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

Added try catch for scraper functions

Browse Source
This commit is contained in:
texhno 2024-02-06 02:37:19 +01:00
parent 9c76ea38ce
commit 9c63ada6e5
1 changed files with 8 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
scraper_functions.py
View File

@ -2,8 +2,11 @@ import requests
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
def query_external_website(base_url, query): def query_external_website(base_url, query):
page = requests.get(base_url + query) try:
soup = BeautifulSoup(page.content, "html.parser") page = requests.get(base_url + query)
title = soup.find("span", class_="mw-page-title-main").text soup = BeautifulSoup(page.content, "html.parser")
content = soup.find(id="mw-content-text").select("p")[2].text title = soup.find("span", class_="mw-page-title-main").text
return "\nTITLE:\n" + title + "\n\nCONTENT:\n" + content + "\n\nFULL LINK:\n" + base_url + query content = soup.find(id="mw-content-text").select("p")[2].text
return "\nTITLE:\n" + title + "\n\nCONTENT:\n" + content + "\n\nFULL LINK:\n" + base_url + query
except:
return "Can't parse search result :("