import os chains_for_pbd=dict() file_list = os.listdir("top500H") for file in file_list : pdb = file[0:4].upper() chains = file[4:-1] assert pdb.lower() + chains + "H" == file if pdb in chains_for_pbd : print "Merging separate entries for %s chains %s and %s" \ % (pdb, chains_for_pbd[pdb], chains) chains_for_pbd[pdb] = chains_for_pbd[pdb] + chains else : chains_for_pbd[pdb]=chains pdb_names = chains_for_pbd.keys() pdb_names.sort() output_file = open("top500_list.tsv","w") for pdb in pdb_names: output_file.write("%s\t%s\n" % (pdb, chains_for_pbd[pdb])) output_file.close()