Add "Tipy dne" folder and fix stale genre folder cleanup

This commit is contained in:
2026-06-29 15:33:44 +02:00
parent a71b209539
commit ee99fc957d
7 changed files with 165 additions and 302 deletions
+15
View File
@@ -21,6 +21,21 @@ Each version entry uses these sections (include only those that apply):
## Unreleased
## 1.6.0 — 2026-06-16
### Added
- Filmotéka generation now also creates a **"Tipy dne"** folder with **10 random
pool movies** (hardlinks; copy-as-is folders like Seriály are excluded). The
folder is refreshed each run (`HardlinkManager.generate_random_tips`).
### Fixed
- Stale **root-level genre folders** were left in the Filmotéka output when the
last movie carrying a genre dropped that tag: obsolete-link cleanup only
scanned genre folders still present on current movies, so an emptied one was
never visited. Cleanup now also sweeps other root-level folders (excluding the
grouping roots and `reserved_subfolders` — copy-as-is mirrors, "Tipy dne") and
removes the now-empty folder. Grouping folders (Dle roku/…) were already fine.
## 1.5.0 — 2026-06-16
### Added
+1 -1
View File
@@ -1,6 +1,6 @@
[project]
name = "curator"
version = "1.5.0"
version = "1.6.0"
description = ""
authors = [
{name = "jan.doubravsky@gmail.com"}
-87
View File
@@ -1,87 +0,0 @@
#!/usr/bin/env python3
"""Minimal PySide6 GUI for filtering magnet lists from ``rargb_magnets.py``.
Just a text box on top and a list below — type to filter live (same syntax as
the CLI: space-separated AND terms, ``-term`` to exclude). Double-click or press
Enter on a row to copy its magnet link to the clipboard.
python tools/filter_magnets_gui.py [files/glob/dir ...]
With no arguments it loads ``magnets_*.txt`` from the current directory. The
loading/filtering logic is reused from ``filter_magnets.py`` in this folder.
"""
from __future__ import annotations
import sys
from pathlib import Path
# Reuse the CLI tool's parsing/filtering (same folder).
sys.path.insert(0, str(Path(__file__).resolve().parent))
from filter_magnets import Entry, load_entries, apply_filter, resolve_inputs # noqa: E402
from PySide6.QtCore import Qt # noqa: E402
from PySide6.QtWidgets import ( # noqa: E402
QApplication, QWidget, QVBoxLayout, QLineEdit, QListWidget, QListWidgetItem,
)
class MagnetFilter(QWidget):
def __init__(self, entries: list[Entry]) -> None:
super().__init__()
self.entries = entries
layout = QVBoxLayout(self)
layout.setContentsMargins(6, 6, 6, 6)
self.search = QLineEdit()
self.search.setPlaceholderText("filtr… (např. 1080p 2022 -hindi) — ↵/dvojklik = kopírovat magnet")
self.search.setClearButtonEnabled(True)
self.search.textChanged.connect(self._refilter)
layout.addWidget(self.search)
self.list = QListWidget()
self.list.itemActivated.connect(self._copy) # Enter / double-click
layout.addWidget(self.list)
self.resize(820, 600)
self._refilter("")
self.search.setFocus()
def _refilter(self, text: str) -> None:
self.list.clear()
for entry in apply_filter(self.entries, text):
short = entry.magnet.split("&", 1)[0] # only the part before the first &
item = QListWidgetItem(f"{entry.name}\n{short}")
item.setData(Qt.UserRole, short)
item.setToolTip(short)
self.list.addItem(item)
self._update_title()
def _copy(self, item: QListWidgetItem) -> None:
QApplication.clipboard().setText(item.data(Qt.UserRole))
self._update_title(copied=item.text())
def _update_title(self, copied: str | None = None) -> None:
base = f"Magnet filtr — {self.list.count()} / {len(self.entries)}"
self.setWindowTitle(f"{base} ✓ zkopírováno" if copied else base)
def main() -> None:
paths = [p for p in resolve_inputs(sys.argv[1:]) if p.exists()]
if not paths:
print("Žádné vstupní soubory (magnets_*.txt) nenalezeny.", file=sys.stderr)
sys.exit(1)
entries = load_entries(paths)
if not entries:
print("Vstupní soubory neobsahují žádné magnet odkazy.", file=sys.stderr)
sys.exit(1)
app = QApplication(sys.argv)
window = MagnetFilter(entries)
window.show()
sys.exit(app.exec())
if __name__ == "__main__":
main()
-196
View File
@@ -1,196 +0,0 @@
#!/usr/bin/env python3
"""Standalone scraper: collect magnet links from a rargb.to search.
