该文件似乎是二进制XML格式。这种格式是什么?如何以编程方式解析(与使用SDK中的aapt转储工具相反)?
这个二进制格式文档中没有讨论在这里。
注意:我想从Android环境之外(最好是从Java)访问此信息。
该文件似乎是二进制XML格式。这种格式是什么?如何以编程方式解析(与使用SDK中的aapt转储工具相反)?
这个二进制格式文档中没有讨论在这里。
注意:我想从Android环境之外(最好是从Java)访问此信息。
Answers:
有一个应用程序可以读取apk文件并将XML解码为几乎原始格式。
用法:
apktool d Gmail.apk && cat Gmail/AndroidManifest.xml
检查android-apktool以获得更多信息
apktool d Gmail.apk && cat Gmail/AndroidManifest.xml
minSdkVersion
和其他版本参数也可以在Gmail/apktool.yml
运行在Android上的Java方法记录了.apk包中AndroidManifest.xml文件的二进制格式(据我所能解释的内容)。第二个代码框显示了如何调用decompressXML以及如何从设备上的应用程序包文件加载byte []。(有些字段的用途我不明白,如果您知道它们的意思,请告诉我,我会更新信息。)
// 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
此方法将AndroidManifest读取到byte []中进行处理:
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
大多数应用程序都存储在/ system / app中,而无需读取我的Evo即可读取,其他应用程序则存储在/ data / app中,而我需要root才能查看。上面的'path'参数类似于:“ /system/app/Weather.apk”
将Android SDK中的Android资产打包工具(aapt)用于Python(或其他任何语言)脚本该怎么办?
实际上,通过aapt(http://elinux.org/Android_aapt),您可以检索有关.apk软件包及其AndroidManifest.xml文件的信息。特别是,您可以通过“转储”提取.apk包中各个元素的值子命令。例如,您可以通过以下方式将用户权限提取到.apk包内的AndroidManifest.xml文件中:
$ aapt dump permissions package.apk
其中package.apk是您的 .apk软件包。
此外,您可以使用Unix pipe命令清除输出。例如:
$ aapt dump permissions package.apk | sed 1d | awk '{ print $NF }'
这是一个以编程方式实现的Python脚本:
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
您可以类似的方式提取其他信息(例如,包,应用名称 AndroidManifest.xml的等):
#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 ""
相反,如果您想解析整个AndroidManifest XML树,则可以使用 xmltree命令操作:
aapt dump xmltree package.apk AndroidManifest.xml
像以前一样使用Python:
#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"))
您可以使用android-random项目中不久前开发的axml2xml.pl工具。它将从二进制文件生成文本清单文件(AndroidManifest.xml)。
我说的是“ 文本的 ”而不是“ 原始的 ”,因为像许多逆向工程工具一样,这种工具也不是完美的,结果也不会是完整的。我猜想它要么永远都没有完整的功能,要么根本就不兼容(使用更新的二进制编码方案)。不管是什么原因,axml2xml.pl工具都将无法正确提取所有属性值。这样的属性是minSdkVersion,targetSdkVersion以及基本上所有引用资源的属性(例如字符串,图标等),即,仅正确提取(活动,服务等的)类名。
但是,您仍然可以通过在原始Android应用文件(.apk)上运行aapt工具来找到这些丢失的信息:
aapt l -a <someapp.apk>
apk-parser,https://github.com/caoqianli/apk-parser,这是Java的轻量级impl,不依赖于aapt或其他二进制文件,非常适合解析二进制xml文件和其他apk信息。
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();
如果您使用Python或使用Androguard,则Androguard Androaxml功能将为您完成此转换。此博客文章中详细介绍了此功能,此处提供其他文档,并在此处提供源。
用法:
$ ./androaxml.py -h
Usage: androaxml.py [options]
Options:
-h, --help show this help message and exit
-i INPUT, --input=INPUT
filename input (APK or android's binary xml)
-o OUTPUT, --output=OUTPUT
filename output of the xml
-v, --version version of the API
$ ./androaxml.py -i yourfile.apk -o output.xml
$ ./androaxml.py -i AndroidManifest.xml -o output.xml
如果有用,这是Ribo发布的Java代码段的C ++版本:
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);
}
};
chars
由新的char []分配,然后释放,而不是正确的delete[] chars;
。在decompressXML ctor的末尾必须为prt(" end at offset "+toIntString(off));
,否则将使用指针算术...
供参考,这是我的Ribo代码版本。主要区别在于decompressXML()直接返回一个String,对我而言,这是一种更合适的用法。
注意:使用Ribo解决方案的唯一目的是从清单XML文件中获取.APK文件的发布版本,并且我确认为此目的,它可以正常工作。
编辑[2013-03-16]:如果将版本设置为纯文本,则可以很好地工作,但是如果设置为引用资源XML,则它将显示为“资源0x1”。在这种特殊情况下,您可能必须将此解决方案与另一个将获取正确的字符串资源引用的解决方案耦合。
/**
* 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
希望它也可以帮助其他人。
在Android Studio 2.2中,您可以直接分析apk。转到构建-分析apk。选择apk,导航至androidmanifest.xml。您可以查看androidmanifest的详细信息。
@Mathieu Kotlin版本如下:
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)
这是上面答案的kotlin版本。
我在Android4Me项目中找到了Java应用程序AXMLPrinter2,可以在我拥有的AndroidManifest.xml上正常工作(并以一种格式正确的方式打印出XML)。 http://code.google.com/p/android4me/downloads/detail?name=AXMLPrinter2.jar
需要注意的是它(以及Ribo上有关此答案的代码)似乎无法处理我遇到的每个已编译XML文件。我发现一个存储字符串的地方是每个字符一个字节,而不是假定的双字节格式。
这可能会有所帮助
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是我的应用程序类:
public class G extends Application {
我使用上面发布的Ribo代码已经运行了一年多,它为我们提供了很好的服务。但是,在最近的更新(Gradle 3.x)中,我不再能够解析AndroidManifest.xml,我无法获取索引错误,并且通常它也无法解析该文件。
更新:我现在认为我们的问题是升级到Gradle3.x。本文介绍了AirWatch如何出现问题,可以通过使用Gradle设置使用aapt而不是aapt2来解决。AirWatch 似乎与Gradle 3.0.0-beta1的Android插件不兼容
在搜索过程中,我遇到了一个开源项目,它得到了维护,并且能够直截了当地阅读我以前可以解析的旧APK,以及Ribo逻辑抛出异常的新APK。
https://github.com/xgouchet/AXML
从他的例子来看,这就是我在做什么
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将有帮助
@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%
android.content.pm.PackageManager.queryXX
方法查询(docs:developer.android.com/reference/android/content/pm/…)。