity"))
print "Number of Services: " + str(xmlTree.count("service"))
print "Number of BroadcastReceivers: " + str(xmlTree.count("receiver"))

Answer 4

axml2xml.plAndroid-randomプロジェクト内で少し前に開発されたツールを使用できます。バイナリファイルからテキストマニフェストファイル（AndroidManifest.xml）を生成します。

私は「textual」ではなく「original」と言っています。多くのリバースエンジニアリングツールのように、これは完璧ではなく結果しません完全になります。機能が完全ではなかったか、単に前方互換性がない（新しいバイナリエンコーディングスキームで）のではないかと思います。理由が何であれ、axml2xml.plツールはすべての属性値を正しく抽出できません。このような属性は、minSdkVersion、targetSdkVersion、および基本的にリソース（文字列、アイコンなど）を参照しているすべての属性です。つまり、クラス名（アクティビティ、サービスなど）のみが正しく抽出されます。

ただし、元のAndroidアプリファイル（。apk）でaaptツールを実行すると、これらの欠落情報を見つけることができます。

aapt l -a<someapp.apk>

Answer 5

以下を確認してください WPF Project プロパティを正しくデコードします。

Answer 6

最新のSDKツールでは、apkanalyzerというツールを使用して、APKのAndroidManifest.xml（およびリソースなどの他の部分）を印刷できるようになりました。

[Android sdk]/tools/bin/apkanalyzer manifest print [app.apk]

apkanalyzer

Answer 7

apk-parser、 https://github.com/caoqianli/apk-parser 、Java用の軽量実装であり、aaptまたは他のバイナリに依存せず、バイナリxmlファイルの解析に適しています。 APKの情報。

ApkParser apkParser = new ApkParser(new File(filePath));
// set a locale to translate resource tag into specific strings in language the locale specified, you set locale to Locale.ENGLISH then get apk title 'WeChat' instead of '@string/app_name' for example
apkParser.setPreferredLocale(locale);

String xml = apkParser.getManifestXml();
System.out.println(xml);

String xml2 = apkParser.transBinaryXml(xmlPathInApk);
System.out.println(xml2);

ApkMeta apkMeta = apkParser.getApkMeta();
System.out.println(apkMeta);

Set<Locale> locales = apkParser.getLocales();
for (Locale l : locales) {
    System.out.println(l);
}
apkParser.close();

Answer 8

便利な場合は、Riboが投稿したJavaスニペットのC++バージョンを以下に示します。

struct decompressXML
{
    // decompressXML -- Parse the 'compressed' binary form of Android XML docs 
    // such as for AndroidManifest.xml in .apk files
    enum
    {
        endDocTag = 0x00100101,
        startTag =  0x00100102,
        endTag =    0x00100103
    };

    decompressXML(const BYTE* xml, int cb) {
    // Compressed XML file/bytes starts with 24x bytes of data,
    // 9 32 bit words in little endian order (LSB first):
    //   0th Word is 03 00 08 00
    //   3rd Word SEEMS TO BE:  Offset at then of StringTable
    //   4th Word is: Number of strings in string table
    // WARNING: Sometime I indiscriminently display or refer to Word in 
    //   little endian storage format, or in integer format (ie MSB first).
    int numbStrings = LEW(xml, cb, 4*4);

    // StringIndexTable starts at offset 24x, an array of 32 bit LE offsets
    // of the length/string data in the StringTable.
    int sitOff = 0x24;  // Offset of start of StringIndexTable

    // StringTable, each string is represented with a 16 bit little endian 
    // character count, followed by that number of 16 bit (LE) (Unicode) chars.
    int stOff = sitOff + numbStrings*4;  // StringTable follows StrIndexTable

    // XMLTags, The XML tag tree starts after some unknown content after the
    // StringTable.  There is some unknown data after the StringTable, scan
    // forward from this point to the flag for the start of an XML start tag.
    int xmlTagOff = LEW(xml, cb, 3*4);  // Start from the offset in the 3rd Word.
    // Scan forward until we find the bytes: 0x02011000(x00100102 in normal int)
    for (int ii=xmlTagOff; ii<cb-4; ii+=4) {
      if (LEW(xml, cb, ii) == startTag) { 
        xmlTagOff = ii;  break;
      }
    } // end of hack, scanning for start of first start tag

    // XML tags and attributes:
    // Every XML start and end tag consists of 6 32 bit words:
    //   0th Word: 02011000 for startTag and 03011000 for endTag 
    //   1st Word: a flag?, like 38000000
    //   2nd Word: Line of where this tag appeared in the original source file
    //   3rd Word: FFFFFFFF ??
    //   4th Word: StringIndex of NameSpace name, or FFFFFFFF for default NS
    //   5th Word: StringIndex of Element Name
    //   (Note: 01011000 in 0th Word means end of XML document, endDocTag)

    // Start tags (not end tags) contain 3 more words:
    //   6th Word: 14001400 meaning?? 
    //   7th Word: Number of Attributes that follow this tag(follow Word 8th)
    //   8th Word: 00000000 meaning??

