Python: Current directory in an os.walk
I need to get the current directory in an os.walk process. It works when there is just one subdirectory level but fails when there's more. Please advise...
[CODE]
# AFFECTS everything reachable from the directory named in "top",
# assuming there are no symbolic links.
# CAUTION: This is dangerous! For example, if top == '/', it
# could affect all your disk files.
import os, glob, arcpy, csv, sys, shutil, datetime
top = r'L:\Raster_Data\Topographic_Maps'
RootOutput = r'L:\Raster_Data\Topographic_Maps'
#FileList = csv.reader(open('FileList.csv'))
SearchString=['Temp_Pol', 'Spatial_Ex']
filecount=0
successcount=0
errorcount=0
print "Working in: "+os.getcwd()
list =[]
f = open(RootOutput+'\\Success_LOG.txt', 'a')
f.write("Log of files Succesfully processed. RESULT of process run @:"+str(datetime.datetime.now())+"\n")
f.close()
#for File in FileList:
for root, dirs, files in os.walk(top, topdown=False):
#for directory in dirs:
for file in files:
#currentPath=os.path.join(root,directory)
currentPath=os.path.abspath(file)
os.chdir(currentPath)
#arcpy.env.workspace = currentPath
#print os.getcwd()
lstFCs = glob.glob('*'+SearchString[0]+'*.shp')
#print lstFCs
OutPutDir=os.path.abspath(currentPath)
for fc in lstFCs:
filecount=filecount+1
list.append(OutPutDir+"\\"+fc)
lstFCs = glob.glob('*'+SearchString[1]+'*.shp')
#print lstFCs
for fc in lstFCs:
OutPutDir=RootOutput+"\\"+directory
filecount=filecount+1
list.append(OutPutDir+"\\"+fc)
print 'Merging: ' + str(list)
#arcpy.Merge_management(list, RootOutput+"\\Full_Extent.shp")
print 'Created: '+RootOutput+"\\Full_Extent.shp"
f = open(RootOutput+'\\Success_LOG.txt', 'a')
f.write(str(list)+"\n\n Merged to: "+RootOutput+"\\Full_Extent.shp")
f.close()
so the list should be appended with the fc and the full path to it but just gets the root path and the final part of the path -not the directories in between.
Thanks for your advise,
[Error Messages]
Working in: L:\Raster_Data\Topographic_Maps Merging: ['L:\Raster_Data\Topographic_Maps\100K\2010_100K\Map_Sheets_BestResolution\qld_north\SE55\ecw\prj_Temp_Polygon_Extent_0.shp', 'L:\Raster_Data\Topographic_Maps\100K\2010_100K\Map_Sheets_BestResolution\qld_north\SE55\ecw\Temp_Polygon_Extent_0.shp', 'L:\Raster_Data\Topographic_Maps\ecw\Spatial_Extent.shp', 'L:\Raster_Data\Topographic_Maps\SC54\Spatial_Extent.shp', 'L:\Raster_Data\Topographic_Maps\SC55\Spatial_Extent.shp', 'L:\Raster_Data\Topographic_Maps\SD54\Spatial_Extent.shp', 'L:\Raster_Data\Topographic_Maps\SD55\Spatial_Extent.shp', 'L:\Raster_Data\Topographic_Maps\SE54\Spatial_Extent.shp', 'L:\Raster_Data\Topographic_Maps\100K\2010_100K\Map_Sheets_BestResolution\qld_north\SE55\prj_Temp_Polygon_Extent_0.shp', 'L:\Raster_Data\Topographic_Maps\100K\201开发者_C百科0_100K\Map_Sheets_BestResolution\qld_north\SE55\Temp_Polygon_Extent_0.shp', 'L:\Raster_Data\Topographic_Maps\SE55\Spatial_Extent.shp', 'L:\Raster_Data\Topographic_Maps\SF54\Spatial_Extent.shp', 'L:\Raster_Data\Topographic_Maps\SF55\Spatial_Extent.shp', 'L:\Raster_Data\Topographic_Maps\SF56\Spatial_Extent.shp', 'L:\Raster_Data\Topographic_Maps\SG55\Spatial_Extent.shp', 'L:\Raster_Data\Topographic_Maps\SG56\Spatial_Extent.shp', 'L:\Raster_Data\Topographic_Maps\SH56\Spatial_Extent.shp', 'L:\Raster_Data\Topographic_Maps\Tablelands_100K\Spatial_Extent.shp', 'L:\Raster_Data\Topographic_Maps\200DPI\Spatial_Extent.shp', 'L:\Raster_Data\Topographic_Maps\1M\prj_Temp_Polygon_Extent_0.shp', 'L:\Raster_Data\Topographic_Maps\1M\Temp_Polygon_Extent_0.shp', 'L:\Raster_Data\Topographic_Maps\250K\prj_Temp_Polygon_Extent_1.shp', 'L:\Raster_Data\Topographic_Maps\250K\Temp_Polygon_Extent_1.shp', 'L:\Raster_Data\Topographic_Maps\250K\Spatial_Extent.shp', 'L:\Raster_Data\Topographic_Maps\5M\prj_Temp_Polygon_Extent_2.shp', 'L:\Raster_Data\Topographic_Maps\5M\Temp_Polygon_Extent_2.shp', 'L:\Raster_Data\Topographic_Maps\5M\Spatial_Extent.shp'] Traceback (most recent call last): File "L:\Raster_Data\Topographic_Maps\CreateFileList.py", line 64, in arcpy.Merge_management(list, RootOutput+"\Full_Extent.shp")
