Appends all URLs in a given text with numbers surrounded by brackets and returns a tuple with the new text and a dict-list with the urls and their numbers.

append_urls_to_text_bottom.py

def append_urls_to_text_bottom(text):
	import re
	url_counter = 0
	unique_url_list = dict()
	appending_list = dict()
	url_expression = "(?:(?:https?|ftp)://)(?:\\S+(?::\\S*)?@)?(?:(?!10(?:\\.\\d{1,3}){3})(?!127(?:\\.\\d{1,3}){3})(?!169\\.254(?:\\.\\d{1,3}){2})(?!192\\.168(?:\\.\\d{1,3}){2})(?!172\\.(?:1[6-9]|2\\d|3[0-1])(?:\\.\\d{1,3}){2})(?:[1-9]\\d?|1\\d\\d|2[01]\\d|22[0-3])(?:\\.(?:1?\\d{1,2}|2[0-4]\\d|25[0-5])){2}(?:\\.(?:[1-9]\\d?|1\\d\\d|2[0-4]\\d|25[0-4]))|(?:(?:[a-z\\u00a1-\\uffff0-9]+-?)*[a-z\\u00a1-\\uffff0-9]+)(?:\\.(?:[a-z\\u00a1-\\uffff0-9]+-?)*[a-z\\u00a1-\\uffff0-9]+)*(?:\\.(?:[a-z\\u00a1-\\uffff]{2,})))(?::\\d{2,5})?(?:/[^\\s]*)?"
		
	list_of_all_urls = re.findall(url_expression, text)

	for one_url in list_of_all_urls:
		if one_url not in unique_url_list:
			url_counter += 1
			unique_url_list[one_url] = url_counter
			
	for single_url, single_number in unique_url_list.items():
		text = re.sub(single_url, "[%d]" % single_number, text)
		appending_list[single_number] = single_url
	
	return (text, appending_list)