    // Attributes consist of 5 words: 
    //   0th Word: StringIndex of Attribute Name's Namespace, or FFFFFFFF
    //   1st Word: StringIndex of Attribute Name
    //   2nd Word: StringIndex of Attribute Value, or FFFFFFF if ResourceId used
    //   3rd Word: Flags?
    //   4th Word: str ind of attr value again, or ResourceId of value

    // TMP, dump string table to tr for debugging
    //tr.addSelect("strings", null);
    //for (int ii=0; ii<numbStrings; ii++) {
    //  // Length of string starts at StringTable plus offset in StrIndTable
    //  String str = compXmlString(xml, sitOff, stOff, ii);
    //  tr.add(String.valueOf(ii), str);
    //}
    //tr.parent();

    // Step through the XML tree element tags and attributes
    int off = xmlTagOff;
    int indent = 0;
    int startTagLineNo = -2;
    while (off < cb) {
      int tag0 = LEW(xml, cb, off);
      //int tag1 = LEW(xml, off+1*4);
      int lineNo = LEW(xml, cb, off+2*4);
      //int tag3 = LEW(xml, off+3*4);
      int nameNsSi = LEW(xml, cb, off+4*4);
      int nameSi = LEW(xml, cb, off+5*4);

      if (tag0 == startTag) { // XML START TAG
        int tag6 = LEW(xml, cb, off+6*4);  // Expected to be 14001400
        int numbAttrs = LEW(xml, cb, off+7*4);  // Number of Attributes to follow
        //int tag8 = LEW(xml, off+8*4);  // Expected to be 00000000
        off += 9*4;  // Skip over 6+3 words of startTag data
        std::string name = compXmlString(xml, cb, sitOff, stOff, nameSi);
        //tr.addSelect(name, null);
        startTagLineNo = lineNo;

        // Look for the Attributes
        std::string sb;
        for (int ii=0; ii<numbAttrs; ii++) {
          int attrNameNsSi = LEW(xml, cb, off);  // AttrName Namespace Str Ind, or FFFFFFFF
          int attrNameSi = LEW(xml, cb, off+1*4);  // AttrName String Index
          int attrValueSi = LEW(xml, cb, off+2*4); // AttrValue Str Ind, or FFFFFFFF
          int attrFlags = LEW(xml, cb, off+3*4);  
          int attrResId = LEW(xml, cb, off+4*4);  // AttrValue ResourceId or dup AttrValue StrInd
          off += 5*4;  // Skip over the 5 words of an attribute

          std::string attrName = compXmlString(xml, cb, sitOff, stOff, attrNameSi);
          std::string attrValue = attrValueSi!=-1
            ? compXmlString(xml, cb, sitOff, stOff, attrValueSi)
            : "resourceID 0x"+toHexString(attrResId);
          sb.append(" "+attrName+"=\""+attrValue+"\"");
          //tr.add(attrName, attrValue);
        }
        prtIndent(indent, "<"+name+sb+">");
        indent++;

      } else if (tag0 == endTag) { // XML END TAG
        indent--;
        off += 6*4;  // Skip over 6 words of endTag data
        std::string name = compXmlString(xml, cb, sitOff, stOff, nameSi);
        prtIndent(indent, "</"+name+">  (line "+toIntString(startTagLineNo)+"-"+toIntString(lineNo)+")");
        //tr.parent();  // Step back up the NobTree

      } else if (tag0 == endDocTag) {  // END OF XML DOC TAG
        break;

      } else {
        prt("  Unrecognized tag code '"+toHexString(tag0)
          +"' at offset "+toIntString(off));
        break;
      }
    } // end of while loop scanning tags and attributes of XML tree
    prt("    end at offset "+off);
    } // end of decompressXML


    std::string compXmlString(const BYTE* xml, int cb, int sitOff, int stOff, int strInd) {
      if (strInd < 0) return std::string("");
      int strOff = stOff + LEW(xml, cb, sitOff+strInd*4);
      return compXmlStringAt(xml, cb, strOff);
    }

    void prt(std::string str)
    {
        printf("%s", str.c_str());
    }
    void prtIndent(int indent, std::string str) {
        char spaces[46];
        memset(spaces, ' ', sizeof(spaces));
        spaces[min(indent*2,  sizeof(spaces) - 1)] = 0;
        prt(spaces);
        prt(str);
        prt("\n");
    }