File "C:\Program Files\ArcGIS\Desktop10.0\arcpy\arcpy\management.py", line 3124, in Merge raise e ExecuteError: Failed to execute. Parameters are not valid. ERROR 000732: Input Datasets: Dataset L:\Raster_Data\Topographic_Maps\100K\2010_100K\Map_Sheets_BestResolution\qld_north\SE55\ecw\prj_Temp_Polygon_Extent_0.shp;L:\Raster_Data\Topographic_Maps\100K\2010_100K\Map_Sheets_BestResolution\qld_north\SE55\ecw\Temp_Polygon_Extent_0.shp;L:\Raster_Data\Topographic_Maps\ecw\Spatial_Extent.shp;L:\Raster_Data\Topographic_Maps\SC54\Spatial_Extent.shp;L:\Raster_Data\Topographic_Maps\SC55\Spatial_Extent.shp;L:\Raster_Data\Topographic_Maps\SD54\Spatial_Extent.shp;L:\Raster_Data\Topographic_Maps\SD55\Spatial_Extent.shp;L:\Raster_Data\Topographic_Maps\SE54\Spatial_Extent.shp;L:\Raster_Data\Topographic_Maps\100K\2010_100K\Map_Sheets_BestResolution\qld_north\SE55\prj_Temp_Polygon_Extent_0.shp;L:\Raster_Data\Topographic_Maps\100K\2010_100K\Map_Sheets_BestResolution\qld_north\SE55\Temp_Polygon_Extent_0.shp;L:\Raster_Data\Topographic_Maps\SE55\Spatial_Extent.shp;L:\Raster_Data\Topographic_Maps\SF54\Spatial_Extent.shp;L:\Raster_Data\Topographic_Maps\SF55\Spatial_Extent.shp;L:\Raster_Data\Topographic_Maps\SF56\Spatial_Extent.shp;L:\Raster_Data\Topographic_Maps\SG55\Spatial_Extent.shp;L:\Raster_Data\Topographic_Maps\SG56\Spatial_Extent.shp;L:\Raster_Data\Topographic_Maps\SH56\Spatial_Extent.shp;L:\Raster_Data\Topographic_Maps\Tablelands_100K\Spatial_Extent.shp;L:\Raster_Data\Topographic_Maps\200DPI\Spatial_Extent.shp;L:\Raster_Data\Topographic_Maps\1M\prj_Temp_Polygon_Extent_0.shp;L:\Raster_Data\Topographic_Maps\1M\Temp_Polygon_Extent_0.shp;L:\Raster_Data\Topographic_Maps\250K\prj_Temp_Polygon_Extent_1.shp;L:\Raster_Data\Topographic_Maps\250K\Temp_Polygon_Extent_1.shp;L:\Raster_Data\Topographic_Maps\250K\Spatial_Extent.shp;L:\Raster_Data\Topographic_Maps\5M\prj_Temp_Polygon_Extent_2.shp;L:\Raster_Data\Topographic_Maps\5M\Temp_Polygon_Extent_2.shp;L:\Raster_Data\Topographic_Maps\5M\Spatial_Extent.shp does not exist or is not supported Failed to execute (Merge).Working in: L:\Raster_Data\Topographic_Maps Traceback (most recent call last): File "L:\Raster_Data\Topographic_Maps\CreateFileList.py", line 28, in os.chdir(currentPath) WindowsError: [Error 2] The system cannot find the file specified: 'L:\Raster_Data\Topographic_Maps\ecw\SC54' directory 'SC54' dirs ['SC54', 'SC55', 'SD54', 'SD55', 'SE54', 'SE55'] os.path.abspath(dirs[0]) 'L:\Raster_Data\Topographic_Maps\ecw\SC54' os.getcwd() 'L:\Raster_Data\Topographic_Maps\ecw' Working in: L:\Raster_Data\Topographic_Maps Traceback (most recent call last): File "L:\Raster_Data\Topographic_Maps\CreateFileList.py", line 28, in os.chdir(currentPath) WindowsError: [Error 2] The system cannot find the file specified: 'L:\Raster_Data\Topographic_Maps\7178cp_dd.ers' file '7178cp_dd.ers' os.path.abspath os.path.abspath(file) 'L:\Raster_Data\Topographic_Maps\7178cp_dd.ers'
Thanks all, I used the input from the forum to complete the script. It's below for anyone who wants it. best,
# AFFECTS everything reachable from the directory named in "top",
# assuming there are no symbolic links.
# CAUTION: This is dangerous! For example, if top == '/', it
# could affect all your disk files.
import os, arcpy, sys, datetime
top = os.getcwd()
RootOutput = top
FileTypes=['shp']
SearchStrings=['Temp_Pol', 'Spatial_Ex']
filecount=0
#successcount=0
#errorcount=0
print "Working in: "+os.getcwd()
list =[]
f = open(RootOutput+'\\Success_LOG.txt', 'a')
f.write("Log of files Succesfully processed. RESULT of process run @:"+str(datetime.datetime.now())+"\n")
f.close()
for root, dirs, files in os.walk(top, topdown=False):
for fl in files:
currentFile=os.path.join(root, fl)
for FileType in FileTypes:
status= str.endswith(currentFile,FileType)
if str(status) == 'True':
for SearchString in SearchStrings:
if str(SearchString in currentFile) == 'True':
#print str(currentFile)+str(status)
filecount=filecount+1
list.append(currentFile)
print 'Merging: ' + str(list)
#Replace with any function you want to carry out on the generated list of files. #arcpy.Merge_management(list, RootOutput+"\Full_Extent.shp")
print 'Created: '+RootOutput+"\\Full_Extent.shp"
f = open(RootOutput+'\\Success_LOG.txt', 'a')
f.write(str(list)+"\n\n Merged to: "+RootOutput+"\\Full_Extent.shp")
f.close()
You should use
os.path.join(root, file)
instead of simply using file like suggested in the os.walk doc examples os.walk
Btw, be careful with the reserved keywords. file is a built-in function and list too
>>> a = list()
>>> a
[]
>>> list = []
>>> b = list()
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
TypeError: 'list' object is not callable
For some applications we always need to change the current working directory while we are in os.walk recursive call, in that case I would suggest changing the current working directory twice as shown below. I am writing about situations where having absolute file paths will not help .
from os import listdir
from os.path import isfile, join
import os
import re
# store the location of the top most directory
top = os.getcwd()
for (dirname, dirs, files) in os.walk(os.getcwd()):
for filename in files:
os.chdir(dirname)
# add all your operations for the current job in the directory
# Now go back to the top of the chain
os.chdir(top)
It looks like you're after a recursive glob. Something like the code below might be of use:
class rglob:
'''A recursive/regex enhanced glob
adapted from os-path-walk-example-3.py - http://effbot.org/librarybook/os-path.htm
'''
def __init__(self, directory, pattern="*", regex=False, regex_flags=0, recurse=True):
''' @type directory: C{str}
@param directory: Path to search
@type pattern: C{type}
@param pattern: Regular expression/wildcard pattern to match files against
@type regex: C{boolean}
@param regex: Use regular expression matching (if False, use fnmatch)
See U{http://docs.python.org/library/re.html}
@type regex_flags: C{int}
@param regex_flags: Flags to pass to the regular expression compiler.
See U{http://docs.python.org/library/re.html}
@type recurse: C{boolean}
@param recurse: Recurse into the directory?
'''
self.stack = [directory]
self.pattern = pattern
self.regex = regex
self.recurse = recurse
self.regex_flags = regex_flags
self.files = []
self.index = 0
def __getitem__(self, index):
while 1:
try:
file = self.files[self.index]
self.index = self.index + 1
except IndexError:
# pop next directory from stack
self.directory = self.stack.pop()
try:
self.files = os.listdir(self.directory)
self.index = 0
except:pass
else:
# got a filename
fullname = os.path.join(self.directory, file)
if os.path.isdir(fullname) and not os.path.islink(fullname) and self.recurse:
self.stack.append(fullname)
if self.regex:
import re
if re.search(self.pattern,file,self.regex_flags):
return fullname
else:
import fnmatch
if fnmatch.fnmatch(file, self.pattern):
return fullname
shplist=[shp for shp in rglob(top,'*.shp')]
print 'Merging: ' + str(shplist)
#arcpy.Merge_management(shplist, RootOutput+"\\Full_Extent.shp")
print 'Created: '+RootOutput+"\\Full_Extent.shp"
f = open(RootOutput+'\\Success_LOG.txt', 'a')
f.write(str(shplist)+"\n\n Merged to: "+RootOutput+"\\Full_Extent.shp")
f.close()
精彩评论