Recursively search folders for '.log' files and scan them for a certain regular expression.

snippet.sc

#! /usr/bin/env python
# Recursively search folders for '.log' files and scan them for a certain regular expression.
import re # regular expressions
import fileinput, sys, os

# precompile the search into a RegularExpression object to make it faster when we do it lots of times
searchExpression=re.compile("Sum\ of\ electronic\ and\ zero-point\ Energies=\s*([\-0-9.]+)")

def process_folder(folderpath):
	#print "searching",folderpath
	folders_to_process=[]
	files_to_process=[]
	for entry in os.listdir(folderpath):
		path = os.path.join(folderpath, entry)
		if os.path.isdir(path):
			folders_to_process.append(path)
		elif re.search('\.log$',entry):
			files_to_process.append(path)
	if files_to_process:
		process_files(files_to_process)
	for path in folders_to_process:
		process_folder(path)
	
def process_files(filelist):
	# fileinput takes all command line arguments (sys.argv[1:]) as files
	# or if given a list of files, uses those
	for line in fileinput.input(filelist):
		match=searchExpression.search(line)
		if match: 
			(fileroot,filextension) = os.path.splitext(fileinput.filename())
			(filepath,filename) = os.path.split(fileroot)
			print "%s\t%s\t%s" % (filepath,filename , match.groups()[0])

# process the folder given on the command line
if sys.argv[1:]:
	for path in sys.argv[1:]:
		if os.path.isdir(path):
			process_folder(path)
else: 
	print "Please supply folder(s) to search. (folders, not files)"