def trimFile_btwn(sFile, string_srt, string_end):
sNAMEFUNC = 'trimFile_btwn'
sTxt = "Called... "
sndMSG(sTxt, 'INFO', sNAMEFUNC)
iCnt = 0
iSrt = 0
iEnd = 0
with open(sFile, 'r+') as data:
lines = data.readlines()
data.seek(0)
for line in lines:
if string_srt in line:
iSrt = iCnt
if string_end in line:
iEnd = iCnt
iCnt += 1
data.truncate()
for i in range(iSrt, iEnd + 1):
data.write(lines[i])
lines = None
data.close()
return (False)
def decompress(self, srcFile, dstFile, cmpType):
if not cmpType in self.CompressionTypes:
sTxt = 'Unknown decompress type: ' + cmpType
sndMSG(sTxt, 'ERROR', self._strClassName)
return (None)
if cmpType == 'gz':
sTxt = 'Attempting to decompress ' + cmpType + ' file '
sndMSG(sTxt, 'INFO', self._strClassName)
return (True)
if cmpType == 'zip':
sTxt = 'Attempting to decompress ' + cmpType + ' file '
sndMSG(sTxt, 'INFO', self._strClassName)
return (True)
if cmpType == 'bz':
sTxt = 'Attempting to decompress ' + cmpType + ' file '
sndMSG(sTxt, 'INFO', self._strClassName)
return (True)
if cmpType == 'tar':
sTxt = 'Attempting to decompress ' + cmpType + ' file '
sndMSG(sTxt, 'INFO', self._strClassName)
return (True)
return (False)
def getFile_CSV2List(sFile, dialect=None, sCommentFlag=None):
"""
Opens received File and parses it based on the received dialect
Keyword arguments:
sFile -- File Path and File name to be parsed
exmple: ./test/test.csv
dialect -- Is an instantiates of mngLoc_File.clsCSVDialect
containing the CSV parsing parameters
sCommentChar -- Is char that begins a line to be ingnored
Returns:
List object containing a List for each line
example:
[['date','ip1','domain1'],
['date','ip2','domain2']
]
"""
import csv
sFuncName = 'mngFiles.getFile_CSV2List'
sTxt = "Attemping to parse file as CSV: " + sFile
sndMSG(sTxt, 'INFO', sFuncName)
if dialect == None:
sTxt = "\--> NOTE: No csv dialect was passed, default parsing is by comma "
sndMSG(sTxt, 'INFO', sFuncName)
if sCommentFlag == None:
sCommentFlag = '#'
sTxt = "\--> NOTE: No comment flag was passed, default is '#' "
sndMSG(sTxt, 'INFO', sFuncName)
try:
#objFile = _getFile_OBJ(sFile)
objFile = open(sFile)
if objFile == None:
return (None)
data = csv.reader(objFile, dialect)
sList = []
for line in data:
if sCommentFlag in str(line):
# TODO: Needs better comment handling,
# As is it will remove line in line comments
# this need to be fixed to just remove commented section
# and still keep the data before it
continue
sList.append(line)
#sList.sort()
objFile.close
return (sList)
except IOError as e:
sTxt = str("\--> I/O error({0}): {1}".format(e.errno, e.strerror))
sndMSG(sTxt, 'ERROR', sFuncName)
return (None)
except:
sTxt = "\--> Unexpected error: " + str(sys.exc_info()[0])
sndMSG(sTxt, 'ERROR', sFuncName)
return (None)
def sndFile(sData, sFile):
import sys
sFuncName = 'mngFiles.sndFile'
sTxt = "Trying to write to this file : " + sFile
sndMSG(sTxt, 'INFO', sFuncName)
with open(sFile, "w") as outfile:
for line in sData:
outfile.write(line)
outfile.close()
return (0)
def decompressor(srcFile, dstFile, cmpFormat):
_strFuncName = 'mngFiles.decompressor'
_strFuncVer = '0.0.0'
if srcFile == None or dstFile == None or cmpFormat == None:
return (None)
if srcFile:
sTxt = 'decompressing ' + srcFile
sndMSG(sTxt, 'INFO', _strFuncName)
return (True)
return (None)
def unpck_file2file(self):
if self._dicParsingArgs['format'][0] in self._lstCompressionTypes:
sTxt = 'Attempting to decompression format: ' + self._dicParsingArgs['format'][0]
sndMSG(sTxt,'INFO',self._strClassName)
### Run decompressor
from mngFiles import decompressor
from mngFiles import Decompressor
sFile = self._strFilePath + self.fileName + "."
srcFile = sFile + self._dicParsingArgs['format'][0]
dstFile = sFile + self._dicParsingArgs['format'][1]
cmpFrmt = self._dicParsingArgs['format'][0]
oDcmp = Decompressor()
bStatus = oDcmp.decompress(srcFile,dstFile,cmpFrmt)
if bStatus == True:
self._dicParsingArgs['format'].pop(0)
elif bStatus == False:
sTxt = 'Failed to unpack ' + self._lstFileEncapFormats(0) + ' file '
sndMSG(sTxt,'ERROR',self._strClassName)
else:
sTxt = 'Unpacker returned unexpected result'
sndMSG(sTxt,'ERROR',self._strClassName)
### This causes a loop to interater through self._lstFileEncapFormats
self.cnvt_SrcFile2Dict()
else:
sTxt = 'Unrecognized file compression format: ' + self._lstFileEncapFormats(0)
sndMSG(sTxt,'ERROR',self._strClassName)
return(None)
def getUTCTime():
'''
- Used to get UTC in a standardized format
Keyword arguments:
Returns:
'''
from datetime import datetime
sFuncName = 'getUTCTime()'
try:
sDateTime = datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ")
return (sDateTime)
except:
sTxt = "Unexpected error: " + str(sys.exc_info()[0])
sndMSG(sTxt, 'ERROR', sFuncName)
return (None)
def cnvt_XML2Dict(srcXML, dstFile=None):
'''
{Description}
Keyword arguments:
Returns:
'''
import urllib2
import xmltodict
### Setup function
sFuncName = 'cnvt_XML2Dict'
if not srcXML:
sTxt = 'XML Source Required'
return (None)
if not "http" in srcXML:
srcXML = "file://" + srcXML
#rssData = urllib2.urlopen(srcXML).read()
try:
rssData = urllib2.urlopen(srcXML).read()
except IOError as e:
sTxt = str("\--> I/O error({0}): {1}".format(e.errno, e.strerror))
sndMSG(sTxt, 'ERROR', sFuncName)
return (None)
except:
sTxt = "\--> Unexpected error: " + str(sys.exc_info()[0])
sndMSG(sTxt, 'ERROR', sFuncName)
return (None)
#dataDict = xmltodict.parse(rssData)
try:
dataDict = xmltodict.parse(rssData)
pass
except IOError as e:
sTxt = str("\--> I/O error({0}): {1}".format(e.errno, e.strerror))
sndMSG(sTxt, 'ERROR', sFuncName)
return (None)
except:
sTxt = "\--> Unexpected error: " + str(sys.exc_info()[0])
sndMSG(sTxt, 'ERROR', sFuncName)
return (None)
if dstFile:
return (sndFile_Dict2JSON(dataDict, dstFile))
else:
return (dataDict)
return (None)
def getFile_JSON2Dict(sFile):
'''
{Description}
Keyword arguments:
Returns:
'''
import json
sFuncName = 'mngFiles.getFile_JSON2Dict'
sTxt = "Attemping to parse file as JSON: " + sFile
sndMSG(sTxt, 'INFO', sFuncName)
try:
#json_data = _getFile_OBJ(sFile)
json_data = open(sFile)
if json_data == None:
return (None)
data = json.load(json_data)
json_data.close()
return (data)
except IOError as e:
sTxt = str("\--> I/O error({0}): {1}".format(e.errno, e.strerror))
sndMSG(sTxt, 'ERROR', sFuncName)
return (None)
except:
sTxt = "\--> Unexpected error: " + str(sys.exc_info()[0])
sndMSG(sTxt, 'ERROR', sFuncName)
return (None)
def getRmt_File(dicCreds,sFile):
'''
- Simple URL Retrieval function based on python's urllib
Keyword arguments:
Returns:
'''
import urllib
sFuncName = 'getRmt_File'
rmtSrcFile = dicCreds['URI']
sTxt = "Connecting to " + rmtSrcFile
sndMSG(sTxt,'INFO',sFuncName)
try:
urllib.urlretrieve(rmtSrcFile,sFile)
return(True)
except:
sTxt = "Unexpected error: " + str(sys.exc_info()[0])
sndMSG(sTxt,'ERROR',sFuncName)
return(False)
return False
def cnvt_SrcFile2Dict(self):
if self._dicParsingArgs['format'][0] in self._lstCompressionTypes:
self.unpck_file2file()
if self._dicParsingArgs['format'][0] in self._lstFileFormatTypes:
sFrmt = self._dicParsingArgs['format'][0]
sFileSuffix = self._strFilePath + self._strFileNameSuffix
if sFrmt == 'txt' or sFrmt == 'csv':
from cnvtFiles import cnvt_CSV2Dict
from mngFiles import clsCSVDialect_01
oDialect = clsCSVDialect_01()
oDialect.from_dict(self._dicParsingArgs)
sFile = self.fileName + "." + sFrmt
return(cnvt_CSV2Dict(sFile,oDialect,strEncoding=self._strUnicodeEncoding))
elif sFrmt == 'xml' or sFrmt == 'rss':
from mngFiles import cnvt_XML2Dict
return(cnvt_XML2Dict(sFileSuffix + sFrmt))
elif sFrmt == 'htm' or sFrmt == 'html':
from mngFiles import cnvt_HTML2Dict
sArg = self._dicParseArg["format"]["htmFltr"]
return(cnvt_HTML2Dict(sFileSuffix + sFrmt,sArg))
else:
sTxt = "Format not recognized: " + sFrmt
sndMSG(sTxt,'ERROR',self._strClassName)
else:
sTxt = 'Unrecognized file compression format: ' + self._dicParsingArgs['format'][0]
sndMSG(sTxt,'ERROR',self._strClassName)
return(None)
def sndFile_Dict2JSON(sData, sFile, isCompact=False):
'''
{Description}
Keyword arguments:
Returns:
'''
import json
sFuncName = 'mngFiles.sndFile_Dict2JSON'
sTxt = "Trying to write to this file : " + sFile
sndMSG(sTxt, 'INFO', sFuncName)
chkFile(sFile, True)
try:
with open(sFile, "w") as outfile:
try:
if isCompact == 'True':
json.dump(sData, outfile)
else:
json.dump(sData, outfile, indent=4)
except:
sTxt = "Unexpected error: " + str(sys.exc_info()[0])
sndMSG(sTxt, 'ERROR', sFuncName)
return (False)
outfile.close()
return (True)
except IOError as e:
sTxt = str("I/O error({0}): {1}".format(e.errno, e.strerror))
sndMSG(sTxt, 'ERROR', sFuncName)
return (None)
except:
sTxt = "Unexpected error: " + str(sys.exc_info()[0])
sndMSG(sTxt, 'ERROR', sFuncName)
return (None)
def getRmt_File2(dicCreds,sFile):
'''
- Simple URL Retreval funtion based on python's urllib2
- With chunking and download update
Keyword arguments:
Returns:
'''
import urllib2
sFuncName = 'getRmtFile2'
rmtFile = dicCreds['URI']
#"Mozilla/5.0 (X11 U Linux i686) Gecko/20071127 Firefox/2.0.0.11"
try:
### Add Proxy
# SOURCE: https://docs.python.org/2.4/lib/urllib2-examples.html
# proxy_handler = urllib2.ProxyHandler({'http': 'http://www.example.com:3128/'})
# proxy_auth_handler = urllib2.HTTPBasicAuthHandler()
# proxy_auth_handler.add_password('realm', 'host', 'username', 'password')
#
# opener = build_opener(proxy_handler, proxy_auth_handler)
# This time, rather than install the OpenerDirector, we use it directly:
# opener.open('http://www.example.com/login.html'
#
# ## Mixed HTTPS HTTP enviroment
# urllib2.ProxyHandler({'https': 'http://*****:*****@proxy:3128' }))
###
### Basic HTTP Authentication
# SOURCE: https://docs.python.org/2.4/lib/urllib2-examples.html
# ##Create an OpenerDirector with support for Basic HTTP Authentication...
# auth_handler = urllib2.HTTPBasicAuthHandler()
# auth_handler.add_password('realm', 'host', 'username', 'password')
# opener = urllib2.build_opener(auth_handler)
# ##...and install it globally so it can be used with urlopen.
# urllib2.install_opener(opener)
# urllib2.urlopen('http://www.example.com/login.html')
###
### Cookie Handler
# jar = cookielib.FileCookieJar("cookies")
# opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(jar))
###
### Modifiy User Agent
# opener = urllib2.build_opener()
# opener.addheaders = [('User-agent', 'Mozilla/5.0')]
# opener.open('http://www.example.com/')
###
objURL = urllib2.urlopen(rmtFile)
except:
sTxt = "Unexpected error: " + str(sys.exc_info()[0])
sndMSG(sTxt,'ERROR',sFuncName)
return(False)
objFile = open(sFile, 'wb')
meta = objURL.info()
file_size = int(meta.getheaders("Content-Length")[0])
sTxt = "Downloading: %s Bytes: %s" % (sFile, file_size)
sndMSG(sTxt,'INFO',sFuncName)
file_size_dl = 0
block_sz = 8192
while True:
buffer = objURL.read(block_sz)
if not buffer:
break
file_size_dl += len(buffer)
objFile.write(buffer)
status = r"%10d [%3.2f%%]" % (file_size_dl, file_size_dl * 100. / file_size)
status = status + chr(8)*(len(status)+1)
sndMSG(status,'INFO',sFuncName)
objFile.close()
return(True)
def cnvt_CSV2Dict(srcCSV, dialect=None, sCommentFlag=None, strEncoding=None):
_sFuncName = 'cnvtFiles.cnvt_CSV2Dict'
sTxt = "Called... "
sndMSG(sTxt, 'INFO', _sFuncName)
bDebug = False
if srcCSV == None or dialect == None:
return (None)
if sCommentFlag == None:
sCommentFlag = '#'
if strEncoding == None:
strEncoding = 'utf-8'
if dialect.header == True:
#TODO: Change Col header from number to Header Names
pass
if bDebug:
sTxt = "\--[ CSV File Location ]--> " + str(srcCSV)
sndMSG(sTxt, 'INFO', _sFuncName)
with open(srcCSV, 'rb') as dataSrc:
if dataSrc == None:
return (None)
if bDebug:
sTxt = "\--[ input File charCnt ]--> " + str(len(dataSrc.read()))
sndMSG(sTxt, 'INFO', _sFuncName)
dataSrc.seek(0)
data = csv.reader(dataSrc, dialect=dialect)
if bDebug:
sTxt = "\--[ output CSV RowCnt ]--> " + str(data)
sndMSG(sTxt, 'INFO', _sFuncName)
csvDict = {}
listHeaders = []
iRow = 0
iCol = 0
for row in data:
if len(row) < 1:
continue
if sCommentFlag in str(row[0]):
continue
if dialect.header == True and len(listHeaders) < 1:
listHeaders = row
continue
csvDict.update({iRow: {}})
for col in row:
try:
col = unicode(col, strEncoding)
except:
col = " (NOTE: This data was modified from origin, due to non " + strEncoding + " compatiable chars) " + unicode(
col, "utf-8", errors='ignore')
if len(listHeaders) > 1:
csvDict[iRow].update({listHeaders[iCol]: col})
else:
csvDict[iRow].update({iCol: col})
iCol += 1
iCol = 0
iRow += 1
if bDebug:
sTxt = "\--[ output Dict RowCnt ]--> " + str(len(csvDict))
sndMSG(sTxt, 'INFO', _sFuncName)
dataSrc.close
return (csvDict)
def _getFile_OBJ(sFile,
MAXFILESIZE=None,
FILEENCODING=None,
sPassFuncName=None):
"""
Code Broken, do not use
"""
#if sPAssFuncName == None:
# sFuncName = 'mngFiles._getFile_OBJ'
#else:
# sFuncName = sPAssFuncName + "(" + sFuncName + ")"
sFuncName = 'mngFiles._getFile_OBJ'
sTxt = "Attemping to open this file: " + sFile
sndMSG(sTxt, 'INFO', sFuncName)
if MAXFILESIZE == None:
MAXFILESIZE = 1000000000 # => 1GB
else:
sTxt = "\--> MAXFILESIZE was changed to: " + MAXFILESIZE
sndMSG(sTxt, 'INFO', sFuncName)
if FILEENCODING == None:
FILEENCODING = 'utf-8'
else:
sTxt = "\--> FILEENCODING was changed to: " + FILEENCODING
sndMSG(sTxt, 'INFO', sFuncName)
#check Existance of file
bFlag = os.path.exists(sFile)
if bFlag == False:
sTxt = "\--> This file or file path does not exist: " + sFile
sndMSG(sTxt, 'ERROR', sFuncName)
return (None)
#check File size
#iSize = os.path.getsize(sFile)
#if iSize > MAXFILESIZE:
#sTxt = "\--> This file is larger than MAXFILESIZE: " + sFile
#sndMSG(sTxt,'ERROR',sFuncName)
#return(None)
try:
with open(sFile) as data:
oFile = data.read()
data.close()
except IOError as e:
sTxt = str("\--> I/O error({0}): {1}".format(e.errno, e.strerror))
sndMSG(sTxt, 'ERROR', sFuncName)
return (None)
except:
sTxt = "\--> Unexpected error: " + str(sys.exc_info()[0])
sndMSG(sTxt, 'ERROR', sFuncName)
return (None)
sTxt = "\--> File was successfully Opened"
sndMSG(sTxt, 'INFO', sFuncName)
return (oFile)
