Last active
June 9, 2016 15:03
-
-
Save tarxvf/041f3b9553ca88de5a047b6ea7a4ed8e to your computer and use it in GitHub Desktop.
takes a directory of files (in this case PDF targets, and creates a distribute list of N processing files (to push out to a poor man's cluster using something like <script src="https://gist.github.com/tarxvf/ba49560220e69a90d1df379a3f309150.js"></script>
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
rootdir = '/tmp/' | |
import re | |
count=0 | |
for subdir, dirs, files in os.walk(rootdir): | |
for file in files: | |
#print file | |
m = re.search("[0-9]+\.pdf$",file) | |
if hasattr(m, 'group'): | |
if m.group(0): | |
#print os.path.join(subdir, file) | |
count=count+1 | |
file_name="/tmp/process_group_{}.txt".format(int(count/501)) | |
print "filename={0} count={1}".format(file_name,count) | |
with open(file_name, "a") as text_file: | |
text_file.write("{0}\n".format(file)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment