Create a runelite bank tag import from a runescape wiki category

OSRS wiki category to runelite bank tags.py

"""
By Mitch Barnett
Discord: Frogman#5072
"""
from mwclient import Site       # pip install mwclient
import re


# Wiki category to collect id's from
wiki_category = "Pets"


# Wiki URL and path to api.php
site = Site("oldschool.runescape.wiki", path="/")


def get_item_ids_from_page(page):
    """Return the item id's found on the given page"""
    print("Getting ID(s) for " + page.page_title)
    # Regex pattern to find "|id? = ???", "|id? = ???,???,???" "|itemid? = ???" and "|itemid? = ???,???,???"
    item_id_regex = r"\|(?:item)?id\d*\s*=\s*(\d+(?:,?\s*\d+)*)"
    regex_matches = re.findall(item_id_regex, page.text())
    ids_found = []

    for match in regex_matches:
        match.replace(' ', '')          # Remove spaces
        match_ids = match.split(',')    # Split into single id's
        ids_found += match_ids

    if ids_found:
        print("Found ID(s): " + str(ids_found) + '\n')
        return ids_found
    else:
        print("No ID found \n")
        return ids_found


def get_item_ids_from_category(category, checked_pages=None):
    """Return the item id's found in the pages of the given category"""
    if checked_pages is None:
        checked_pages = []
    item_ids = []                               # List of item id's to be populated
    page_list = site.categories[category]       # Page list to be iterated through

    for page in page_list:
        if page.page_title in checked_pages:    # Don't check pages multiple times to save time
            continue
        if page.namespace == 14:                # Page is in category namespace
            print("Subcategory " + page.page_title)
            item_ids += get_item_ids_from_category(page.page_title, checked_pages)    # Recurse on the subcategory
            checked_pages.append(page.page_title)
        else:
            item_ids += get_item_ids_from_page(page)
            checked_pages.append(page.page_title)
    return item_ids


item_ids = get_item_ids_from_category(wiki_category)
item_ids = list(set(item_ids))                          # Remove duplicates()
item_ids.sort(key=int)


import_string = wiki_category + ',' + item_ids[0] + ','
for item_id in item_ids:
    import_string += str(item_id) + ','

import_string = import_string[:-1]

runelite_preview_link = "https://runelite.net/tag/show/" + import_string

print('\n')
print("Runelite import string:")
print(import_string)
print('\n')
print("Runelite preview link:")
print(runelite_preview_link)