get yo links

scrap99.py

#script guidance from John G. Fisher
# check his youtube https://www.youtube.com/watch?v=e6xZAISu-5E
# grab all links we talked about
from bs4 import BeautifulSoup
import requests
import re

#use 'python http.server' on the directory to serve the folder. sb4 doesnt do local links
inbox_path='http://localhost:8000/messages/inbox/ElBootkeh_64b09d1ba5/message.html'
print(inbox_path)
url = requests.get(inbox_path)
soup = BeautifulSoup(url.text, 'html.parser')

with open('idiot_links.txt', 'w') as f:
    for link in soup.find_all(href=True):
        try:
            #grab href see> https://stackoverflow.com/q/5815747/184085
            link=link['href']
            print(link)
            # afterwards pass .html\?.*$ into .html (in vscode to fomrat long aliexpress links...)
            link=re.sub(r'.html\?.*$',r'.html',link)
            #TBD remove stickers messages with '^messages/stickers_used.*png'
            #TBD shorten deep dirs
            #TBD remove dups 'awk '!seen[$0]++' idiot_links.txt > idiot_linksU.txt'
            #TBD reverse order
            #TBD add {{currly bractes}} to media
            #TBD extract date of event
            #TBD auto uplaod relevant files to wiki
            f.write(link.lstrip() + '\n\n')
        except:
            TypeError