File ini tampaknya dalam format XML biner. Apa format ini dan bagaimana cara mem-parsing secara terprogram (sebagai lawan dari menggunakan aapt dump tool di SDK)?

Format biner ini tidak dibahas dalam dokumentasi di sini .

Catatan : Saya ingin mengakses informasi ini dari luar lingkungan Android, lebih disukai dari Jawa.

Gunakan android-apktool

Ada aplikasi yang membaca file apk dan menerjemahkan XML ke bentuk yang hampir asli.

Pemakaian:

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

Periksa android-apktool untuk informasi lebih lanjut

Metode Java ini, yang berjalan pada Android, mendokumentasikan (apa yang saya bisa tafsirkan) format biner dari file AndroidManifest.xml dalam paket .apk. Kotak kode kedua menunjukkan cara memanggil decompressXML dan cara memuat byte [] dari file paket aplikasi pada perangkat. (Ada bidang yang tujuannya tidak saya mengerti, jika Anda tahu artinya, katakan padaku, saya akan memperbarui informasinya.)

// 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

Metode ini membaca AndroidManifest ke dalam byte [] untuk diproses:

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

Sebagian besar aplikasi disimpan di / system / app yang dapat dibaca tanpa me-root Evo saya, aplikasi lain berada di / data / app yang saya butuhkan untuk melihatnya. Argumen 'jalur' di atas adalah sesuatu seperti: "/system/app/Weather.apk"

Bagaimana dengan menggunakan Perangkat Pengemasan Aset Android (aapt), dari Android SDK, menjadi skrip Python (atau apa pun)?

Melalui aapt ( http://elinux.org/Android_aapt ), memang, Anda dapat mengambil informasi tentang paket .apk dan tentang file AndroidManifest.xml -nya . Secara khusus, Anda dapat mengekstrak nilai elemen individual dari paket .apk melalui sub-perintah 'dump' . Misalnya, Anda dapat mengekstrak izin pengguna dalam file AndroidManifest.xml di dalam paket .apk dengan cara ini:

$ aapt dump permissions package.apk

Di mana package.apk adalah paket .apk Anda .

Selain itu, Anda dapat menggunakan perintah pipa Unix untuk menghapus output. Sebagai contoh:

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

Berikut skrip Python untuk itu secara terprogram:

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

Dengan cara yang sama Anda dapat mengekstrak informasi lain (mis. Paket , nama aplikasi , dll ...) dari 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 ""

Jika Anda ingin mem-parsing seluruh pohon AndroidManifest XML, Anda bisa melakukannya dengan cara yang sama menggunakan perintah xmltree :

aapt dump xmltree package.apk AndroidManifest.xml

Menggunakan Python seperti sebelumnya:

#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"))

Anda dapat menggunakan alat axml2xml.pl yang dikembangkan beberapa waktu lalu dalam proyek android-random . Ini akan menghasilkan file manifes teks (AndroidManifest.xml) dari file biner.

Saya mengatakan " tekstual " dan bukan " asli " karena seperti banyak alat reverse-engineering yang satu ini tidak sempurna dan hasilnya tidak akan lengkap . Saya kira itu tidak pernah fitur lengkap atau hanya tidak kompatibel dengan maju (dengan skema pengkodean biner yang lebih baru). Apa pun alasannya, alat axml2xml.pl tidak akan dapat mengekstraksi semua nilai atribut dengan benar. Atribut tersebut adalah minSdkVersion, targetSdkVersion, dan pada dasarnya semua atribut yang mereferensikan sumber daya (seperti string, ikon, dll.), Yaitu hanya nama kelas (aktivitas, layanan, dll.) Yang diekstraksi dengan benar.

Namun, Anda masih dapat menemukan informasi yang hilang ini dengan menjalankan alat aapt pada file aplikasi Android asli ( .apk ):

aapt l -a <someapp.apk>

Dengan SDK-Tools terbaru, Anda sekarang dapat menggunakan alat yang disebut apkanalyzer untuk mencetak AndroidManifest.xml dari APK (serta bagian lain, seperti sumber daya).

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

apkanalyzer

Periksa Proyek WPF berikut yang menerjemahkan properti dengan benar.

apk-parser, https://github.com/caoqianli/apk-parser , alat ringan untuk java, tanpa ketergantungan untuk aapt atau biner lainnya, bagus untuk parse file biner xml, dan info apk lainnya.

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();

Jika Anda menggunakan Python atau menggunakan Androguard , fitur Androguard Androaxml akan melakukan konversi ini untuk Anda. Fitur ini dirinci dalam posting blog ini , dengan dokumentasi tambahan di sini dan sumber di sini .

Pemakaian:

$ ./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

Jika berguna, berikut adalah versi C ++ dari cuplikan Java yang diposting oleh 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);
    }
};

untuk referensi di sini adalah versi kode Ribo saya. Perbedaan utamanya adalah bahwa decompressXML () langsung mengembalikan sebuah String, yang untuk tujuan saya adalah penggunaan yang lebih tepat.

CATATAN: Satu-satunya tujuan saya dalam menggunakan solusi Ribo adalah untuk mengambil versi file .APK yang diterbitkan dari file XML Manifest, dan saya mengonfirmasi bahwa untuk tujuan ini berfungsi dengan baik.

EDIT [2013-03-16]: Ini berfungsi dengan baik JIKA versi ini ditetapkan sebagai teks biasa, tetapi jika diatur untuk merujuk ke Resource XML, itu akan muncul sebagai 'Sumber Daya 0x1' misalnya. Dalam kasus khusus ini, Anda mungkin harus memasangkan solusi ini ke solusi lain yang akan mengambil referensi sumber daya string yang tepat.

/**
 * 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

Semoga bisa membantu orang lain juga.

Di Android studio 2.2 Anda dapat langsung menganalisis apk. Goto build-analysis apk. Pilih apk, arahkan ke androidmanifest.xml. Anda dapat melihat detail dari androidmanifest.

Versi @Mathieu Kotlin mengikuti:

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)

Ini adalah versi kotlin dari jawaban di atas.

Saya menemukan AXMLPrinter2, aplikasi Java di proyek Android4Me untuk bekerja dengan baik di AndroidManifest.xml yang saya miliki (dan mencetak XML dengan cara yang diformat dengan baik). http://code.google.com/p/android4me/downloads/detail?name=AXMLPrinter2.jar

Satu catatan .. itu (dan kode pada jawaban ini dari Ribo) tampaknya tidak menangani setiap file XML terkompilasi yang saya temui. Saya menemukan satu di mana string disimpan dengan satu byte per karakter, daripada format byte ganda yang diasumsikan.

ini bisa membantu

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 adalah kelas Aplikasi saya:

public class G extends Application {

Saya telah menjalankan dengan kode Ribo yang diposting di atas selama lebih dari setahun, dan itu telah membantu kami dengan baik. Namun, dengan pembaruan terkini (Gradle 3.x), saya tidak lagi dapat menguraikan AndroidManifest.xml, saya mendapatkan indeks dari kesalahan batas, dan secara umum tidak lagi dapat mengurai file.

Pembaruan: Saya sekarang percaya bahwa masalah kami adalah peningkatan ke Gradle 3.x. Artikel ini menjelaskan bagaimana AirWatch memiliki masalah dan dapat diperbaiki dengan menggunakan pengaturan Gradle untuk menggunakan aapt bukannya aapt2 AirWatch tampaknya tidak kompatibel dengan Plugin Android untuk Gradle 3.0.0-beta1

Ketika mencari-cari, saya menemukan proyek open source ini, dan itu sedang dipertahankan dan saya bisa langsung ke intinya dan membaca kedua APK lama saya yang sebelumnya bisa saya uraikan, dan APK baru yang logika dari Ribo melempar pengecualian.

https://github.com/xgouchet/AXML

Dari contohnya inilah yang saya lakukan

  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 akan sangat membantu

@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%

pos asli https://stackoverflow.com/a/51905063/1383521