Re-create missing .shx-file for ESRI shapefiles

generate_shx.py

# Based on solution given here: http://geospatialpython.com/2011/11/generating-shapefile-shx-files.html
# Depends on pyshp

# Build a new shx index file
import fnmatch
import os
import shapefile

# List all the shapefiles
def find(pattern, path):
    result = []
    for root, dirs, files in os.walk(path):
        for name in files:
            if fnmatch.fnmatch(name, pattern):
                result.append(os.path.join(root, name))
    return result

shp_files = find('*.shp', '.')

for shp_file in shp_files:

  # Explicitly name the shp and dbf file objects
  # so pyshp ignores the missing/corrupt shx
  
  shp = open(shp_file, "rb")
  dbf = open(shp_file.replace("shp", "dbf"), "rb")
  r = shapefile.Reader(shp=shp, shx=None, dbf=dbf)
  w = shapefile.Writer(r.shapeType)
  
  # Copy everything from reader object to writer object
  
  w._shapes = r.shapes()
  w.records = r.records()
  w.fields = list(r.fields)
  
  # saving will generate the shx
  fixed_shp_file = os.path.join(os.path.dirname(shp_file),
                                "fixed_" + os.path.basename(shp_file))
  w.save(fixed_shp_file)

For corrupted shapefile, I also used shapechecker. It reconstruct the dbf and shx when missing.

Download here: http://www.oocities.org/andrew_williamson/old_shapechk.zip
Page: https://allaroundgis.wordpress.com/2013/12/10/shapefile-shp-shape-checker-v3-2/

@jlehtoma, what's the license on this script?

^Same question :)

Note: This script does not work anymore!
You have to specify the filename when creating the writer object:
fixed_shp_file = os.path.join(os.path.dirname(shp_file), "fixed_" + os.path.basename(shp_file))
w = shapefile.Writer(fixed_shp_file, shapeType=r.shapeType)
and then instead of using save, just close (it auto-saves)

The way you copy the fields + records + shapes has also changed. See Adding from an existing Shape object of https://github.com/GeospatialPython/pyshp