Given a search query it walks every results page
(``https://rargb.to/search/?search=<query>`` and ``/search/<N>/?search=<query>``),
opens each torrent's detail page and saves its magnet link.
This is a self-contained tool — it only needs ``requests`` and
``beautifulsoup4`` and does not import anything from the Curator project.
Examples:
python scripts/rargb_magnets.py "ubuntu 24.04"
python scripts/rargb_magnets.py test --output test_magnets.txt --max-pages 3
python scripts/rargb_magnets.py test --tsv # also write name<TAB>magnet
Be considerate: a polite delay is inserted between requests by default. Use the
results responsibly and respect the target site's terms and your local law.
"""
from __future__ import annotations
import re
import sys
import time
import argparse
from pathlib import Path
from urllib.parse import quote, urljoin
import requests
from bs4 import BeautifulSoup
BASE_URL = "https://rargb.to"
HEADERS = {
"User-Agent": (
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 "
"(KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
),
"Accept-Language": "en-US,en;q=0.9",
}
MAGNET_RE = re.compile(r"magnet:\?[^\"'\s<>]+")
def search_page_url(query: str, page: int) -> str:
"""URL of the N-th results page for a query (page 1 has no number)."""
q = quote(query)
if page <= 1:
return f"{BASE_URL}/search/?search={q}"
return f"{BASE_URL}/search/{page}/?search={q}"
def fetch(session: requests.Session, url: str, timeout: float, retries: int) -> str | None:
"""GET ``url`` and return the HTML, or None after exhausting retries."""
for attempt in range(1, retries + 1):
try:
resp = session.get(url, headers=HEADERS, timeout=timeout)
resp.raise_for_status()
return resp.text
except requests.RequestException as exc:
wait = attempt * 2
print(f" ! chyba ({attempt}/{retries}) u {url}: {exc} — čekám {wait}s",
file=sys.stderr)
time.sleep(wait)
return None
def parse_result_links(html: str) -> list[tuple[str, str]]:
"""Return (name, detail_url) for each result row on a search page."""
soup = BeautifulSoup(html, "html.parser")
results: list[tuple[str, str]] = []
seen: set[str] = set()
for row in soup.select("tr.lista2"):
link = row.find("a", href=re.compile(r"^/torrent/"))
if not link:
continue
href = link.get("href")
if not href or href in seen:
continue
seen.add(href)
name = link.get("title") or link.get_text(strip=True) or href
results.append((name.strip(), urljoin(BASE_URL, href)))
return results
def parse_last_page(html: str) -> int:
"""Best-effort highest page number from the pager (1 if none found)."""
pages = [int(n) for n in re.findall(r"/search/(\d+)/\?search=", html)]
return max(pages) if pages else 1
def extract_magnet(html: str) -> str | None:
"""First magnet link found on a torrent detail page, or None."""
match = MAGNET_RE.search(html)
return match.group(0) if match else None
def scrape(query: str, max_pages: int | None, delay: float,
timeout: float, retries: int) -> list[tuple[str, str]]:
"""Walk all result pages and return a de-duplicated [(name, magnet)] list."""
session = requests.Session()
collected: list[tuple[str, str]] = []
seen_magnets: set[str] = set()
seen_details: set[str] = set()
first_html = fetch(session, search_page_url(query, 1), timeout, retries)
if first_html is None:
print("Nepodařilo se načíst první stránku výsledků.", file=sys.stderr)
return collected
last_page = parse_last_page(first_html)
if max_pages is not None:
last_page = min(last_page, max_pages)
print(f"Dotaz: {query!r} — stránek k projití: ~{last_page}")
page = 1
while True:
html = first_html if page == 1 else fetch(
session, search_page_url(query, page), timeout, retries)
if html is None:
break
rows = parse_result_links(html)
new_rows = [(n, u) for n, u in rows if u not in seen_details]
if not new_rows:
# No fresh results → past the last real page; stop.
break
print(f"[strana {page}] nalezeno položek: {len(new_rows)}")
for name, detail_url in new_rows:
seen_details.add(detail_url)
time.sleep(delay)
detail_html = fetch(session, detail_url, timeout, retries)
if detail_html is None:
print(f" - {name}: detail se nenačetl", file=sys.stderr)
continue
magnet = extract_magnet(detail_html)
if not magnet:
print(f" - {name}: magnet nenalezen", file=sys.stderr)
continue
if magnet in seen_magnets:
continue
seen_magnets.add(magnet)
collected.append((name, magnet))
print(f" + {name}")
if max_pages is not None and page >= max_pages:
break
page += 1
if page > last_page:
# Probe one page past the detected last page in case the pager was
# windowed; the empty-results check above will stop us if it's truly
# the end.
last_page = page
time.sleep(delay)
return collected
def main() -> None:
parser = argparse.ArgumentParser(
description="Vyparsuje magnet odkazy z vyhledávání na rargb.to.")