    // compXmlStringAt -- Return the string stored in StringTable format at
    // offset strOff.  This offset points to the 16 bit string length, which 
    // is followed by that number of 16 bit (Unicode) chars.
    std::string compXmlStringAt(const BYTE* arr, int cb, int strOff) {
        if (cb < strOff + 2) return std::string("");
      int strLen = arr[strOff+1]<<8&0xff00 | arr[strOff]&0xff;
      char* chars = new char[strLen + 1];
      chars[strLen] = 0;
      for (int ii=0; ii<strLen; ii++) {
          if (cb < strOff + 2 + ii * 2)
          {
              chars[ii] = 0;
              break;
          }
        chars[ii] = arr[strOff+2+ii*2];
      }
      std::string str(chars);
      free(chars);
      return str;
    } // end of compXmlStringAt


    // LEW -- Return value of a Little Endian 32 bit Word from the byte array
    //   at offset off.
    int LEW(const BYTE* arr, int cb, int off) {
      return (cb > off + 3) ? ( arr[off+3]<<24&0xff000000 | arr[off+2]<<16&0xff0000
          | arr[off+1]<<8&0xff00 | arr[off]&0xFF ) : 0;
    } // end of LEW

    std::string toHexString(DWORD attrResId)
    {
        char ch[20];
        sprintf_s(ch, 20, "%lx", attrResId);
        return std::string(ch);
    }
    std::string toIntString(int i)
    {
        char ch[20];
        sprintf_s(ch, 20, "%ld", i);
        return std::string(ch);
    }
};

Answer 9

Pythonを使用する場合、または Androguard を使用する場合、Androguard Androaxml機能がこの変換を行います。この機能の詳細は このブログ投稿 に追加の ドキュメントはこちら および ソースはこちら を追加しています。

使用法：

$ ./androaxml.py -h
Usage: androaxml.py [options]

Options:
-h, --help            show this help message and exit
-i INPUT, --input=INPUT
                      filename input (APK or Android's binary xml)
-o OUTPUT, --output=OUTPUT
                      filename output of the xml
-v, --version         version of the API

$ ./androaxml.py -i yourfile.apk -o output.xml
$ ./androaxml.py -i AndroidManifest.xml -o output.xml

Answer 10

ここで参照するのは、Riboのコードの私のバージョンです。主な違いは、decompressXML（）が文字列を直接返すことです。これは、私の目的にとってはより適切な使用法でした。

注：Riboのソリューションを使用する私の唯一の目的は、マニフェストXMLファイルから.APKファイルの公開バージョンを取得することでした。この目的のために、それが美しく機能することを確認します。

編集[2013-03-16]：きれいに動作しますIFバージョンはプレーンテキストとして設定されていますが、リソースXMLを参照するように設定されている場合は、 'Resource 0x1として表示されます' 例えば。この特定のケースでは、おそらくこのソリューションを、適切な文字列リソース参照を取得する別のソリューションに結合する必要があります。

/**
 * Binary XML doc ending Tag
 */
public static int endDocTag = 0x00100101;

/**
 * Binary XML start Tag
 */
public static int startTag =  0x00100102;

/**
 * Binary XML end Tag
 */
public static int endTag =    0x00100103;


/**
 * Reference var for spacing
 * Used in prtIndent()
 */
public static String spaces = "                                             ";


/**
 * Parse the 'compressed' binary form of Android XML docs 
 * such as for AndroidManifest.xml in .apk files
 * Source: http://stackoverflow.com/questions/2097813/how-to-parse-the-androidmanifest-xml-file-inside-an-apk-package/4761689#4761689
 * 
 * @param xml Encoded XML content to decompress
 */
public static String decompressXML(byte[] xml) {

    StringBuilder resultXml = new StringBuilder();

    // Compressed XML file/bytes starts with 24x bytes of data,
    // 9 32 bit words in little endian order (LSB first):
    //   0th Word is 03 00 08 00
    //   3rd Word SEEMS TO BE:  Offset at then of StringTable
    //   4th Word is: Number of strings in string table
    // WARNING: Sometime I indiscriminently display or refer to Word in 
    //   little endian storage format, or in integer format (ie MSB first).
    int numbStrings = LEW(xml, 4*4);

    // StringIndexTable starts at offset 24x, an array of 32 bit LE offsets
    // of the length/string data in the StringTable.
    int sitOff = 0x24;  // Offset of start of StringIndexTable

    // StringTable, each string is represented with a 16 bit little endian 
    // character count, followed by that number of 16 bit (LE) (Unicode) chars.
    int stOff = sitOff + numbStrings*4;  // StringTable follows StrIndexTable

