Created
October 22, 2022 10:34
-
-
Save TheMasteredPanda/940ce56d76eb3abdce1baf5d0ddc317e to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import asyncio | |
import json | |
import aiohttp | |
import bs4 | |
from bs4.element import Tag | |
async def parse_cgs(): | |
async with aiohttp.ClientSession() as session: | |
async with session.get( | |
"https://tldrnews.co.uk/discord-community-guidelines/" | |
) as response: | |
result = {} | |
html = await response.text() | |
soup = bs4.BeautifulSoup(html, "html.parser") | |
entry = soup.find("div", {"class": "entry-content"}) | |
cg_list = [*entry.children][15] | |
cg: bs4.element.Tag | |
i: int | |
def walk(step_str: str, cg_id: int, parent: Tag, branch: Tag) -> dict: | |
contents = branch.contents | |
result = {} | |
if len(contents) > 1: | |
step_str = f"{step_str}.{cg_id}" | |
for i, cg_c in enumerate( | |
filter(lambda cg_c: type(cg_c) == Tag, contents[1]) | |
): | |
result = result | walk(step_str, i + 1, branch, cg_c) | |
else: | |
step_str = f"{step_str}.{cg_id}" | |
result[step_str] = contents[0] | |
return result | |
parsed_cg = {} | |
for i, cg in enumerate(filter(lambda cg: type(cg) == Tag, cg_list)): | |
cg_id = i + 1 | |
str_cg_id = f"{cg_id}" | |
contents = cg.contents | |
parsed_cg[str_cg_id] = contents[0] | |
if len(contents) > 1: | |
cg_c: Tag | |
j: int | |
for j, cg_c in enumerate( | |
filter(lambda cg_c: type(cg_c) == Tag, contents[1]) | |
): | |
parsed_cg = parsed_cg | walk(str_cg_id, j + 1, cg, cg_c) | |
return parsed_cg | |
async def main(): | |
result = await parse_cgs() | |
print(json.dumps(result, indent=4)) | |
asyncio.run(main()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment