bin/get-fandom-wiki-urls

134 lines
4.9 KiB
Python
Executable File

#!/usr/bin/env python3
#
# This little script makes it easy to Archive All The Things.
# It prints a list of URLs from fandom wiki pages to stdout.
#
# Stdout can then be redirected to a plaintext file with e.g:
# `get-fandom-wiki-urls cyberpunk > ~/downloads/cyberpunk-wiki-urls.txt`
#
# These URLs can then be imported directly into ArchiveBox. Each URL will
# be a page of the local sitemap. The local sitemap is a list of wiki pages
# in alphabetical order. Importing the URLs scraped by the script into
# ArchiveBox with a depth of '1' will pull every URL one hop away, so every
# wiki page listed in the local sitemap will be archived.
#
# This script wouldn't be necessary if there was a way to view the entire
# local sitemap in one html page. Then all you'd have to do is import the
# URL for the local sitemap into ArchiveBox with a depth of '1'. As far I
# know there is no way to get this view of the local sitemap. For some
# unknown reason the Wiki fandom site developers didn't design the frontend
# to enable that.
#
# LICENSE
# This is free and unencumbered software released into the public domain.
# Anyone is free to copy, modify, publish, use, compile, sell, or
# distribute this software, either in source code form or as a compiled
# binary, for any purpose, commercial or non-commercial, and by any
# means.
# In jurisdictions that recognize copyright laws, the author or authors
# of this software dedicate any and all copyright interest in the
# software to the public domain. We make this dedication for the benefit
# of the public at large and to the detriment of our heirs and
# successors. We intend this dedication to be an overt act of
# relinquishment in perpetuity of all present and future rights to this
# software under copyright law.
# THE SOFTWARE IS PROVIDED \AS IS\, WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
# IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
# OTHER DEALINGS IN THE SOFTWARE.
# For more information, please refer to <https://unlicense.org>
import sys
import requests
from bs4 import BeautifulSoup
def get_hop0_urls(fandom: str) -> list():
starting_url = "https://" + fandom + ".fandom.com/wiki/Local_Sitemap"
hop0_urls = [starting_url]
while True:
reqs = requests.get(starting_url)
soup = BeautifulSoup(reqs.text, "html.parser")
mw_allpages_nav = soup.find_all("div", {"class": "mw-allpages-nav"})[0]
if (
len(mw_allpages_nav.find_all("a")) < 2
and "Next page" not in mw_allpages_nav.find_all("a")[0].get_text()
):
break
else:
if len(mw_allpages_nav.find_all("a")) < 2:
starting_url = (
"https://"
+ fandom
+ ".fandom.com"
+ mw_allpages_nav.find_all("a")[0].get("href")
)
else:
starting_url = (
"https://"
+ fandom
+ ".fandom.com"
+ mw_allpages_nav.find_all("a")[1].get("href")
)
hop0_urls.append(starting_url)
return hop0_urls
def get_hop1_urls(hop0_urls: list) -> list():
hop1_urls = list()
for url in hop0_urls:
reqs = requests.get(url)
soup = BeautifulSoup(reqs.text, "html.parser")
fandom = url.split(sep="/wiki")[0]
for item in soup.find_all("a"):
if item.get("href") and item.get("href").startswith("/wiki"):
hop1_urls.append(fandom + item.get("href"))
return hop1_urls
def help_message():
supported_wikis = ["cyberpunk", "dishonored", "dragonage", "forgottenrealms", "masseffect", "residentevil"]
print("Supply a fandom wiki name as arg1.\n")
print("Currently supported wikis:")
for wiki in supported_wikis:
print("- %s" % wiki)
if __name__ == "__main__":
if len(sys.argv) > 1:
match sys.argv[1]:
case "cyberpunk":
urls = get_hop1_urls(get_hop0_urls("cyberpunk"))
case "dishonored":
urls = get_hop1_urls(get_hop0_urls("dishonored"))
case "dragonage":
urls = get_hop1_urls(get_hop0_urls("dragonage"))
case "forgottenrealms":
urls = get_hop1_urls(get_hop0_urls("forgottenrealms"))
case "masseffect":
urls = get_hop1_urls(get_hop0_urls("masseffect"))
case "residentevil":
urls = get_hop1_urls(get_hop0_urls("residentevil"))
case _:
help_message()
for url in urls:
print(url)
else:
help_message()