Merge files starting with same characters using ArcPy

Question

I am trying to merge files starting with same 2 characters as below;

1. 11111 - merge (output name : 11.shp)
2. 11112 - merge (output name : 11.shp)
3. 11113 - merge (output name : 11.shp)
4. 22112 - merge (output name : 22.shp)
5. 22153 - merge (output name : 22.shp)

But my python script' result merge together if "11" is including in the filenames(like 4)). I only want 11***.shp(1)~3)) but A Script merges 11.shp (merge 1~4 as 11.shp)

========================================================================

import sys, os, arcpy, fnmatch
reload(sys)

arcpy.env.workspace  = r"F:\a"


workspace = arcpy.env.workspace
outdir = r"F:\b"

List = []

for dirpath, dirnames, filenames in os.walk(workspace, topdown=True):
    for filename in filenames:
        List.append(os.path.join(dirpath, filename))
    break

patterns = set([os.path.basename(fl)[:2] for fl in List])

for pattern in patterns:
    group = [fl for fl in List if fnmatch.fnmatchcase(fl, '*' + pattern + '*.shp')]
    output = os.path.join(outdir, pattern)
    arcpy.Merge_management(group, output)

========================================================================

How can I fix it?

Answer 1

I like collections.defaultdict(list):

...to group a sequence of key-value pairs into a dictionary of lists

Example:

import arcpy, os
from collections import defaultdict as dd

folder = r'C:\GIS\data\testdata\merge'
out_folder = r'C:\GIS\data\testdata\outfolder'

d = dd(list)

for item in os.listdir(folder):
    if os.path.isfile(os.path.join(folder,item)) and file.endswith('.shp'):
        d[item[:2]].append(os.path.join(folder, item))

#Execute code above then print(d) to make sure its ok before merging 

for group, mergelist in d.items():
    #print(group, mergelist)
    arcpy.Merge_management(inputs=mergelist, output=os.path.join(out_folder, 'Merge_{}.shp'.format(group)))

If you want to search subdirectories aswell use os.walk like you tried, example:

import os
from collections import defaultdict as dd

folder_main = r'C:\GIS\data\testdata'
d = dd(list)
for root, folder, files in os.walk(folder_main):
    for file in files:
        if os.path.isfile(os.path.join(root, file)) and file.endswith('.shp'):
            print(file)
            d[file[:2]].append(os.path.join(root, file))