# File_in is essentially copy-paste of the text version of the webpage:
# http://dfat.gov.au/about-us/our-people/homs/pages/australian-ambassadors-and-other-representatives.aspx
# Ctrl-A, then Ctrl-C, then Ctrl-V into a file list.txt, making sure to remove all lines except the list
# (Whitespaces between names/countries will be removed during execution of this script)
file_in  = open("list.txt", "r")
file_out = open("list2.txt", "w")

lists  = [line for line in file_in]

# Removes duplicates in input file, and organises data
lists2 = []

i = 0
while i < len(lists):
    if lists[i] == "\n":
        i += 2
    else:
        lists2.append(lists[i].rstrip("\n"))
        i += 1

# Organises data into (title+country, person) format
lists3 = []

i = 0
while i < len(lists2)-1:
    lists3.append((lists2[i+1],lists2[i]))
    i += 2

# Organises data into (country, title, person) format
lists4 = []
for country, person in lists3:
    # Removes instances of " , located in "
    country2 = country.partition(", ")[0]
    # Remove title (e.g. "Mr", "Ms") from person. Has some false positives
    person2 = person.partition(" ")[2]

    if "Consul" in country or "Deputy" in country:
        continue
    elif "Ambassador" in country:
        cnty = country2[14:] # Remove "Ambassador to "
        lists4.append((cnty, "Ambassador", person))
    elif "High Commissioner" in country:
        cnty = country2[21:] # Remove "High Commissioner to "
        lists4.append((cnty, "High Commissioner", person))
    else: # Edge case
        lists4.append((country, "", person))

# Outputs wikipedia markup
for cnty, title, person in lists4:
    file_out.write("|-\n")
    file_out.write("| [[" + cnty + "]] | [[" + title + " of Australia to " + cnty + "|" + title + "]] | " + person2 + "\n")

# Further modifications are necessary, but are mostly case-by-case