    // XMLTags, The XML tag tree starts after some unknown content after the
    // StringTable.  There is some unknown data after the StringTable, scan
    // forward from this point to the flag for the start of an XML start tag.
    int xmlTagOff = LEW(xml, 3*4);  // Start from the offset in the 3rd Word.
    // Scan forward until we find the bytes: 0x02011000(x00100102 in normal int)
    for (int ii=xmlTagOff; ii<xml.length-4; ii+=4) {
      if (LEW(xml, ii) == startTag) { 
        xmlTagOff = ii;  break;
      }
    } // end of hack, scanning for start of first start tag

    // XML tags and attributes:
    // Every XML start and end tag consists of 6 32 bit words:
    //   0th Word: 02011000 for startTag and 03011000 for endTag 
    //   1st Word: a flag?, like 38000000
    //   2nd Word: Line of where this tag appeared in the original source file
    //   3rd Word: FFFFFFFF ??
    //   4th Word: StringIndex of NameSpace name, or FFFFFFFF for default NS
    //   5th Word: StringIndex of Element Name
    //   (Note: 01011000 in 0th Word means end of XML document, endDocTag)

    // Start tags (not end tags) contain 3 more words:
    //   6th Word: 14001400 meaning?? 
    //   7th Word: Number of Attributes that follow this tag(follow Word 8th)
    //   8th Word: 00000000 meaning??

    // Attributes consist of 5 words: 
    //   0th Word: StringIndex of Attribute Name's Namespace, or FFFFFFFF
    //   1st Word: StringIndex of Attribute Name
    //   2nd Word: StringIndex of Attribute Value, or FFFFFFF if ResourceId used
    //   3rd Word: Flags?
    //   4th Word: str ind of attr value again, or ResourceId of value

    // TMP, dump string table to tr for debugging
    //tr.addSelect("strings", null);
    //for (int ii=0; ii<numbStrings; ii++) {
    //  // Length of string starts at StringTable plus offset in StrIndTable
    //  String str = compXmlString(xml, sitOff, stOff, ii);
    //  tr.add(String.valueOf(ii), str);
    //}
    //tr.parent();

    // Step through the XML tree element tags and attributes
    int off = xmlTagOff;
    int indent = 0;
    int startTagLineNo = -2;
    while (off < xml.length) {
      int tag0 = LEW(xml, off);
      //int tag1 = LEW(xml, off+1*4);
      int lineNo = LEW(xml, off+2*4);
      //int tag3 = LEW(xml, off+3*4);
      int nameNsSi = LEW(xml, off+4*4);
      int nameSi = LEW(xml, off+5*4);

      if (tag0 == startTag) { // XML START TAG
        int tag6 = LEW(xml, off+6*4);  // Expected to be 14001400
        int numbAttrs = LEW(xml, off+7*4);  // Number of Attributes to follow
        //int tag8 = LEW(xml, off+8*4);  // Expected to be 00000000
        off += 9*4;  // Skip over 6+3 words of startTag data
        String name = compXmlString(xml, sitOff, stOff, nameSi);
        //tr.addSelect(name, null);
        startTagLineNo = lineNo;

        // Look for the Attributes
        StringBuffer sb = new StringBuffer();
        for (int ii=0; ii<numbAttrs; ii++) {
          int attrNameNsSi = LEW(xml, off);  // AttrName Namespace Str Ind, or FFFFFFFF
          int attrNameSi = LEW(xml, off+1*4);  // AttrName String Index
          int attrValueSi = LEW(xml, off+2*4); // AttrValue Str Ind, or FFFFFFFF
          int attrFlags = LEW(xml, off+3*4);  
          int attrResId = LEW(xml, off+4*4);  // AttrValue ResourceId or dup AttrValue StrInd
          off += 5*4;  // Skip over the 5 words of an attribute

          String attrName = compXmlString(xml, sitOff, stOff, attrNameSi);
          String attrValue = attrValueSi!=-1
            ? compXmlString(xml, sitOff, stOff, attrValueSi)
            : "resourceID 0x"+Integer.toHexString(attrResId);
          sb.append(" "+attrName+"=\""+attrValue+"\"");
          //tr.add(attrName, attrValue);
        }
        resultXml.append(prtIndent(indent, "<"+name+sb+">"));
        indent++;

      } else if (tag0 == endTag) { // XML END TAG
        indent--;
        off += 6*4;  // Skip over 6 words of endTag data
        String name = compXmlString(xml, sitOff, stOff, nameSi);
        resultXml.append(prtIndent(indent, "</"+name+">  (line "+startTagLineNo+"-"+lineNo+")"));
        //tr.parent();  // Step back up the NobTree

      } else if (tag0 == endDocTag) {  // END OF XML DOC TAG
        break;

      } else {
          Log.e(TAG, "  Unrecognized tag code '"+Integer.toHexString(tag0)
          +"' at offset "+off);
        break;
      }
    } // end of while loop scanning tags and attributes of XML tree
    Log.i(TAG, "    end at offset "+off);

    return resultXml.toString();
} // end of decompressXML


/**
 * Tool Method for decompressXML();
 * Compute binary XML to its string format 
 * Source: Source: http://stackoverflow.com/questions/2097813/how-to-parse-the-androidmanifest-xml-file-inside-an-apk-package/4761689#4761689
 * 
 * @param xml Binary-formatted XML
 * @param sitOff
 * @param stOff
 * @param strInd
 * @return String-formatted XML
 */
public static String compXmlString(byte[] xml, int sitOff, int stOff, int strInd) {
  if (strInd < 0) return null;
  int strOff = stOff + LEW(xml, sitOff+strInd*4);
  return compXmlStringAt(xml, strOff);
}


/**
 * Tool Method for decompressXML(); 
 * Apply indentation
 * 
 * @param indent Indentation level
 * @param str String to indent
 * @return Indented string
 */
public static String prtIndent(int indent, String str) {

    return (spaces.substring(0, Math.min(indent*2, spaces.length()))+str);
}


/** 
 * Tool method for decompressXML()
 * Return the string stored in StringTable format at
 * offset strOff.  This offset points to the 16 bit string length, which 
 * is followed by that number of 16 bit (Unicode) chars.
 * 
 * @param arr StringTable array
 * @param strOff Offset to get string from
 * @return String from StringTable at offset strOff
 * 
 */
public static String compXmlStringAt(byte[] arr, int strOff) {
  int strLen = arr[strOff+1]<<8&0xff00 | arr[strOff]&0xff;
  byte[] chars = new byte[strLen];
  for (int ii=0; ii<strLen; ii++) {
    chars[ii] = arr[strOff+2+ii*2];
  }
  return new String(chars);  // Hack, just use 8 byte chars
} // end of compXmlStringAt


/** 
 * Return value of a Little Endian 32 bit Word from the byte array
 *   at offset off.
 * 
 * @param arr Byte array with 32 bit Word
 * @param off Offset to get Word from
 * @return Value of Little Endian 32 bit Word specified
 */
public static int LEW(byte[] arr, int off) {
  return arr[off+3]<<24&0xff000000 | arr[off+2]<<16&0xff0000
    | arr[off+1]<<8&0xff00 | arr[off]&0xFF;
} // end of LEW

他の人にも役立つことを願っています。

Answer 11

Android studio 2.2では、apkを直接分析できます。 Gotoビルド-APKを分析します。 apkを選択し、androidmanifest.xmlに移動します。 androidmanifestの詳細を確認できます。

Answer 12

私は1年以上にわたって上記のRiboコードで実行してきましたが、それは私たちに役立っています。しかし、最近の更新（Gradle 3.x）では、AndroidManifest.xmlを解析できなくなり、インデックスの範囲外エラーが発生し、一般的にファイルを解析できなくなりました。

更新：現在、私たちの問題はGradle 3.xへのアップグレードにあったと考えています。この記事では、AirWatchに問題があり、aapt2の代わりにaaptを使用するGradle設定を使用して修正できる方法について説明します AirWatchはGradle 3.0.0-beta1のAndroidプラグインと互換性がないようです

周りを検索すると、このオープンソースプロジェクトに出会い、それが維持されているので、私は以前に解析できた古いAPKとRiboのロジックが例外をスローした新しいAPKの両方に到達することができました

https://github.com/xgouchet/AXML

彼の例から、これは私がやっていることです

  zf = new ZipFile(apkFile);

  //Getting the manifest
  ZipEntry entry = zf.getEntry("AndroidManifest.xml");
  InputStream is = zf.getInputStream(entry);

     // Read our manifest Document
     Document manifestDoc = new CompressedXmlParser().parseDOM(is);

     // Make sure we got a doc, and that it has children
     if (null != manifestDoc && manifestDoc.getChildNodes().getLength() > 0) {
        //
        Node firstNode = manifestDoc.getFirstChild();

        // Now get the attributes out of the node
        NamedNodeMap nodeMap = firstNode.getAttributes();

        // Finally to a point where we can read out our values
        versionName = nodeMap.getNamedItem("Android:versionName").getNodeValue();
        versionCode = nodeMap.getNamedItem("Android:versionCode").getNodeValue();
     }

Answer 13

Android4MeプロジェクトでJavaアプリであるAXMLPrinter2を見つけて、AndroidManifest.xmlで正常に動作することを確認しました（そして、XMLを適切な形式で出力します）。 http://code.google.com/p/Android4me/downloads/detail?name=AXMLPrinter2.jar

1つの注意..（およびRiboからのこの回答のコード）は、私が遭遇したすべてのコンパイル済みXMLファイルを処理するようには見えません。文字列が想定されている2バイト形式ではなく、文字ごとに1バイトで格納されているものを見つけました。

