List the titles of portlets extracted from the portlet-definition.xml files in a specified directory.

list_portlets.py

import os
import re
import sys

'''
Given the path to a directory containing uPortal portlet-definition.xml entity files, prints the title element from each.
Assumes . if target directory not specified.

Example of running:
$ python list_portlets.py /Users/apetro/code/code_doit/MUM-overlay/my-prod-overlay/entities/tags/entities-51/src/main/resources/portlet-definition
Academic Advisors List of Advisees - with Notes
Academic Planning and Analysis
Academic Resources
Access Denied Records
Activate Services
Advisee Lookup - with Notes
Advisee Lookup
...

'''


def main():
  # Get the directory of portlets from the command line, using '.' as a fallback.
  target_directory = "."

  if len(sys.argv) >= 2:
    target_directory = sys.argv[1]
  
  if target_directory == "-h":
  	print("usage: [path to target directory]")
  	sys.exit(1)

  # TODO: filter down to portlet-definition.xml files
  # TODO: limit file size so as to not open illegitimately large files
  portlet_definition_file_names = [name for name in os.listdir(target_directory) if os.path.isfile(os.path.join(target_directory, name))]

  for portlet_definition_file_name in portlet_definition_file_names:
  	full_path_file_name = os.path.join(target_directory, portlet_definition_file_name)
	with open(full_path_file_name, 'rt') as f:
	  file_contents = f.read()
	  match = re.search('(<title>)(.*)(</title>)', file_contents)
	  if match:
	  	print match.group(2)

  
if __name__ == '__main__':
  main()