parser.add_argument("query", help="Vyhledávací dotaz (např. \"ubuntu 24.04\")")
parser.add_argument("-o", "--output", type=Path,
help="Výstupní soubor (výchozí: magnets_<dotaz>.txt)")
parser.add_argument("--max-pages", type=int, default=None,
help="Maximální počet stránek (výchozí: všechny)")
parser.add_argument("--delay", type=float, default=1.0,
help="Prodleva mezi requesty v sekundách (výchozí: 1.0)")
parser.add_argument("--timeout", type=float, default=20.0,
help="Timeout requestu v sekundách (výchozí: 20)")
parser.add_argument("--retries", type=int, default=3,
help="Počet pokusů při chybě (výchozí: 3)")
parser.add_argument("--tsv", action="store_true",
help="Uložit i <název>\\t<magnet> vedle čistých magnetů")
args = parser.parse_args()
output = args.output or Path(
f"magnets_{re.sub(r'[^A-Za-z0-9._-]+', '_', args.query).strip('_')}.txt")
results = scrape(args.query, args.max_pages, args.delay, args.timeout, args.retries)
if not results:
print("Nenalezeny žádné magnet odkazy.")
sys.exit(1)
output.write_text("".join(f"{magnet}\n" for _, magnet in results), encoding="utf-8")
print(f"\nUloženo {len(results)} magnet odkazů do: {output}")
if args.tsv:
tsv_path = output.with_suffix(".tsv")
tsv_path.write_text(
"".join(f"{name}\t{magnet}\n" for name, magnet in results), encoding="utf-8")
print(f"Uloženo také název+magnet do: {tsv_path}")
if __name__ == "__main__":
main()
+83 -12
View File
@@ -18,6 +18,7 @@ Example:
└── film.mkv (hardlink)
"""
import os
import random
from pathlib import Path
from typing import List, Tuple, Optional, Dict, Set
from .file import File
@@ -115,25 +116,40 @@ class HardlinkManager:
def _managed_top_dirs(
self, files: List[File], roots: Optional[Dict[str, str]],
transforms: Optional[Dict[str, str]] = None,
reserved_subfolders: Optional[Set[str]] = None,
) -> Optional[Set[str]]:
"""Top-level output folders owned by the tag tree (None = all of them).
For a category with a non-empty root the root folder is owned; for a
category placed at the output root (empty root, e.g. genres) each of its
(transformed) tag values is its own top-level folder. This lets cleanup
skip unrelated root entries such as the copy-as-is mirror (Seriály).
A category with a non-empty root owns that root folder. A category placed
at the output root (empty root, e.g. genres) owns its own folders at the
root — and, so a genre whose last movie dropped the tag still gets its
now-stale folder cleaned, *every* root-level folder is treated as owned
except the grouping roots and any ``reserved_subfolders`` (copy-as-is
mirrors, "Tipy dne", …). The obsolete check still only removes links to
current pool files, so reserved/foreign folders are doubly protected.
"""
if roots is None:
return None
tops: Set[str] = set()
grouping_roots = {folder for folder in roots.values() if folder}
has_root_level = any(not folder for folder in roots.values())
tops: Set[str] = set(grouping_roots)
# genre folders currently present on the movies
for cat, folder in roots.items():
if folder:
tops.add(folder)
else:
if not folder:
for file_obj in files:
for tag in file_obj.tags:
if tag.category == cat:
tops.add(self._folder_value(tag, transforms))
# plus any other root-level folder (catches genres that lost their last
# movie), minus grouping roots and reserved (mirrors / Tipy dne / …)
if has_root_level and self.output_dir.exists():
reserved = set(reserved_subfolders or set())
for entry in self.output_dir.iterdir():
if (entry.is_dir() and entry.name not in grouping_roots
and entry.name not in reserved):
tops.add(entry.name)
return tops
def create_structure_for_files(
@@ -258,6 +274,53 @@ class HardlinkManager:
return success_count, fail_count
def generate_random_tips(
self,
files: List[File],
count: int = 10,
subfolder: str = "Tipy dne",
dry_run: bool = False,
) -> Tuple[int, int]:
"""(Re)fill ``subfolder`` with ``count`` random files as hardlinks.
The folder is emptied first so each run picks a fresh random selection.
``files`` should be the pool movies only (copy-as-is mirrors excluded).
Returns:
Tuple of (created_links, failed_links)
"""
base = self.output_dir / subfolder
if not dry_run and base.exists():
for child in base.iterdir():
if child.is_file():
try:
child.unlink()
except OSError:
pass
chosen = random.sample(files, min(count, len(files)))
created = 0
fail = 0
for file_obj in chosen:
target = base / file_obj.filename
try:
if not dry_run:
base.mkdir(parents=True, exist_ok=True)
if target.exists():
if self._is_same_file(file_obj.file_path, target):
created += 1
continue
target = self._get_unique_name(target)
os.link(file_obj.file_path, target)
self.created_links.append(target)
created += 1
except OSError as e:
self.errors.append((file_obj.file_path, str(e)))
fail += 1
return created, fail
def _is_same_file(self, path1: Path, path2: Path) -> bool:
"""Check if two paths point to the same file (same inode)."""
try:
@@ -359,6 +422,7 @@ class HardlinkManager:
category_roots: Optional[Dict[str, str]] = None,
category_transforms: Optional[Dict[str, str]] = None,
category_filename_templates: Optional[Dict[str, str]] = None,
reserved_subfolders: Optional[Set[str]] = None,
) -> List[Tuple[Path, Path]]:
"""
Find hardlinks in the output directory that no longer match file tags.
@@ -411,7 +475,8 @@ class HardlinkManager:
continue
# Scan only the tag-tree's own top-level folders (skip copy-as-is mirrors)
top_dirs = self._managed_top_dirs(files, roots, category_transforms)
top_dirs = self._managed_top_dirs(
files, roots, category_transforms, reserved_subfolders)
for top in self.output_dir.iterdir():
if not top.is_dir():
continue
@@ -441,6 +506,7 @@ class HardlinkManager:
category_roots: Optional[Dict[str, str]] = None,
category_transforms: Optional[Dict[str, str]] = None,
category_filename_templates: Optional[Dict[str, str]] = None,
reserved_subfolders: Optional[Set[str]] = None,
) -> Tuple[int, List[Path]]:
"""
Remove hardlinks that no longer match file tags.
@@ -453,13 +519,15 @@ class HardlinkManager:
``categories`` when given).
category_transforms: Optional category → transform-name map for folders.
category_filename_templates: Optional category → hardlink-name template.
reserved_subfolders: Output top-level folders to never touch (mirrors,
"Tipy dne", …).
Returns:
Tuple of (removed_count, list_of_removed_paths)
"""
obsolete = self.find_obsolete_links(
files, categories, category_roots, category_transforms,
category_filename_templates)
category_filename_templates, reserved_subfolders)
removed_paths = []
if dry_run:
@@ -485,6 +553,7 @@ class HardlinkManager:
category_roots: Optional[Dict[str, str]] = None,
category_transforms: Optional[Dict[str, str]] = None,
category_filename_templates: Optional[Dict[str, str]] = None,
reserved_subfolders: Optional[Set[str]] = None,
) -> Tuple[int, int, int, int]:
"""
Synchronize hardlink structure with current file tags.
@@ -501,6 +570,8 @@ class HardlinkManager:
``categories`` when given).
category_transforms: Optional category → transform-name map for folders.
category_filename_templates: Optional category → hardlink-name template.
reserved_subfolders: Output top-level folders to never touch (mirrors,
"Tipy dne", …).
Returns:
Tuple of (created, create_failed, removed, remove_failed)
@@ -508,12 +579,12 @@ class HardlinkManager:
# First find how many obsolete links there are
obsolete_count = len(self.find_obsolete_links(
files, categories, category_roots, category_transforms,
category_filename_templates))
category_filename_templates, reserved_subfolders))
# Remove obsolete links
removed, removed_paths = self.remove_obsolete_links(
files, categories, dry_run, category_roots, category_transforms,
category_filename_templates
category_filename_templates, reserved_subfolders
)
remove_failed = obsolete_count - removed if not dry_run else 0
+11 -4
View File
@@ -957,12 +957,14 @@ class QtApp(QMainWindow):
QMessageBox.information(self, "Filmotéka", "Pool je prázdný.")
