Wygląda na to, że ten plik ma binarny format XML. Co to za format i jak można go przeanalizować programowo (w przeciwieństwie do używania narzędzia aapt dump w SDK)?

Ten format binarny nie jest omawiany w dokumentacji tutaj .

Uwaga : chcę uzyskać dostęp do tych informacji spoza środowiska Android, najlepiej z poziomu Java.

Użyj android-apktool

Istnieje aplikacja, która czyta pliki apk i dekoduje XML do prawie oryginalnej postaci.

Stosowanie:

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

Sprawdź Android apktool aby uzyskać więcej informacji

Ta metoda Java, która działa na Androidzie, dokumentuje (o czym byłem w stanie zinterpretować) format binarny pliku AndroidManifest.xml w pakiecie .apk. Drugie pole z kodem pokazuje, jak wywołać decompressXML i jak załadować bajt [] z pliku pakietu aplikacji na urządzeniu. (Są pola, których celu nie rozumiem, jeśli wiesz, co oznaczają, powiedz mi, zaktualizuję informacje.)

// 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

Ta metoda odczytuje AndroidManifest do bajtu [] w celu przetworzenia:

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

Większość aplikacji jest przechowywana w / system / app, który można odczytać bez rootowania mojego Evo, inne aplikacje znajdują się w / data / app, do których potrzebowałem roota. Powyższy argument „ścieżka” wyglądałby tak: „/system/app/Weather.apk”

A co z użyciem narzędzia do pakowania zasobów systemu Android (aapt), z zestawu Android SDK, do skryptu w języku Python (lub cokolwiek innego)?

Za pośrednictwem aapt ( http://elinux.org/Android_aapt ) można rzeczywiście pobrać informacje o pakiecie .apk i jego pliku AndroidManifest.xml . W szczególności można wyodrębnić wartości poszczególnych elementów pakietu .apk za pomocą polecenia podrzędnego „dump” . Na przykład, możesz wyodrębnić uprawnienia użytkownika w pliku AndroidManifest.xml wewnątrz pakietu .apk w następujący sposób:

$ aapt dump permissions package.apk

Gdzie package.apk to Twój pakiet .apk .

Co więcej, możesz użyć polecenia potoku systemu Unix, aby wyczyścić dane wyjściowe. Na przykład:

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

Tutaj skrypt w Pythonie, który do tego programowo:

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

W podobny sposób możesz wyodrębnić inne informacje (np. Pakiet , nazwa aplikacji itp.) Z pliku 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 ""

Jeśli zamiast tego chcesz przeanalizować całe drzewo XML AndroidManifest, możesz to zrobić w podobny sposób za pomocą polecenia xmltree :

aapt dump xmltree package.apk AndroidManifest.xml

Używanie Pythona jak poprzednio:

#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"))

Możesz skorzystać z narzędzia axml2xml.pl opracowanego jakiś czas temu w ramach projektu android-random . Wygeneruje tekstowy plik manifestu (AndroidManifest.xml) z pliku binarnego.

Mówię „ tekstowy ”, a nie „ oryginalny ”, ponieważ podobnie jak wiele narzędzi do inżynierii odwrotnej, to nie jest doskonałe, a wynik nie będzie kompletny . Zakładam, że albo nigdy nie był on kompletny, albo po prostu nie był kompatybilny z nowszymi wersjami binarnymi. Niezależnie od przyczyny, narzędzie axml2xml.pl nie będzie w stanie poprawnie wyodrębnić wszystkich wartości atrybutów. Takie atrybuty to minSdkVersion, targetSdkVersion i w zasadzie wszystkie atrybuty, które odwołują się do zasobów (jak napisy, ikony itp.), Tj. Tylko nazwy klas (działań, usług itp.) Są poprawnie wyodrębniane.

Jednak nadal możesz znaleźć te brakujące informacje, uruchamiając narzędzie aapt w oryginalnym pliku aplikacji na Androida ( .apk ):

aapt l -a <someapp.apk>

Dzięki najnowszym narzędziom SDK możesz teraz użyć narzędzia zwanego apkanalyzer do wydrukowania pliku AndroidManifest.xml pliku APK (a także innych części, takich jak zasoby).

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

apkanalyzer

Sprawdź ten następujący projekt WPF, który poprawnie dekoduje właściwości.

apk-parser, https://github.com/caoqianli/apk-parser , lekki impl dla java, bez zależności od aapt lub innych plików binarnych, jest dobry do analizowania binarnych plików xml i innych informacji o 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();

Jeśli korzystasz z Pythona lub Androguard , funkcja Androguard Androaxml wykona tę konwersję za Ciebie. Ta funkcja jest szczegółowo opisana w tym poście na blogu , z dodatkową dokumentacją tutaj i źródłem tutaj .

Stosowanie:

$ ./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

Na wypadek, gdyby było to przydatne, oto wersja C ++ fragmentu kodu Java opublikowana przez 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);
    }
};

w celach informacyjnych tutaj jest moja wersja kodu Ribo. Główna różnica polega na tym, że decompressXML () bezpośrednio zwraca ciąg znaków, co dla moich celów było bardziej odpowiednim zastosowaniem.

UWAGA: moim jedynym celem korzystania z rozwiązania Ribo było pobranie opublikowanej wersji pliku .APK z pliku Manifest XML i potwierdzam, że w tym celu działa pięknie.

EDYCJA [2013-03-16]: Działa pięknie, JEŻELI wersja jest ustawiona jako zwykły tekst, ale jeśli jest ustawiona na odwołanie się do zasobu XML, pojawi się na przykład jako „Zasób 0x1”. W tym konkretnym przypadku prawdopodobnie będziesz musiał połączyć to rozwiązanie z innym rozwiązaniem, które pobierze odpowiednie odwołanie do zasobu ciągu.

/**
 * 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

Mam nadzieję, że pomoże to również innym ludziom.

W Android Studio 2.2 możesz bezpośrednio przeanalizować apk. Idź do kompilacji - przeanalizuj apk. Wybierz apk, przejdź do androidmanifest.xml. Możesz zobaczyć szczegóły manifestu androida.

Wersja @Mathieu Kotlin wygląda następująco:

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)

To jest wersja kotlin odpowiedzi powyżej.

Znalazłem AXMLPrinter2, aplikację Java w projekcie Android4Me, która działa dobrze na AndroidManifest.xml, który miałem (i drukuje XML w ładnie sformatowany sposób). http://code.google.com/p/android4me/downloads/detail?name=AXMLPrinter2.jar

Jedna uwaga ... to (i kod w tej odpowiedzi z Ribo) nie wydaje się obsługiwać każdego skompilowanego pliku XML, z którym się spotkałem. Znalazłem taki, w którym łańcuchy były przechowywane z jednym bajtem na znak, a nie w zakładanym formacie dwubajtowym.

to może być pomocne

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 to moja klasa aplikacji:

public class G extends Application {

Używam kodu Ribo zamieszczonego powyżej od ponad roku i dobrze nam służył. Jednak po ostatnich aktualizacjach (Gradle 3.x) nie byłem już w stanie przeanalizować pliku AndroidManifest.xml, otrzymywałem błędy indeksu poza zakresem i generalnie nie był już w stanie przeanalizować pliku.

Aktualizacja: teraz uważam, że nasze problemy dotyczyły aktualizacji do Gradle 3.x. W tym artykule opisano, w jaki sposób AirWatch miał problemy i można je naprawić za pomocą ustawienia Gradle do używania aapt zamiast aapt2 AirWatch wydaje się być niekompatybilny z wtyczką Android dla Gradle 3.0.0-beta1

Szukając w okolicy, natknąłem się na ten projekt open source i jest on utrzymywany i byłem w stanie przejść do rzeczy i przeczytać zarówno moje stare pliki APK, które mogłem wcześniej przeanalizować, jak i nowe pliki APK, które logika z Ribo rzuciła wyjątki

https://github.com/xgouchet/AXML

Z jego przykładu robię to

  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 będzie pomocny

@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%

oryginalny post https://stackoverflow.com/a/51905063/1383521