Answer 14

Kotlinバージョンは次のとおりです。@ Mathieu

fun main(args : Array<String>) {
    val fileName = "app.apk"
    ZipFile(fileName).use { Zip ->
        Zip.entries().asSequence().forEach { entry ->
            if(entry.name == "AndroidManifest.xml") {
                Zip.getInputStream(entry).use { input ->
                    val xml = decompressXML(input.readBytes())
                    //TODO: parse the XML
                    println(xml)

                }
            }
        }
    }
}

    /**
     * Binary XML doc ending Tag
     */
    var endDocTag = 0x00100101

    /**
     * Binary XML start Tag
     */
    var startTag = 0x00100102

    /**
     * Binary XML end Tag
     */
    var endTag = 0x00100103


    /**
     * Reference var for spacing
     * Used in prtIndent()
     */
    var spaces = "                                             "


    /**
     * Parse the 'compressed' binary form of Android XML docs
     * such as for AndroidManifest.xml in .apk files
     * Source: http://stackoverflow.com/questions/2097813/how-to-parse-the-androidmanifest-xml-file-inside-an-apk-package/4761689#4761689
     *
     * @param xml Encoded XML content to decompress
     */
    fun decompressXML(xml: ByteArray): String {

        val resultXml = StringBuilder()

        // Compressed XML file/bytes starts with 24x bytes of data,
        // 9 32 bit words in little endian order (LSB first):
        //   0th Word is 03 00 08 00
        //   3rd Word SEEMS TO BE:  Offset at then of StringTable
        //   4th Word is: Number of strings in string table
        // WARNING: Sometime I indiscriminently display or refer to Word in
        //   little endian storage format, or in integer format (ie MSB first).
        val numbStrings = LEW(xml, 4 * 4)

        // StringIndexTable starts at offset 24x, an array of 32 bit LE offsets
        // of the length/string data in the StringTable.
        val sitOff = 0x24  // Offset of start of StringIndexTable

        // StringTable, each string is represented with a 16 bit little endian
        // character count, followed by that number of 16 bit (LE) (Unicode) chars.
        val stOff = sitOff + numbStrings * 4  // StringTable follows StrIndexTable

        // XMLTags, The XML tag tree starts after some unknown content after the
        // StringTable.  There is some unknown data after the StringTable, scan
        // forward from this point to the flag for the start of an XML start tag.
        var xmlTagOff = LEW(xml, 3 * 4)  // Start from the offset in the 3rd Word.
        // Scan forward until we find the bytes: 0x02011000(x00100102 in normal int)
        run {
            var ii = xmlTagOff
            while (ii < xml.size - 4) {
                if (LEW(xml, ii) == startTag) {
                    xmlTagOff = ii
                    break
                }
                ii += 4
            }
        } // end of hack, scanning for start of first start tag

        // XML tags and attributes:
        // Every XML start and end tag consists of 6 32 bit words:
        //   0th Word: 02011000 for startTag and 03011000 for endTag
        //   1st Word: a flag?, like 38000000
        //   2nd Word: Line of where this tag appeared in the original source file
        //   3rd Word: FFFFFFFF ??
        //   4th Word: StringIndex of NameSpace name, or FFFFFFFF for default NS
        //   5th Word: StringIndex of Element Name
        //   (Note: 01011000 in 0th Word means end of XML document, endDocTag)

        // Start tags (not end tags) contain 3 more words:
        //   6th Word: 14001400 meaning??
        //   7th Word: Number of Attributes that follow this tag(follow Word 8th)
        //   8th Word: 00000000 meaning??

        // Attributes consist of 5 words:
        //   0th Word: StringIndex of Attribute Name's Namespace, or FFFFFFFF
        //   1st Word: StringIndex of Attribute Name
        //   2nd Word: StringIndex of Attribute Value, or FFFFFFF if ResourceId used
        //   3rd Word: Flags?
        //   4th Word: str ind of attr value again, or ResourceId of value

        // TMP, dump string table to tr for debugging
        //tr.addSelect("strings", null);
        //for (int ii=0; ii<numbStrings; ii++) {
        //  // Length of string starts at StringTable plus offset in StrIndTable
        //  String str = compXmlString(xml, sitOff, stOff, ii);
        //  tr.add(String.valueOf(ii), str);
        //}
        //tr.parent();

        // Step through the XML tree element tags and attributes
        var off = xmlTagOff
        var indent = 0
        var startTagLineNo = -2
        while (off < xml.size) {
            val tag0 = LEW(xml, off)
            //int tag1 = LEW(xml, off+1*4);
            val lineNo = LEW(xml, off + 2 * 4)
            //int tag3 = LEW(xml, off+3*4);
            val nameNsSi = LEW(xml, off + 4 * 4)
            val nameSi = LEW(xml, off + 5 * 4)

            if (tag0 == startTag) { // XML START TAG
                val tag6 = LEW(xml, off + 6 * 4)  // Expected to be 14001400
                val numbAttrs = LEW(xml, off + 7 * 4)  // Number of Attributes to follow
                //int tag8 = LEW(xml, off+8*4);  // Expected to be 00000000
                off += 9 * 4  // Skip over 6+3 words of startTag data
                val name = compXmlString(xml, sitOff, stOff, nameSi)
                //tr.addSelect(name, null);
                startTagLineNo = lineNo

                // Look for the Attributes
                val sb = StringBuffer()
                for (ii in 0 until numbAttrs) {
                    val attrNameNsSi = LEW(xml, off)  // AttrName Namespace Str Ind, or FFFFFFFF
                    val attrNameSi = LEW(xml, off + 1 * 4)  // AttrName String Index
                    val attrValueSi = LEW(xml, off + 2 * 4) // AttrValue Str Ind, or FFFFFFFF
                    val attrFlags = LEW(xml, off + 3 * 4)
                    val attrResId = LEW(xml, off + 4 * 4)  // AttrValue ResourceId or dup AttrValue StrInd
                    off += 5 * 4  // Skip over the 5 words of an attribute

                    val attrName = compXmlString(xml, sitOff, stOff, attrNameSi)
                    val attrValue = if (attrValueSi != -1)
                        compXmlString(xml, sitOff, stOff, attrValueSi)
                    else
                        "resourceID 0x" + Integer.toHexString(attrResId)
                    sb.append(" $attrName=\"$attrValue\"")
                    //tr.add(attrName, attrValue);
                }
                resultXml.append(prtIndent(indent, "<$name$sb>"))
                indent++

            } else if (tag0 == endTag) { // XML END TAG
                indent--
                off += 6 * 4  // Skip over 6 words of endTag data
                val name = compXmlString(xml, sitOff, stOff, nameSi)
                resultXml.append(prtIndent(indent, "</$name>  (line $startTagLineNo-$lineNo)"))
                //tr.parent();  // Step back up the NobTree

            } else if (tag0 == endDocTag) {  // END OF XML DOC TAG
                break

            } else {
                        println("  Unrecognized tag code '" + Integer.toHexString(tag0)
                            + "' at offset " + off
                )
                break
            }
        } // end of while loop scanning tags and attributes of XML tree
        println("    end at offset $off")

        return resultXml.toString()
    } // end of decompressXML


    /**
     * Tool Method for decompressXML();
     * Compute binary XML to its string format
     * Source: Source: http://stackoverflow.com/questions/2097813/how-to-parse-the-androidmanifest-xml-file-inside-an-apk-package/4761689#4761689
     *
     * @param xml Binary-formatted XML
     * @param sitOff
     * @param stOff
     * @param strInd
     * @return String-formatted XML
     */
    fun compXmlString(xml: ByteArray, sitOff: Int, stOff: Int, strInd: Int): String? {
        if (strInd < 0) return null
        val strOff = stOff + LEW(xml, sitOff + strInd * 4)
        return compXmlStringAt(xml, strOff)
    }


    /**
     * Tool Method for decompressXML();
     * Apply indentation
     *
     * @param indent Indentation level
     * @param str String to indent
     * @return Indented string
     */
    fun prtIndent(indent: Int, str: String): String {

        return spaces.substring(0, Math.min(indent * 2, spaces.length)) + str
    }


    /**
     * Tool method for decompressXML()
     * Return the string stored in StringTable format at
     * offset strOff.  This offset points to the 16 bit string length, which
     * is followed by that number of 16 bit (Unicode) chars.
     *
     * @param arr StringTable array
     * @param strOff Offset to get string from
     * @return String from StringTable at offset strOff
     */
    fun compXmlStringAt(arr: ByteArray, strOff: Int): String {
        val strLen = (arr[strOff + 1] shl (8 and 0xff00)) or (arr[strOff].toInt() and 0xff)
        val chars = ByteArray(strLen)
        for (ii in 0 until strLen) {
            chars[ii] = arr[strOff + 2 + ii * 2]
        }
        return String(chars)  // Hack, just use 8 byte chars
    } // end of compXmlStringAt


    /**
     * Return value of a Little Endian 32 bit Word from the byte array
     * at offset off.
     *
     * @param arr Byte array with 32 bit Word
     * @param off Offset to get Word from
     * @return Value of Little Endian 32 bit Word specified
     */
    fun LEW(arr: ByteArray, off: Int): Int {
        return (arr[off + 3] shl 24 and -0x1000000 or ((arr[off + 2] shl 16) and 0xff0000)
                or (arr[off + 1] shl 8 and 0xff00) or (arr[off].toInt() and 0xFF))
    } // end of LEW

    private infix fun Byte.shl(i: Int): Int = (this.toInt() shl i)
    private infix fun Int.shl(i: Int): Int = (this shl i)

これは上記の答えのkotlinバージョンです。

Answer 15

役立つことがあります

public static int vCodeApk(String path) {
    PackageManager pm = G.context.getPackageManager();
    PackageInfo info = pm.getPackageArchiveInfo(path, 0);
    return info.versionCode;
    //        Toast.makeText(this, "VersionCode : " + info.versionCode + ", VersionName : " + info.versionName, Toast.LENGTH_LONG).show();
}

Gは私のアプリケーションクラスです：

public class G extends Application {

Answer 16

apkanalyzerが役立ちます

@echo off

::##############################################################################
::##
::##  apkanalyzer start up script for Windows
::##
::##  converted by ewwink
::##
::##############################################################################

::Attempt to set APP_HOME

SET SAVED=%cd%
SET APP_HOME=C:\Android\sdk\tools
SET APP_NAME="apkanalyzer"

::Add default JVM options here. You can also use Java_OPTS and APKANALYZER_OPTS to pass JVM options to this script.
SET DEFAULT_JVM_OPTS=-Dcom.Android.sdklib.toolsdir=%APP_HOME%

SET CLASSPATH=%APP_HOME%\lib\dvlib-26.0.0-dev.jar;%APP_HOME%\lib\util-2.2.1.jar;%APP_HOME%\lib\jimfs-1.1.jar;%APP_HOME%\lib\annotations-13.0.jar;%APP_HOME%\lib\ddmlib-26.0.0-dev.jar;%APP_HOME%\lib\repository-26.0.0-dev.jar;%APP_HOME%\lib\sdk-common-26.0.0-dev.jar;%APP_HOME%\lib\kotlin-stdlib-1.1.3-2.jar;%APP_HOME%\lib\protobuf-Java-3.0.0.jar;%APP_HOME%\lib\apkanalyzer-cli.jar;%APP_HOME%\lib\gson-2.3.jar;%APP_HOME%\lib\httpcore-4.2.5.jar;%APP_HOME%\lib\dexlib2-2.2.1.jar;%APP_HOME%\lib\commons-compress-1.12.jar;%APP_HOME%\lib\generator.jar;%APP_HOME%\lib\error_prone_annotations-2.0.18.jar;%APP_HOME%\lib\commons-codec-1.6.jar;%APP_HOME%\lib\kxml2-2.3.0.jar;%APP_HOME%\lib\httpmime-4.1.jar;%APP_HOME%\lib\annotations-12.0.jar;%APP_HOME%\lib\bcpkix-jdk15on-1.56.jar;%APP_HOME%\lib\jsr305-3.0.0.jar;%APP_HOME%\lib\explainer.jar;%APP_HOME%\lib\builder-model-3.0.0-dev.jar;%APP_HOME%\lib\baksmali-2.2.1.jar;%APP_HOME%\lib\j2objc-annotations-1.1.jar;%APP_HOME%\lib\layoutlib-api-26.0.0-dev.jar;%APP_HOME%\lib\jcommander-1.64.jar;%APP_HOME%\lib\commons-logging-1.1.1.jar;%APP_HOME%\lib\annotations-26.0.0-dev.jar;%APP_HOME%\lib\builder-test-api-3.0.0-dev.jar;%APP_HOME%\lib\animal-sniffer-annotations-1.14.jar;%APP_HOME%\lib\bcprov-jdk15on-1.56.jar;%APP_HOME%\lib\httpclient-4.2.6.jar;%APP_HOME%\lib\common-26.0.0-dev.jar;%APP_HOME%\lib\jopt-simple-4.9.jar;%APP_HOME%\lib\sdklib-26.0.0-dev.jar;%APP_HOME%\lib\apkanalyzer.jar;%APP_HOME%\lib\shared.jar;%APP_HOME%\lib\binary-resources.jar;%APP_HOME%\lib\guava-22.0.jar

SET APP_ARGS=%*
::Collect all arguments for the Java command, following the Shell quoting and substitution rules
SET APKANALYZER_OPTS=%DEFAULT_JVM_OPTS% -classpath %CLASSPATH% com.Android.tools.apk.analyzer.ApkAnalyzerCli %APP_ARGS%

::Determine the Java command to use to start the JVM.
SET JAVACMD="Java"
where %JAVACMD% >nul 2>nul
if %errorlevel%==1 (
  echo ERROR: 'Java' command could be found in your PATH.
  echo Please set the 'Java' variable in your environment to match the
  echo location of your Java installation.
  echo.
  exit /b 0
)

:: execute apkanalyzer

%JAVACMD% %APKANALYZER_OPTS%

元の投稿 https://stackoverflow.com/a/51905063/1383521