return
manager = HardlinkManager(out)
reserved = set(self.filehandler.copyasis_folders) | {"Tipy dne"}
created, create_fail, removed, remove_fail = manager.sync_structure(
files,
category_roots=self.filehandler.filmoteka_category_roots(),
category_transforms=self.filehandler.filmoteka_category_transforms(),
category_filename_templates=(
self.filehandler.filmoteka_category_filename_templates()),
reserved_subfolders=reserved,
)
# Copy-as-is folders (e.g. Seriály): mirror each 1:1 (hardlinked)
@@ -976,17 +978,22 @@ class QtApp(QMainWindow):
mirrored += m_created
mirror_fail += m_failed
# "Tipy dne": 10 random pool movies (copy-as-is folders excluded)
tips, tips_fail = manager.generate_random_tips(files, count=10)
msg = (
f"Filmy — vytvořeno: {created}, odebráno zastaralých: {removed}\n"
f"Copy-as-is — zrcadleno: {mirrored}"
f"Copy-as-is — zrcadleno: {mirrored}\n"
f"Tipy dne — náhodně: {tips}"
)
if create_fail or remove_fail or mirror_fail:
msg += f"\nSelhalo: {create_fail + remove_fail + mirror_fail}"
if create_fail or remove_fail or mirror_fail or tips_fail:
msg += f"\nSelhalo: {create_fail + remove_fail + mirror_fail + tips_fail}"
QMessageBox.warning(self, "Filmotéka dokončena s chybami", msg)
else:
QMessageBox.information(self, "Filmotéka vygenerována", msg)
self.status.showMessage(
f"Filmotéka: filmy +{created}/-{removed}, copy-as-is +{mirrored}", 5000
f"Filmotéka: filmy +{created}/-{removed}, copy-as-is +{mirrored}, "
f"tipy +{tips}", 5000
)
def edit_copyasis_folders(self) -> None:
+55 -2
View File
@@ -136,11 +136,30 @@ class TestHardlinkManager:
mirror_link = mirror / "file1.txt"
os.link(temp_source_dir / "file1.txt", mirror_link)
manager.sync_structure(files_with_tags, category_roots=roots)
manager.sync_structure(
files_with_tags, category_roots=roots,
reserved_subfolders={"Seriály"})
# The mirror (not a managed tag folder) is left alone
# The mirror (reserved folder) is left alone
assert mirror_link.exists()
def test_sync_removes_root_genre_folder_when_last_movie_drops_tag(
self, temp_source_dir, temp_output_dir, tag_manager
):
"""A genre folder at the output root is cleaned when no movie has it."""
f = File(temp_source_dir / "file1.txt", tag_manager)
f.tags.clear()
f.add_tag(Tag("žánr", "Akční"))
roots = {"žánr": ""}
manager = HardlinkManager(temp_output_dir)
manager.sync_structure([f], category_roots=roots)
assert (temp_output_dir / "Akční").is_dir()
# last movie with the tag loses it → folder must go
f.tags.clear()
manager.sync_structure([f], category_roots=roots)
assert not (temp_output_dir / "Akční").exists()
def test_category_transform_groups_folder_by_band(
self, temp_source_dir, temp_output_dir, tag_manager
):
@@ -202,6 +221,40 @@ class TestHardlinkManager:
assert [p.name for p in folder.iterdir()] == ["1962 - Dr. No.txt"]
assert removed == 0 # nothing treated as obsolete on the second run
def test_generate_random_tips_creates_hardlinks(
self, files_with_tags, temp_output_dir
):
"""Tips folder gets `count` random pool files as hardlinks."""
manager = HardlinkManager(temp_output_dir)
created, fail = manager.generate_random_tips(files_with_tags, count=2)
tips = temp_output_dir / "Tipy dne"
assert created == 2
assert fail == 0
links = sorted(p.name for p in tips.iterdir())
assert len(links) == 2
# each is a hardlink to one of the source files
srcs = {f.filename for f in files_with_tags}
assert set(links) <= srcs
def test_generate_random_tips_caps_at_available(
self, files_with_tags, temp_output_dir
):
"""Asking for more than available yields all of them, no error."""
manager = HardlinkManager(temp_output_dir)
created, _ = manager.generate_random_tips(files_with_tags, count=99)
assert created == len(files_with_tags)
def test_generate_random_tips_refreshes_each_run(
self, files_with_tags, temp_output_dir
):
"""A second run replaces the previous selection (folder is emptied)."""
manager = HardlinkManager(temp_output_dir)
manager.generate_random_tips(files_with_tags, count=1)
manager.generate_random_tips(files_with_tags, count=1)
tips = temp_output_dir / "Tipy dne"
assert len(list(tips.iterdir())) == 1 # not accumulated to 2
def test_dry_run(self, files_with_tags, temp_output_dir):
"""Test dry run (bez skutečného vytváření)"""
manager = HardlinkManager(temp_output_dir)