For looping folder to batch clip rasters by polygon using python and QGIS?

Question

I am using Python and QGIS 2.0.

I am trying to clip rasters in a folder by one polygon feature.

It's the first time for me using PyQGIS; I was used to ArcPy before.

How do I get my script to work?

import qgis.core, qgis,utils
QgsApplication.setPrefixPath("C:/OSGeo4W64/apps/qgis", True)
QgsApplication.initQgis()

CLIP= "C:/Users/unim/Documents/Umberto/Universita/PhD/Guglielmin/Permafrost/Alta_Valtellina/Landsat_ita/study_area_foscagno.shp"
INPUT_FOLDER="C:/Users/unimi/Documents/Umberto/Universita/PhD/Guglielmin/Permafrost/Alta_Valtellina/Landsat_ita/LE71930282000259EDC00"
OUTPUT= "C:/Users/unim/Documents/Umberto/Universita/PhD/Guglielmin/Permafrost/Alta_Valtellina/Landsat_ita/foscagno_pyqgis/"


for RASTER in INPUT_FOLDER.tif
do
    echo "Processing $RASTER"
    gdalwarp -q -cutline CLIP -crop_to_cutline -of GTiff RASTER OUTPUT+ "clip_"+ RASTER
done

QgsApplication.exitQgis()

Below are the improvements I've done since now, not getting the script to work though, but I think I might be getting closer.

import qgis.core, qgis.utils, os, fnmatch
from osgeo import gdal

CLIP= "C:/Users/unimi/Documents/Umberto/Universita/PhD/Guglielmin/Permafrost/Alta_Valtellina/Landsat_ita/study_area_foscagno.shp"
INPUT_FOLDER= "C:/Users/unimi/Documents/Umberto/Universita/PhD/Guglielmin/Permafrost/Alta_Valtellina/Landsat_ita/LE71930282000259EDC00/DNs2Reflectance_LE71930282000259EDC00"
OUTPUT= "C:/Users/unimi/Documents/Umberto/Universita/PhD/Guglielmin/Permafrost/Alta_Valtellina/Landsat_ita/Cloud_mask_AltaValtellina/clip_2_foscagno"

def findRasters (path, filter):
    for root, dirs, files in os.walk(path):
        for file in fnmatch.filter(files, filter):
            yield os.path.join (root, file)

for raster in findRasters (INPUT_FOLDER, '*.tif'):
    print (raster)
    outRaster = OUTPUT + '/clip_' + raster
    cmd = 'gdalwarp -dstnodata 0 -q -cutline CLIP -crop_to_cutline %s %s' % (raster, outRaster)
    os.system (cmd)

I think there might be something wrong in the "gdal" command, as the "print" function does its job properly, but no file is written to the output, neither I receive any error.

Answer 1

You need to pythonize your whole script. So substitute your for loop with something like the following:

import os, fnmatch

def findRasters (path, filter):
    for root, dirs, files in os.walk(path):
        for file in fnmatch.filter(files, filter):
            yield file

for raster in findRasters(INPUT_FOLDER, '*.tif'):
    inRaster = INPUT_FOLDER + '/' + raster
    outRaster = OUTPUT_FOLDER + '/clip_' + raster
    cmd = 'gdalwarp -q -cutline %s -crop_to_cutline %s %s' % (CLIP, inRaster, outRaster)
    os.system(cmd)

Note 1: I'm supposing that your raster files are GeoTIFF (*.tif).
Note 2: -of GTiff is not needed in cmd, because it's the default output format in gdalwarp.

Answer 2

Modified version of umbe1987`s solution for Linux users:

import os, fnmatch
from subprocess import call
call(["ls", "-l"])

inFolder= '/run/media/user/SOFT/LANDSAT/Bulk Order 595257/L8 OLI_TIRS/LC81840262015165LGN00/'
outFolder= '/run/media/user/SOFT/LANDSAT/Bulk Order 595257/summer_clipped/'
shp = '/run/media/user/SOFT/LANDSAT/Bulk Order 595257/vector/mask.shp'
os.chdir (inFolder)

def findRasters (path, filter):
    for root, dirs, files in os.walk(path, filter):
        for file in fnmatch.filter(files, filter):
            yield os.path.join (root, file)

for raster in findRasters (inFolder, '*.TIF'):
    (infilepath, infilename)= os.path.split (raster)
    print infilename
    outRaster= outFolder+ 'clip_'+ infilename
    print outRaster
    warp= 'gdalwarp -cutline \'%s\' -crop_to_cutline -dstalpha \'%s\' \'%s\'' % (shp, raster, outRaster)
    os.system(warp)

Answer 3

I finally managed with this very simple and clean script, which calls GDAL from Python without importing it (as suggested, but using "Call ()" method instead of "os.system ()".

import os, fnmatch
from subprocess import call
call(["ls", "-l"])

inFolder= 'C:/Users/unimi/Documents/Umberto/Universita/PhD/Guglielmin/Permafrost/Alta_Valtellina/Landsat_ita/LE71930282000259EDC00/DNs2Reflectance_LE71930282000259EDC00/'
outFolder= 'C:/Users/unimi/Documents/Umberto/Universita/PhD/Guglielmin/Permafrost/Alta_Valtellina/Landsat_ita/Cloud_mask_AltaValtellina/clip_2_foscagno/'

os.chdir (inFolder)

def findRasters (path, filter):
    for root, dirs, files in os.walk(path, filter):
        for file in fnmatch.filter(files, filter):
            yield os.path.join (root, file)

for raster in findRasters (inFolder, '*.tif'):
    (infilepath, infilename)= os.path.split (raster)
    print infilename
    outRaster= outFolder+ 'clip_'+ infilename
    print outRaster
    warp= 'gdalwarp -dstnodata 0 -q -cutline %s -crop_to_cutline -of GTiff %s %s' % ('study_area_foscagno.shp', raster, outRaster)
    call (warp)

Answer 4

Here is a version for GDAL >= 2.1 that does not use 'from subprocess call gdal'

import os, fnmatch
from osgeo import gdal
call(["ls", "-l"])

inFolder = "/Users/username/Documents/MassCropTest/"
outFolder =  "/Users/username/Documents/MassCropTest/OutputFolder/"
mask = "/Users/username/Documents/MassCropTest/Mask2.shp"
os.chdir (inFolder)

def findRasters (path, filter):
    for root, dirs, files in os.walk(path, filter):
        for file in fnmatch.filter(files, filter):
            yield os.path.join (root, file)


for raster in findRasters (inFolder, '*.tif'): #Find all tifs
        (infilepath, infilename)= os.path.split (raster)
        print(infilename)
        outRaster= outFolder+ 'clip_'+ infilename
        print(outRaster)
        warp= gdal.Warp(outRaster,raster, cutlineDSName = mask, dstNodata = 255)