Created
June 10, 2021 20:54
-
-
Save emresaglam/8da2a417b47fd169ed529f4fbc456dbb to your computer and use it in GitHub Desktop.
Crude scraper for the security conferences page
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
import json | |
from bs4 import BeautifulSoup as bs | |
# The URL for the conf page | |
url = "https://infosec-conferences.com/" | |
r = requests.get(url) | |
r.text | |
# header needed as their nginx blocks other User Agents... | |
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36'} | |
r = requests.get(url, headers=headers) | |
conf = r.text | |
conferences = [] | |
soup = bs(conf,features="html.parser") | |
conf_list = soup.find("div", {"class": "conf_list"}) | |
for p in conf_list.find_all("p"): | |
conference = {} | |
link = p.find("a", {"rel": "ugc"}) | |
conference["link"] = link["href"] | |
conference["text"] = link.text | |
date_blob = p.find("span", {"class": "e74c3c"}) | |
conference["date"] = date_blob.text | |
conferences.append(conference) | |
loc_blob = p.find("a", {"rel": "tag"}) | |
conference["location"] = loc_blob.text | |
# Printing, but it's up to you to do whatever... | |
print(json.dumps(conferences)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment