Skip to content

🕵️‍♂️ (2-in-1) Email & Username OSINT suite featuring native MCP support for deep data extraction just from a single Email/Username. Analyzes 2720+ actively maintained scan vectors (210+ email / 2510+ username) for security research, investigations, and digital footprinting.

fix(pdf): route media downloads through configured proxy (#692)

Kaif7a143a12dc45
diff --git a/docs/FLAGS.md b/docs/FLAGS.md
index 4342367..b75d380 100644
--- a/docs/FLAGS.md
+++ b/docs/FLAGS.md
@@ -23,13 +23,14 @@
| `--all` | Show all results including Not Found/Not Registered/Error/Skipped |
| `-m, --module MODULE` | Scan a specific module (comma-separated for multiple); also narrows `--cross-scan` |
| `-p, --permute PERMUTE` | Generate username permutations using a pattern/suffix |
-| `-P, --proxy-file FILE` | Use proxies from file (one per line) |
+| `-P, --proxy-file FILE` | Use proxies from file (one per line). Tip: Combine with `--no-pdf-media` to save proxy bandwidth |
| `--validate-proxies` | Validate proxies before scanning (tests against google.com) |
| `-s, --stop STOP` | Limit the number of permutations generated |
| `-d, --delay DELAY` | Delay (in seconds) between requests |
| `-t, --timeout TIMEOUT` | Override default request timeout in seconds |
| `-C, --concurrency CONC` | Override default concurrency limit |
| `-f, --format {csv,json,pdf}`| Select output format |
+| `--no-pdf-media` | Disable profile photo media fetching in PDF reports (conserves bandwidth on metered proxies) |
| `-o, --output OUTPUT` | Save results to a file (Can be used directly without `-f`) |
| `-U, --update` | Update the tool to the latest version |
| `--version` | Print the current version |
diff --git a/tests/test_pdf_generator.py b/tests/test_pdf_generator.py
index 4836d28..97b2573 100644
--- a/tests/test_pdf_generator.py
+++ b/tests/test_pdf_generator.py
@@ -94,3 +94,91 @@ def test_pdf_no_reportlab_import_error(monkeypatch):
generate_pdf_report("target", "Username", [])
assert "ReportLab is required for PDF generation" in str(exc_info.value)
+
+
+def test_fetch_and_resize_image_routes_through_proxy(monkeypatch):
+ from unittest.mock import MagicMock
+ import httpx
+ import user_scanner.core.pdf_generator as pdf_gen
+ from user_scanner.core.helpers import set_proxy_manager, set_global_timeout
+ from user_scanner.core.pdf_generator import fetch_and_resize_image
+
+ monkeypatch.setattr(pdf_gen, "PIL_AVAILABLE", True)
+ recorded_kwargs = {}
+
+ def mock_get(url, **kwargs):
+ recorded_kwargs.update(kwargs)
+ resp = MagicMock()
+ resp.status_code = 404
+ return resp
+
+ monkeypatch.setattr(httpx, "get", mock_get)
+
+ try:
+ set_proxy_manager(proxies=["http://10.0.0.1:8080"])
+ set_global_timeout(7.5)
+
+ res = fetch_and_resize_image("https://example.com/avatar.png")
+ assert res is None
+ assert recorded_kwargs.get("proxy") == "http://10.0.0.1:8080"
+ assert recorded_kwargs.get("timeout") == 7.5
+ finally:
+ set_proxy_manager(proxies=None)
+ set_global_timeout(None)
+
+
+def test_fetch_and_resize_image_no_proxy(monkeypatch):
+ from unittest.mock import MagicMock
+ import httpx
+ import user_scanner.core.pdf_generator as pdf_gen
+ from user_scanner.core.helpers import set_proxy_manager, set_global_timeout
+ from user_scanner.core.pdf_generator import fetch_and_resize_image
+
+ monkeypatch.setattr(pdf_gen, "PIL_AVAILABLE", True)
+ recorded_kwargs = {}
+
+ def mock_get(url, **kwargs):
+ recorded_kwargs.update(kwargs)
+ resp = MagicMock()
+ resp.status_code = 404
+ return resp
+
+ monkeypatch.setattr(httpx, "get", mock_get)
+
+ set_proxy_manager(proxies=None)
+ set_global_timeout(None)
+
+ res = fetch_and_resize_image("https://example.com/avatar.png")
+ assert res is None
+ assert recorded_kwargs.get("proxy") is None
+ assert recorded_kwargs.get("timeout") == 5.0
+
+
+def test_fetch_and_resize_image_proxy_failure_returns_none(monkeypatch):
+ import httpx
+ import user_scanner.core.pdf_generator as pdf_gen
+ from user_scanner.core.helpers import set_proxy_manager
+ from user_scanner.core.pdf_generator import fetch_and_resize_image
+
+ monkeypatch.setattr(pdf_gen, "PIL_AVAILABLE", True)
+
+ def mock_get(url, **kwargs):
+ raise httpx.ProxyError("Proxy connection refused")
+
+ monkeypatch.setattr(httpx, "get", mock_get)
+
+ try:
+ set_proxy_manager(proxies=["http://10.0.0.1:8080"])
+ res = fetch_and_resize_image("https://example.com/avatar.png")
+ assert res is None
+ finally:
+ set_proxy_manager(proxies=None)
+
+
+def test_fetch_and_resize_image_without_pil_returns_none(monkeypatch):
+ import user_scanner.core.pdf_generator as pdf_gen
+
+ monkeypatch.setattr(pdf_gen, "PIL_AVAILABLE", False)
+ assert pdf_gen.fetch_and_resize_image("https://example.com/avatar.png") is None
+
+
diff --git a/user_scanner/__main__.py b/user_scanner/__main__.py
index 9c99d74..d425e42 100644
--- a/user_scanner/__main__.py
+++ b/user_scanner/__main__.py
@@ -165,7 +165,7 @@ def main():
parser.add_argument(
"--no-pdf-media",
action="store_true",
- help="Disable profile photo media fetching in PDF report generation",
+ help="Disable profile photo media fetching in PDF report generation (useful for metered proxies or saving bandwidth)",
)
parser.add_argument("-o", "--output", type=str, help="Output file path")
@@ -174,7 +174,7 @@ def main():
"-P",
"--proxy-file",
type=str,
- help="Path to proxy list file (one proxy per line)",
+ help="Path to proxy list file (one proxy per line). Tip: use --no-pdf-media to conserve bandwidth on metered proxies",
)
parser.add_argument(
diff --git a/user_scanner/core/pdf_generator.py b/user_scanner/core/pdf_generator.py
index 7ae4edf..c066ea1 100644
--- a/user_scanner/core/pdf_generator.py
+++ b/user_scanner/core/pdf_generator.py
@@ -6,6 +6,7 @@ from datetime import datetime
from typing import List, Any, Optional
import httpx
+from user_scanner.core.helpers import get_global_timeout, get_proxy
try:
from rich.progress import Progress, SpinnerColumn, TextColumn, BarColumn, MofNCompleteColumn # type: ignore[import-untyped,import-not-found]
@@ -65,13 +66,17 @@ def clean_metadata(extra: Any) -> List[tuple]:
def fetch_and_resize_image(url: str, max_size: tuple = (600, 600), timeout: float = 5.0) -> Optional[Any]:
if not PIL_AVAILABLE:
return None
+ global_timeout = get_global_timeout()
+ effective_timeout = global_timeout if global_timeout is not None else timeout
+ proxy = get_proxy()
try:
resp = httpx.get(
url,
headers={
"User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/141.0.0.0 Safari/537.36"
},
- timeout=timeout,
+ proxy=proxy,
+ timeout=effective_timeout,
follow_redirects=True,
)
if resp.status_code == 200: