Decentrala/chatbot
12
0
Fork 1
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix wiki commands

Browse Source
This commit is contained in:
fram3d 2024-02-06 20:51:31 +01:00
commit c011383f0e
Signed by: fram3d
GPG Key ID: 938920E709EEA32A
2 changed files with 16 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
functions.py
View File

@ -21,5 +21,6 @@ def command(msg, rcpt):
response = client.chat(model='llama2-uncensored:latest', messages=[{'role':'user','content':f'{msg[4:]}'}]) response = client.chat(model='llama2-uncensored:latest', messages=[{'role':'user','content':f'{msg[4:]}'}])
return(response['message']['content']) return(response['message']['content'])
elif msg.startswith("!wiki"): elif msg.startswith("!wiki"):
return sf.query_external_website("https://en.wikipedia.org/wiki/", msg.split(" ")[1]) cmd, query = msg.split(" ", 1)
return sf.query_external_website("https://en.wikipedia.org", "/wiki/" + query)

19
scraper_functions.py
View File

@ -1,12 +1,19 @@
import requests import requests
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from urllib.parse import quote
def query_external_website(base_url, query): def query_external_website(base_url, query):
try: try:
page = requests.get(base_url + query) page = requests.get(base_url + quote(query))
soup = BeautifulSoup(page.content, "html.parser") soup = BeautifulSoup(page.content, "html.parser")
title = soup.find("span", class_="mw-page-title-main").text title = soup.find(id="firstHeading").text
content = soup.find(id="mw-content-text").select("p")[2].text mainContentElement = soup.find(id="mw-content-text")
return "\nTITLE:\n" + title + "\n\nCONTENT:\n" + content + "\n\nFULL LINK:\n" + base_url + query if "This page is a redirect" in mainContentElement.text:
except: redirectLink = mainContentElement.find(class_="redirectMsg").find_all("a")[0]["href"]
return "Can't parse search result :(" return query_external_website(base_url, redirectLink)
content = next((paragraph for paragraph in mainContentElement.select("p") if not paragraph.has_attr("class")), None)
if content == None:
raise Exception("Can't parse search result :(")
return "\nTITLE:\n" + title + "\n\nCONTENT:\n" + content.text + "\n\nFULL LINK:\n" + base_url + quote(query)
except Exception as e:
return e