Skip to content

Fix: Validate and sanitize search URL to prevent open redirect vulnerability #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
SoClosee wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix: Validate and sanitize search URL to prevent open redirect vulnerability #5

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 10 additions & 11 deletions main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,16 +1,9 @@
"""FreeWork Data Scraper — CLI entry point.

Usage:
python main.py # Interactive mode
python main.py --url "https://..." # Direct URL mode
streamlit run app.py # Streamlit UI mode
"""

from __future__ import annotations

import argparse
import logging
import sys
import re

from freework_scraper import __version__
from freework_scraper.scraper.browser import BrowserManager
Expand All @@ -28,6 +21,8 @@
)
logger = logging.getLogger("freework")

TRUSTED_DOMAIN = r"^https://www\.free-work\.com/"


def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(
Expand Down Expand Up @@ -78,6 +73,10 @@ def parse_args() -> argparse.Namespace:
return parser.parse_args()


def validate_url(url: str) -> bool:
return re.match(TRUSTED_DOMAIN, url) is not None


def main() -> None:
args = parse_args()

Expand All @@ -86,8 +85,8 @@ def main() -> None:
if not search_url:
search_url = input("Entrez l'URL de recherche FreeWork : ").strip()

if not search_url:
logger.error("Aucune URL fournie. Abandon.")
if not search_url or not validate_url(search_url):
logger.error("URL invalide ou non fournie. Abandon.")
sys.exit(1)

headless = args.headless and not args.no_headless
Expand Down Expand Up @@ -178,4 +177,4 @@ def on_job(idx, total, job):


if __name__ == "__main__":
main()
main()