Added scraper functions (wikipedia,for now)
This commit is contained in:
9
scraper_functions.py
Normal file
9
scraper_functions.py
Normal file
@@ -0,0 +1,9 @@
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
def query_external_website(base_url, query):
|
||||
page = requests.get(base_url + query)
|
||||
soup = BeautifulSoup(page.content, "html.parser")
|
||||
title = soup.select(".mw-page-title-main")[0]
|
||||
content = soup.find(id="bodyContent").select("p")[2].text
|
||||
return "\nTITLE: " + title.text + "\n\n" + "CONTENT:" + "\n" + content + "\n\n" + "FULL LINK:\n" + base_url + query
|
Reference in New Issue
Block a user