extract_participants_copX.py
154caa57dcc3master

extract_participants_copX.py
View Options

			""" The main script of the cop participants extraction.
			Takes as an argument the number of the cop to process.
			"""

			import os
			import sys

			from COP_TextExtractor import COP_TextExtractor
			from COP_Analyzer import COP_Analyzer


			# Constants
			# This is used to differ names from abbreviations
			uppercase_abbrev = ["US", "USA", "AO", "UK", "WWF-US", "WWF-UK", "EPFL"]
			# Must be a tuple for the funtion "startsWith" of String
			salutory_addresses = ("Mr", "Ms", "Sr", "Sra", "H.E.", "S.E.", "M.",
			"Mme", "Dr.", "Drs.")

			seperator = "#"


			# format:
			# extract_participants_xopX.py <numberOfCop> <intermediateFilename>
			# <outputFilename> (<startpage> <endpage>)
			# the last option is given if the OCR has already been done (for cop 1 - 4)

			# parse arguments
			arguments = sys.argv
			cop_number = int(arguments[1])
			intermediate_name = arguments[2]
			output_name = arguments[3]
			startpage = 0
			endpage = 0
			if(len(arguments) == 6):
			startpage = int(arguments[4])
			endpage = int(arguments[5])

			succ = False

			# First, extract the text from the pdf if not already done
			if not os.path.isfile(intermediate_name):
			extr = COP_TextExtractor(cop_number, intermediate_name)
			succ = extr.extract_text()

			# Second, extract the data from the text
			ana = COP_Analyzer(cop_number, intermediate_name, output_name)
			succ = ana.get_data()

			# TODO properly handle succ

			if succ:
			print("The data has successfully been extracted")
			else:
			print("The data couldn't be extracted correctly. Maybe this cop is not implemented yet.")