Skip to content

https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

feat(cli): add batch URL input support (#64)

DyNooob05a8f1f7c180
diff --git a/render/src/pixelrag_render/render.py b/render/src/pixelrag_render/render.py
index ee76afb..62de779 100644
--- a/render/src/pixelrag_render/render.py
+++ b/render/src/pixelrag_render/render.py
@@ -198,8 +198,8 @@ def main() -> None:
# Single URL, default CDP backend
pixelshot https://example.com --output ./tiles
- # Multiple inputs with 4 workers
- pixelshot https://a.com https://b.com --output ./tiles --workers 4
+ # Multiple inputs
+ pixelshot https://a.com https://b.com --output ./tiles
# PDF
pixelshot report.pdf --output ./tiles
@@ -207,8 +207,8 @@ def main() -> None:
# Local HTML
pixelshot index.html --output ./tiles --backend playwright
- # Pipe URLs from a file
- cat urls.txt | xargs pixelshot --output ./tiles --workers 8
+ # URL file
+ pixelshot urls.txt --output ./tiles
# Chrome management (folded from the former `pixelrag-chrome`)
pixelshot install-chrome # download the patched headless Chrome
@@ -311,18 +311,25 @@ def main() -> None:
args = parser.parse_args()
output_dir = Path(args.output)
- # Partition inputs into URLs and files for batch processing
urls = []
files = []
for inp in args.inputs:
- if inp.startswith("http://") or inp.startswith("https://"):
+ if inp.lower().endswith(".txt"):
+ try:
+ with open(inp, encoding="utf-8") as f:
+ for line in f:
+ url = line.strip()
+ if url:
+ urls.append(url)
+ except FileNotFoundError:
+ parser.error(f"URL file not found: {inp}")
+ elif inp.startswith("http://") or inp.startswith("https://"):
urls.append(inp)
else:
files.append(Path(inp))
results: list[Path] = []
- # Batch-render URLs together for efficiency
if urls:
logger.info(
"Rendering %d URL(s) with backend=%s workers=%d",
diff --git a/tests/test_cli.py b/tests/test_cli.py
index 2d32016..72fca9f 100644
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -8,6 +8,8 @@ import subprocess
import sys
from pathlib import Path
+import pytest
+
# Console scripts live next to the interpreter running the tests (works whether
# invoked via `uv run pytest` or `.venv/bin/python -m pytest`).
_BIN = Path(sys.executable).parent
@@ -23,6 +25,57 @@ def test_pixelshot_help():
assert "pixelshot" in r.stdout
+def test_pixelshot_txt_input_uses_batch_render(monkeypatch, tmp_path, capsys):
+ from pixelrag_render import render as render_mod
+
+ urls_file = tmp_path / "urls.txt"
+ urls_file.write_text(
+ "\n https://example.com/a \n\nhttps://example.com/b\nhttps://example.com/c\n"
+ )
+ calls = []
+
+ def fake_render_urls(urls, output_dir, **kwargs):
+ calls.append((list(urls), kwargs["workers"]))
+ return [Path(output_dir) / "a.png.tiles", Path(output_dir) / "c.png.tiles"]
+
+ monkeypatch.setattr(render_mod, "render_urls", fake_render_urls)
+ monkeypatch.setattr(
+ sys,
+ "argv",
+ ["pixelshot", str(urls_file), "-o", str(tmp_path / "out"), "-w", "8"],
+ )
+
+ render_mod.main()
+
+ assert calls == [
+ (
+ [
+ "https://example.com/a",
+ "https://example.com/b",
+ "https://example.com/c",
+ ],
+ 8,
+ )
+ ]
+ stdout = capsys.readouterr().out
+ assert "a.png.tiles" in stdout
+ assert "b.png.tiles" not in stdout
+ assert "c.png.tiles" in stdout
+
+
+def test_pixelshot_missing_txt_input(monkeypatch, tmp_path, capsys):
+ from pixelrag_render import render as render_mod
+
+ missing = tmp_path / "missing.txt"
+ monkeypatch.setattr(sys, "argv", ["pixelshot", str(missing)])
+
+ with pytest.raises(SystemExit) as exc:
+ render_mod.main()
+
+ assert exc.value.code == 2
+ assert "URL file not found" in capsys.readouterr().err
+
+
def test_pixelrag_umbrella_help():
r = _run("pixelrag", "--help")
assert r.returncode == 0