Este archivo parece estar en formato XML binario. ¿Cuál es este formato y cómo se puede analizar mediante programación (en lugar de utilizar la herramienta de volcado aapt en el SDK)?

Este formato binario no se trata en la documentación aquí .

Nota : Deseo acceder a esta información desde fuera del entorno de Android, preferiblemente desde Java.

Utilice android-apktool

Hay una aplicación que lee archivos apk y decodifica XML a su forma casi original.

Uso:

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

Consulte android-apktool para más información

Este método Java, que se ejecuta en un Android, documenta (sobre lo que he podido interpretar) el formato binario del archivo AndroidManifest.xml en el paquete .apk. El segundo cuadro de código muestra cómo llamar a decompressXML y cómo cargar el byte [] desde el archivo del paquete de la aplicación en el dispositivo. (Hay campos cuyo propósito no entiendo, si sabes lo que significan, dime, actualizaré la información).

// 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

Este método lee el AndroidManifest en un byte [] para procesar:

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

La mayoría de las aplicaciones se almacenan en / system / app que es legible sin root mi Evo, otras aplicaciones están en / data / app que necesitaba root para ver. El argumento 'ruta' anterior sería algo como: "/system/app/Weather.apk"

¿Qué pasa con el uso de Android Asset Packaging Tool (aapt), desde el SDK de Android, en un script Python (o lo que sea)?

A través del aapt ( http://elinux.org/Android_aapt ), de hecho, puede recuperar información sobre el paquete .apk y sobre su archivo AndroidManifest.xml . En particular, puede extraer los valores de elementos individuales de un paquete .apk a través del subcomando 'dump' . Por ejemplo, puede extraer los permisos de usuario en el archivo AndroidManifest.xml dentro de un paquete .apk de esta manera:

$ aapt dump permissions package.apk

Donde package.apk es tu paquete .apk .

Además, puede usar el comando de tubería Unix para borrar la salida. Por ejemplo:

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

Aquí un script de Python que a eso programáticamente:

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

De manera similar, puede extraer otra información (por ejemplo , paquete , nombre de la aplicación , etc.) del 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 ""

Si, en cambio, desea analizar todo el árbol XML de AndroidManifest, puede hacerlo de manera similar con el comando xmltree :

aapt dump xmltree package.apk AndroidManifest.xml

Usando Python como antes:

#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"))

Puede usar la herramienta axml2xml.pl desarrollada hace un tiempo dentro del proyecto android-random . Generará el archivo de manifiesto textual (AndroidManifest.xml) a partir del binario.

Digo " textual " y no " original " porque, como muchas herramientas de ingeniería inversa, esta no es perfecta y el resultado no será completo . Supongo que nunca se completó la función o simplemente no era compatible con el reenvío (con el nuevo esquema de codificación binaria). Cualquiera sea la razón, la herramienta axml2xml.pl no podrá extraer todos los valores de los atributos correctamente. Dichos atributos son minSdkVersion, targetSdkVersion y básicamente todos los atributos que hacen referencia a recursos (como cadenas, iconos, etc.), es decir, solo se extraen correctamente los nombres de clase (de actividades, servicios, etc.).

Sin embargo, aún puede encontrar esta información faltante ejecutando una herramienta en el archivo original de la aplicación de Android ( .apk ):

aapt l -a <someapp.apk>

Con las últimas herramientas SDK, ahora puede usar una herramienta llamada apkanalyzer para imprimir el AndroidManifest.xml de un APK (así como otras partes, como recursos).

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

apkanalyzer

Verifique esto a continuación del Proyecto WPF que decodifica las propiedades correctamente.

apk-parser, https://github.com/caoqianli/apk-parser , un impl ligero para java, sin dependencia de aapt u otros binarios, es bueno para analizar archivos binarios xml y otras informaciones de apk.

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();

Si estás en Python o usas Androguard , la función Androguard Androaxml hará esta conversión por ti. La característica se detalla en esta publicación de blog , con documentación adicional aquí y fuente aquí .

Uso:

$ ./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

En caso de que sea útil, aquí hay una versión C ++ del fragmento de Java publicado por Ribo:

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);
    }
};

para referencia aquí está mi versión del código de Ribo. La principal diferencia es que decompressXML () devuelve directamente una cadena, que para mi propósito fue un uso más apropiado.

NOTA: mi único propósito al usar la solución de Ribo era obtener una versión publicada del archivo .APK del archivo XML Manifest, y confirmo que para este propósito funciona de maravilla.

EDITAR [2013-03-16]: Funciona maravillosamente SI la versión está configurada como texto sin formato, pero si está configurada para hacer referencia a un XML de recursos, aparecerá como 'Recurso 0x1' por ejemplo. En este caso particular, probablemente tenga que acoplar esta solución a otra solución que obtenga la referencia de recursos de cadena adecuada.

/**
 * 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

Espero que pueda ayudar a otras personas también.

En Android studio 2.2 puedes analizar directamente el apk. Ir a construir- analizar apk. Seleccione el apk, navegue a androidmanifest.xml. Puedes ver los detalles de androidmanifest.

La versión de @Mathieu Kotlin sigue:

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)

Esta es una versión kotlin de la respuesta anterior.

Encontré la AXMLPrinter2, una aplicación Java en el proyecto Android4Me que funciona bien en el AndroidManifest.xml que tenía (e imprime el XML de una forma muy bien formateada). http://code.google.com/p/android4me/downloads/detail?name=AXMLPrinter2.jar

Una nota ... (y el código en esta respuesta de Ribo) no parece manejar todos los archivos XML compilados que he encontrado. Encontré uno donde las cadenas se almacenaban con un byte por carácter, en lugar del formato de doble byte que asume.

puede ser útil

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 es mi clase de aplicación:

public class G extends Application {

He estado utilizando el código Ribo publicado anteriormente durante más de un año, y nos ha servido bien. Sin embargo, con las actualizaciones recientes (Gradle 3.x), ya no podía analizar el AndroidManifest.xml, estaba obteniendo errores de índice fuera de los límites y, en general, ya no podía analizar el archivo.

Actualización: ahora creo que nuestros problemas fueron con la actualización a Gradle 3.x. Este artículo describe cómo AirWatch tuvo problemas y se puede solucionar mediante el uso de una configuración de Gradle para usar aapt en lugar de aapt2 AirWatch parece ser incompatible con el complemento de Android para Gradle 3.0.0-beta1

Al buscar me encontré con este proyecto de código abierto, y se está manteniendo y pude llegar al punto y leer tanto mis viejos APK que pude analizar previamente como los nuevos APK que la lógica de Ribo arrojó excepciones

https://github.com/xgouchet/AXML

De su ejemplo, esto es lo que estoy haciendo.

  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();
     }

apkanalyzer será útil

@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%

publicación original https://stackoverflow.com/a/51905063/1383521