一文搞懂：【Python】torrentParser1.01

在昨天的版本上做了一些改进，如增加getAll，修改getSingleFileName等

代码：

#------------------------------------------------------------------------------------

# torrentParser1.01，用于解析torrent文件

# 2018年5月9日

#------------------------------------------------------------------------------------

from bencode import bdecode

import time

#-------------------------------------

# torrentParser类

#-------------------------------------

class torrentParser(object):

# 构造函数

def init(self,filePathname):

self.filePathname=filePathname

with open(filePathname,'rb') as fObj:

self.fileDic=bdecode(fObj.read())

# 得到所有键值

def getKeys(self):

return self.fileDic.keys()

# 得到全部内容

def getAll(self):

return self.fileDic;

# 获得tracker服务器的URL

def getAnnounce(self):

if 'announce' in self.fileDic:

return self.fileDic【'announce'】.decode('utf-8')

return ''

# 获得tracker服务器的URL列表

def getAnnounceList(self):

retval=【】

if 'announce-list' in self.fileDic:

arr=self.fileDic【'announce-list'】

for childArr in arr:

if type(childArr)==type(【】):

for item in childArr:

retval.append(item.decode('utf-8'))

else:

retval.append(childArr.decode('utf-8'))

return retval

# 得到制作日期

def getCreateTime(self):

if 'creation date' in self.fileDic:

unixTimestamp=self.fileDic【'creation date'】

firmalTime = time.localtime(unixTimestamp)

dt = time.strftime('%Y-%m-%d %H:%M:%S', firmalTime)

return dt

else:

return ''

# 获得编码方式

def getEncoding(self):

if 'encoding' in self.fileDic:

return self.fileDic【'encoding'】.decode('utf-8') #去掉字符串前面的b'

return ''

# 是否包含多个文件

def hasMultiFiles(self):

if 'files' in self.fileDic【'info'】:

return True

else:

return False

# 获得文件名

def getTitle(self):

arr=【】

info = self.fileDic【'info'】

if 'name.utf-8' in info:

arr=info【'name.utf-8'】

else:

arr = info【'name'】

#print(str(arr))

return arr.decode('utf-8') # \x 开头编码的数据解码成中文

# 获得备注(可选项)

def getComment(self):

if 'comment' in self.fileDic:

return self.fileDic【'comment'】.decode('utf-8')

return ''

# 获得创建者(可选项)

def getCreatedBy(self):

if 'created by' in self.fileDic:

return self.fileDic【'created by'】.decode('utf-8')

return ''

# 多文件的情况下，得到多个文件的个数

def getFileCount(self):

return len(self.fileDic【'info'】【'files'】)

# 多文件的情况下，获得所有文件，返回为:dic

def getFiles(self):

files=【】

for item in self.fileDic【'info'】【'files'】:

file={}

for key in item.keys():

value=item.get(key)

if key=='path':

path=value【0】.decode()

value=path

if key=='path.utf-8':

path=value【0】.decode()

value=path

file【key】=value

files.append(file)

return files

# 单文件情况下，取文件名

def getSingleFileName(self):

#print(str(self.fileDic【'info'】【'name'】))

#return str(self.fileDic【'info'】【'name'】,'utf-8')

return self.getTitle();

# 单文件情况下，取文件长度

def getSingleFileLength(self):

return self.fileDic【'info'】【'length'】

# 单文件情况下，取文件md5sum

def getSingleFileMd5sum(self):

if 'md5sum' in self.fileDic【'info'】:

return str(self.fileDic【'info'】【'md5sum'】,'utf-8')

else:

return ''

# 单文件情况下，取文件长度

def getSingleFilePieceLength(self):

return self.fileDic【'info'】【'piece length'】

# 单文件情况下，取文件pieces

def getSingleFilePieces(self):

return self.fileDic【'info'】【'pieces'】

# 得到文件简报

def getBrief(self):

retval=""

retval=retval+"File:"+self.filePathname+"\n"

retval=retval+"announce:"+self.getAnnounce()+"\n"

arr=self.getAnnounceList()

if(len(arr)>0):

retval=retval+"announce list:"+"\n"

for it in arr:

retval=retval+"\t"+it+"\n"

retval=retval+"Create time:"+self.getCreateTime()+"\n"

retval=retval+"Ecoding:"+self.getEncoding()+"\n"

retval=retval+"Title:"+self.getTitle()+"\n"

retval=retval+"Comment:"+self.getComment()+"\n"

retval=retval+"Created by:"+self.getCreatedBy()+"\n"

hasMulti=self.hasMultiFiles()

retval=retval+"has multi files:"+str(hasMulti)+"\n"

if hasMulti==True:

retval=retval+"【多文件结构】"+"\n"

retval=retval+"包含文件个数为:"+str(self.getFileCount())+"\n"

//代码效果参考：http://hnjlyzjd.com/xl/wz_25474.html

files=self.getFiles();

index=1

for item in files:

retval=retval+"\tfile#"+str(index)+"\n"

for key in item.keys():

value=item.get(key)

retval=retval+"\t\t"+str(key)+":"+str(value)+"\n"

retval=retval+"\n"

index=index+1

else:

retval=retval+"【单文件结构】"+"\n"

retval=retval+"文件名为:"+self.getSingleFileName()+"\n"

retval=retval+"文件长度:"+str(self.getSingleFileLength())+"byte\n"

retval=retval+"文件md5sum:"+self.getSingleFileMd5sum()+"\n"

retval=retval+"文件块长度:"+str(self.getSingleFilePieceLength())+"byte\n"

return retval

#-------------------------------------

# 入口

#-------------------------------------

def main():

tp=torrentParser(filePathname='./5.torrent')

#print(tp.getBrief());

print(str(tp.getAll()));

# Start

main()

对只包含一个文件的torrent文件分析情况：

C:\Users\horn1\Desktop\python\40-torrentParser>python torrentParser.py

File:./5.torrent

announce:

announce list: