chatbot/scraper_functions.py

import requests
from bs4 import BeautifulSoup
from urllib.parse import quote

def query_external_website(base_url, query):
    try:
        page = requests.get(base_url + quote(query))
        soup = BeautifulSoup(page.content, "html.parser")
        title = soup.find(id="firstHeading").text
        mainContentElement = soup.find(id="mw-content-text")
        if "This page is a redirect" in mainContentElement.text:
            redirectLink = mainContentElement.find(class_="redirectMsg").find_all("a")[0]["href"]
            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

def getDmzTasks(url):
    try:
        page = requests.get(url)
        soup = BeautifulSoup(page.content, "html.parser")
        tasks = soup.find_all(class_="task")
        result = "\nActive tasks:\n"
        for task in tasks:
            taskIndex = task.select("div")[0].text
            taskTitle = task.select("div")[1].text
            result += taskIndex + " " + taskTitle + " | " + "Link: " + url + task.find("a")["href"][1:] + "\n"
        return result
    except Exception as e:
        return e