Files
SoftwareManager/src/core/data/scrapers/uztracker.py
T

35 lines
1.2 KiB
Python

import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
from core.utils.logging.logs import consoleLog
def scrape_uztracker(query):
base_url="https://uztracker.net/"
search_url = f"{base_url.rstrip('/')}/tracker.php?nm={query}"
consoleLog(search_url)
posts = []
try:
response = requests.get(search_url)
response.raise_for_status()
soup = BeautifulSoup(response.text, 'html.parser')
links = soup.find_all('tr', class_="tCenter hl-tr", id=lambda x: x and x.startswith('tor_'))
for link in links:
theme_link = link.find('a', class_="genmed tLink", href=lambda x: x and x.startswith('./viewtopic'))
url = urljoin(base_url, theme_link['href'])
title = theme_link.b.text
author_link = link.find('a', class_="med")
author = author_link.text.strip() if author_link else "Unknown"
posts.append(dict(
title=title,
url=url,
author=author
))
return posts
except requests.RequestException as e:
consoleLog(f"Failed to fetch {search_url}: {e}")
return None