HugeFrog24/jailbirdz-dl
1
0
Fork 0
mirror of https://github.com/HugeFrog24/jailbirdz-dl.git synced 2026-03-02 09:04:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

Cookie validation logic

Browse Source
This commit is contained in:
HugeFrog24
2026-02-28 21:37:39 +01:00
parent 80444405e9
commit e3e14293cd
15 changed files with 802 additions and 398 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
.env.example
View File

@@ -1,7 +1,12 @@
# Copy your wordpress_logged_in_... cookie from browser DevTools → Storage → Cookies. # Login credentials for grab_cookie.py (recommended)
# Paste the full name=value pair below. # These are used to obtain a fresh WP_LOGIN_COOKIE via the WooCommerce AJAX endpoint.
# wordpress_sec_... is the wp-admin cookie — irrelevant for read-only viewers. WP_USERNAME=your-email-or-username
# __cf_bm is a Cloudflare bot-management cookie — also not needed. WP_PASSWORD=your-password
# Alternatively, set WP_LOGIN_COOKIE manually (expires in ~2 weeks).
# Get it from browser DevTools → Storage → Cookies while on jailbirdz.com.
# Copy the full name=value of the wordpress_logged_in_* cookie.
# wordpress_sec_... is the wp-admin cookie — not needed.
WP_LOGIN_COOKIE=wordpress_logged_in_<hash>=<value> WP_LOGIN_COOKIE=wordpress_logged_in_<hash>=<value>
# PeerTube upload target # PeerTube upload target

47
.github/workflows/nightly-index.yml vendored Normal file
View File

@@ -0,0 +1,47 @@
name: Nightly Index
on:
schedule:
- cron: '0 3 * * *' # 03:00 UTC daily
workflow_dispatch: # manual trigger via GitHub UI
permissions:
contents: write # needed to push video_map.json back
concurrency:
group: nightly-index
cancel-in-progress: false # let an in-progress scrape finish; queue the next run
jobs:
index:
runs-on: ubuntu-latest
timeout-minutes: 300 # 5 h ceiling; scraper resumes where it left off on next run
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v5
with:
python-version: '3.12'
cache: pip
- name: Install dependencies
run: pip install -r requirements.txt
- name: Install Playwright Firefox
run: playwright install firefox --with-deps
- name: Run scraper
run: python main.py
env:
WP_USERNAME: ${{ secrets.WP_USERNAME }}
WP_PASSWORD: ${{ secrets.WP_PASSWORD }}
- name: Commit updated video_map.json
if: always() # save progress even if main.py crashed or timed out
run: |
git config user.name "github-actions[bot]"
git config user.email "github-actions[bot]@users.noreply.github.com"
git add video_map.json
git diff --staged --quiet || git commit -m "chore: nightly index update [skip ci]"
git push

9
.gitignore vendored
View File

@@ -1,5 +1,14 @@
# Temporary cache
__pycache__/ __pycache__/
.ruff_cache/
# Local IDE config
.vscode
# Project output & artifacts
downloads/ downloads/
*.mp4 *.mp4
*.mp4.part *.mp4.part
# Secrets & sensitive info
.env .env

4
.vscode/settings.json vendored
View File

@@ -1,4 +0,0 @@
{
"snyk.advanced.organization": "512ef4a1-6034-4537-a391-9692d282122a",
"snyk.advanced.autoSelectOrganization": true
}

32
README.md
View File

@@ -21,21 +21,14 @@ cp .env.example .env
### WP_LOGIN_COOKIE ### WP_LOGIN_COOKIE
You need to be logged into jailbirdz.com in a browser. Then either: **Option A — credentials (recommended):** set `WP_USERNAME` and `WP_PASSWORD` in `.env`. `main.py` logs in automatically on startup — no separate step needed.
**Option A — auto (recommended):** let `grab_cookie.py` read it from your browser and write it to `.env` automatically:
```bash
python grab_cookie.py # tries Firefox, Chrome, Edge, Brave in order
python grab_cookie.py -b firefox # or target a specific browser
```
> **Note:** Chrome and Edge on Windows 130+ require the script to run as Administrator due to App-bound Encryption. Firefox works without elevated privileges.
**Option B — manual:** open `.env` and set `WP_LOGIN_COOKIE` yourself. Get the value from browser DevTools → Storage → Cookies while on jailbirdz.com — copy the full `name=value` of the `wordpress_logged_in_*` cookie. **Option B — manual:** open `.env` and set `WP_LOGIN_COOKIE` yourself. Get the value from browser DevTools → Storage → Cookies while on jailbirdz.com — copy the full `name=value` of the `wordpress_logged_in_*` cookie.
### Other `.env` values ### Other `.env` values
- `WP_USERNAME` — jailbirdz.com login (email or username).
- `WP_PASSWORD` — jailbirdz.com password.
- `PEERTUBE_URL` — base URL of your PeerTube instance. - `PEERTUBE_URL` — base URL of your PeerTube instance.
- `PEERTUBE_USER` — PeerTube username. - `PEERTUBE_USER` — PeerTube username.
- `PEERTUBE_CHANNEL` — channel to upload to. - `PEERTUBE_CHANNEL` — channel to upload to.
@@ -89,6 +82,25 @@ Options:
Uploads in resumable 10 MB chunks. After each batch, waits for transcoding and object storage to complete before uploading the next batch — this prevents disk exhaustion on the PeerTube server. Videos already present on the channel (matched by name) are skipped. Progress is tracked in `.uploaded` inside the input directory. Uploads in resumable 10 MB chunks. After each batch, waits for transcoding and object storage to complete before uploading the next batch — this prevents disk exhaustion on the PeerTube server. Videos already present on the channel (matched by name) are skipped. Progress is tracked in `.uploaded` inside the input directory.
## CI / Nightly Indexing
`.github/workflows/nightly-index.yml` runs `main.py` at 03:00 UTC daily and commits any new `video_map.json` entries back to the repo.
**One-time setup — add repo secrets:**
```bash
gh secret set WP_USERNAME
gh secret set WP_PASSWORD
```
**Seed CI with your current progress before the first run:**
```bash
git add video_map.json && git commit -m "chore: seed video_map"
```
**Trigger manually:** Actions → Nightly Index → Run workflow.
## Utilities ## Utilities
### Check for filename clashes ### Check for filename clashes

82
check_clashes.py
View File

@@ -9,38 +9,58 @@ Importable functions:
fetch_sizes(urls, workers, on_progress) - bulk size lookup fetch_sizes(urls, workers, on_progress) - bulk size lookup
make_session() - requests.Session with required headers make_session() - requests.Session with required headers
load_video_map() - load video_map.json, returns {} on missing/corrupt load_video_map() - load video_map.json, returns {} on missing/corrupt
is_valid_url(url) - True if url is a plain http(s) URL with no HTML artefacts
expects_video(url) - True if url is a members-only video page
""" """
from collections import defaultdict from collections import defaultdict
from concurrent.futures import ThreadPoolExecutor, as_completed from concurrent.futures import ThreadPoolExecutor, as_completed
from pathlib import Path, PurePosixPath from pathlib import Path, PurePosixPath
from typing import Any, Callable, Optional, cast
from urllib.parse import urlparse, unquote from urllib.parse import urlparse, unquote
import json import json
import requests import requests
from config import BASE_URL from config import BASE_URL
REFERER = f"{BASE_URL}/" REFERER: str = f"{BASE_URL}/"
VIDEO_MAP_FILE = "video_map.json" VIDEO_MAP_FILE: str = "video_map.json"
VIDEO_EXTS = {".mp4", ".mov", ".m4v", ".webm", ".avi"} VIDEO_EXTS: set[str] = {".mp4", ".mov", ".m4v", ".webm", ".avi"}
def load_video_map(): def is_valid_url(url: str) -> bool:
"""True if url is a plain http(s) URL with no HTML artefacts (<, >, href= etc.)."""
return (
url.startswith("http")
and "<" not in url
and ">" not in url
and " href=" not in url
)
def expects_video(url: str) -> bool:
"""True if url is a members-only video page that should contain a video."""
return "/pinkcuffs-videos/" in url
def load_video_map() -> dict[str, Any]:
if Path(VIDEO_MAP_FILE).exists(): if Path(VIDEO_MAP_FILE).exists():
try: try:
with open(VIDEO_MAP_FILE, encoding="utf-8") as f: with open(VIDEO_MAP_FILE, encoding="utf-8") as f:
return json.load(f) data_any: Any = json.load(f)
data = cast(dict[str, Any], data_any)
return data
except (json.JSONDecodeError, OSError): except (json.JSONDecodeError, OSError):
return {} return {}
return {} return {}
def make_session(): def make_session() -> requests.Session:
s = requests.Session() s = requests.Session()
s.headers.update({"Referer": REFERER}) s.headers.update({"Referer": REFERER})
return s return s
def fmt_size(b): def fmt_size(b: float | int) -> str:
for unit in ("B", "KB", "MB", "GB"): for unit in ("B", "KB", "MB", "GB"):
if b < 1024: if b < 1024:
return f"{b:.1f} {unit}" return f"{b:.1f} {unit}"
@@ -48,30 +68,34 @@ def fmt_size(b):
return f"{b:.1f} TB" return f"{b:.1f} TB"
def url_to_filename(url): def url_to_filename(url: str) -> str:
return unquote(PurePosixPath(urlparse(url).path).name) return unquote(PurePosixPath(urlparse(url).path).name)
def find_clashes(urls): def find_clashes(urls: list[str]) -> dict[str, list[str]]:
# Case-insensitive grouping so that e.g. "DaisyArrest.mp4" and # Case-insensitive grouping so that e.g. "DaisyArrest.mp4" and
# "daisyarrest.mp4" are treated as a clash. This is required for # "daisyarrest.mp4" are treated as a clash. This is required for
# correctness on case-insensitive filesystems (NTFS, exFAT, macOS HFS+) # correctness on case-insensitive filesystems (NTFS, exFAT, macOS HFS+)
# and harmless on case-sensitive ones (ext4) — the actual filenames on # and harmless on case-sensitive ones (ext4) — the actual filenames on
# disk keep their original casing; only the clash *detection* is folded. # disk keep their original casing; only the clash *detection* is folded.
by_lower = defaultdict(list) by_lower: defaultdict[str, list[str]] = defaultdict(list)
for url in urls: for url in urls:
by_lower[url_to_filename(url).lower()].append(url) by_lower[url_to_filename(url).lower()].append(url)
return {url_to_filename(srcs[0]): srcs return {
for srcs in by_lower.values() if len(srcs) > 1} url_to_filename(srcs[0]): srcs for srcs in by_lower.values() if len(srcs) > 1
}
def _clash_subfolder(url): def _clash_subfolder(url: str) -> str:
"""Parent path segment used as disambiguator for clashing filenames.""" """Parent path segment used as disambiguator for clashing filenames."""
parts = urlparse(url).path.rstrip("/").split("/") parts = urlparse(url).path.rstrip("/").split("/")
return unquote(parts[-2]) if len(parts) >= 2 else "unknown" return unquote(parts[-2]) if len(parts) >= 2 else "unknown"
def build_download_paths(urls, output_dir): def build_download_paths(
urls: list[str],
output_dir: str | Path,
) -> dict[str, Path]:
"""Map each URL to a local file path. Flat layout; clashing names get a subfolder.""" """Map each URL to a local file path. Flat layout; clashing names get a subfolder."""
clashes = find_clashes(urls) clashes = find_clashes(urls)
clash_lower = {name.lower() for name in clashes} clash_lower = {name.lower() for name in clashes}
@@ -86,7 +110,10 @@ def build_download_paths(urls, output_dir):
return paths return paths
def get_remote_size(session, url): def get_remote_size(
session: requests.Session,
url: str,
) -> Optional[int]:
try: try:
r = session.head(url, allow_redirects=True, timeout=15) r = session.head(url, allow_redirects=True, timeout=15)
if r.status_code < 400 and "Content-Length" in r.headers: if r.status_code < 400 and "Content-Length" in r.headers:
@@ -94,8 +121,7 @@ def get_remote_size(session, url):
except Exception: except Exception:
pass pass
try: try:
r = session.get( r = session.get(url, headers={"Range": "bytes=0-0"}, stream=True, timeout=15)
url, headers={"Range": "bytes=0-0"}, stream=True, timeout=15)
r.close() r.close()
cr = r.headers.get("Content-Range", "") cr = r.headers.get("Content-Range", "")
if "/" in cr: if "/" in cr:
@@ -105,10 +131,14 @@ def get_remote_size(session, url):
return None return None
def fetch_sizes(urls, workers=20, on_progress=None): def fetch_sizes(
urls: list[str],
workers: int = 20,
on_progress: Optional[Callable[[int, int], None]] = None,
) -> dict[str, Optional[int]]:
"""Return {url: size_or_None}. on_progress(done, total) called after each URL.""" """Return {url: size_or_None}. on_progress(done, total) called after each URL."""
session = make_session() session = make_session()
sizes = {} sizes: dict[str, Optional[int]] = {}
total = len(urls) total = len(urls)
with ThreadPoolExecutor(max_workers=workers) as pool: with ThreadPoolExecutor(max_workers=workers) as pool:
@@ -117,7 +147,7 @@ def fetch_sizes(urls, workers=20, on_progress=None):
for fut in as_completed(futures): for fut in as_completed(futures):
sizes[futures[fut]] = fut.result() sizes[futures[fut]] = fut.result()
done += 1 done += 1
if on_progress: if on_progress is not None:
on_progress(done, total) on_progress(done, total)
return sizes return sizes
@@ -125,14 +155,20 @@ def fetch_sizes(urls, workers=20, on_progress=None):
# --------------- CLI --------------- # --------------- CLI ---------------
def main():
def main() -> None:
vm = load_video_map() vm = load_video_map()
urls = [u for entry in vm.values() for u in entry.get("videos", []) if u.startswith("http")] urls = [
u
for entry in vm.values()
for u in entry.get("videos", [])
if u.startswith("http")
]
clashes = find_clashes(urls) clashes = find_clashes(urls)
print(f"Total URLs: {len(urls)}") print(f"Total URLs: {len(urls)}")
by_name = defaultdict(list) by_name: defaultdict[str, list[str]] = defaultdict(list)
for url in urls: for url in urls:
by_name[url_to_filename(url)].append(url) by_name[url_to_filename(url)].append(url)
print(f"Unique filenames: {len(by_name)}") print(f"Unique filenames: {len(by_name)}")

7
config.py
View File

@@ -1,2 +1,5 @@
BASE_URL = "https://www.jailbirdz.com" # config.py
COOKIE_DOMAIN = "jailbirdz.com" # rookiepy domain filter (no www) from typing import Final
BASE_URL: Final[str] = "https://www.jailbirdz.com"
COOKIE_DOMAIN: Final[str] = "jailbirdz.com" # rookiepy domain filter (no www)

0
openapi.json → docs/external/peertube/openapi.json vendored
View File

167
download.py
View File

@@ -17,6 +17,8 @@ import re
import shutil import shutil
from collections import defaultdict from collections import defaultdict
from concurrent.futures import ThreadPoolExecutor, as_completed from concurrent.futures import ThreadPoolExecutor, as_completed
from typing import Any, Optional
import requests
from check_clashes import ( from check_clashes import (
make_session, make_session,
@@ -25,32 +27,35 @@ from check_clashes import (
find_clashes, find_clashes,
build_download_paths, build_download_paths,
fetch_sizes, fetch_sizes,
load_video_map,
is_valid_url,
VIDEO_MAP_FILE,
) )
VIDEO_MAP_FILE = "video_map.json"
CHUNK_SIZE = 8 * 1024 * 1024 CHUNK_SIZE = 8 * 1024 * 1024
DEFAULT_OUTPUT = "downloads" DEFAULT_OUTPUT: str = "downloads"
DEFAULT_WORKERS = 4 DEFAULT_WORKERS: int = 4
MODE_FILE = ".naming_mode" MODE_FILE: str = ".naming_mode"
MODE_ORIGINAL = "original" MODE_ORIGINAL: str = "original"
MODE_TITLE = "title" MODE_TITLE: str = "title"
# ── Naming mode persistence ────────────────────────────────────────── # ── Naming mode persistence ──────────────────────────────────────────
def read_mode(output_dir):
def read_mode(output_dir: str | Path) -> Optional[str]:
p = Path(output_dir) / MODE_FILE p = Path(output_dir) / MODE_FILE
if p.exists(): if p.exists():
return p.read_text().strip() return p.read_text().strip()
return None return None
def write_mode(output_dir, mode): def write_mode(output_dir: str | Path, mode: str) -> None:
Path(output_dir).mkdir(parents=True, exist_ok=True) Path(output_dir).mkdir(parents=True, exist_ok=True)
(Path(output_dir) / MODE_FILE).write_text(mode) (Path(output_dir) / MODE_FILE).write_text(mode)
def resolve_mode(args): def resolve_mode(args: argparse.Namespace) -> str:
"""Determine naming mode from CLI flags + saved marker. Returns mode string.""" """Determine naming mode from CLI flags + saved marker. Returns mode string."""
saved = read_mode(args.output) saved = read_mode(args.output)
@@ -69,13 +74,18 @@ def resolve_mode(args):
# ── Filename helpers ───────────────────────────────────────────────── # ── Filename helpers ─────────────────────────────────────────────────
def sanitize_filename(title, max_len=180):
name = re.sub(r'[<>:"/\\|?*]', '', title) def sanitize_filename(title: str, max_len: int = 180) -> str:
name = re.sub(r'\s+', ' ', name).strip().rstrip('.') name = re.sub(r'[<>:"/\\|?*]', "", title)
name = re.sub(r"\s+", " ", name).strip().rstrip(".")
return name[:max_len].rstrip() if len(name) > max_len else name return name[:max_len].rstrip() if len(name) > max_len else name
def build_title_paths(urls, url_to_title, output_dir): def build_title_paths(
urls: list[str],
url_to_title: dict[str, str],
output_dir: str | Path,
) -> dict[str, Path]:
name_to_urls = defaultdict(list) name_to_urls = defaultdict(list)
url_to_base = {} url_to_base = {}
@@ -91,14 +101,19 @@ def build_title_paths(urls, url_to_title, output_dir):
base, ext = url_to_base[url] base, ext = url_to_base[url]
full = base + ext full = base + ext
if len(name_to_urls[full]) > 1: if len(name_to_urls[full]) > 1:
slug = url_to_filename(url).rsplit('.', 1)[0] slug = url_to_filename(url).rsplit(".", 1)[0]
paths[url] = Path(output_dir) / f"{base} [{slug}]{ext}" paths[url] = Path(output_dir) / f"{base} [{slug}]{ext}"
else: else:
paths[url] = Path(output_dir) / full paths[url] = Path(output_dir) / full
return paths return paths
def get_paths_for_mode(mode, urls, video_map, output_dir): def get_paths_for_mode(
mode: str,
urls: list[str],
video_map: dict[str, Any],
output_dir: str | Path,
) -> dict[str, Path]:
if mode == MODE_TITLE: if mode == MODE_TITLE:
url_title = build_url_title_map(video_map) url_title = build_url_title_map(video_map)
return build_title_paths(urls, url_title, output_dir) return build_title_paths(urls, url_title, output_dir)
@@ -107,7 +122,14 @@ def get_paths_for_mode(mode, urls, video_map, output_dir):
# ── Reorganize ─────────────────────────────────────────────────────── # ── Reorganize ───────────────────────────────────────────────────────
def reorganize(urls, video_map, output_dir, target_mode, dry_run=False):
def reorganize(
urls: list[str],
video_map: dict[str, Any],
output_dir: str | Path,
target_mode: str,
dry_run: bool = False,
) -> None:
"""Rename existing files from one naming scheme to another.""" """Rename existing files from one naming scheme to another."""
other_mode = MODE_TITLE if target_mode == MODE_ORIGINAL else MODE_ORIGINAL other_mode = MODE_TITLE if target_mode == MODE_ORIGINAL else MODE_ORIGINAL
old_paths = get_paths_for_mode(other_mode, urls, video_map, output_dir) old_paths = get_paths_for_mode(other_mode, urls, video_map, output_dir)
@@ -163,21 +185,27 @@ def reorganize(urls, video_map, output_dir, target_mode, dry_run=False):
# ── Download ───────────────────────────────────────────────────────── # ── Download ─────────────────────────────────────────────────────────
def download_one(session, url, dest, expected_size):
def download_one(
session: requests.Session,
url: str,
dest: str | Path,
expected_size: Optional[int],
) -> tuple[str, int]:
dest = Path(dest) dest = Path(dest)
part = dest.parent / (dest.name + ".part") part = dest.parent / (dest.name + ".part")
dest.parent.mkdir(parents=True, exist_ok=True) dest.parent.mkdir(parents=True, exist_ok=True)
if dest.exists(): if dest.exists():
local = dest.stat().st_size local = dest.stat().st_size
if expected_size and local == expected_size: if expected_size is not None and local == expected_size:
return "ok", 0 return "ok", 0
if expected_size and local != expected_size: if expected_size is not None and local != expected_size:
dest.unlink() dest.unlink()
existing = part.stat().st_size if part.exists() else 0 existing = part.stat().st_size if part.exists() else 0
headers = {} headers = {}
if existing and expected_size and existing < expected_size: if existing and expected_size is not None and existing < expected_size:
headers["Range"] = f"bytes={existing}-" headers["Range"] = f"bytes={existing}-"
try: try:
@@ -205,33 +233,21 @@ def download_one(session, url, dest, expected_size):
return f"error: {e}", written return f"error: {e}", written
final_size = existing + written final_size = existing + written
if expected_size and final_size != expected_size: if expected_size is not None and final_size != expected_size:
return "size_mismatch", written return "size_mismatch", written
part.rename(dest) part.rename(dest)
return "ok", written return "ok", written
# ── Data loading ───────────────────────────────────────────────────── def collect_urls(video_map: dict[str, Any]) -> list[str]:
def load_video_map():
with open(VIDEO_MAP_FILE, encoding="utf-8") as f:
return json.load(f)
def _is_valid_url(url):
return url.startswith(
"http") and "<" not in url and ">" not in url and " href=" not in url
def collect_urls(video_map):
urls, seen, skipped = [], set(), 0 urls, seen, skipped = [], set(), 0
for entry in video_map.values(): for entry in video_map.values():
for video_url in entry.get("videos", []): for video_url in entry.get("videos", []):
if video_url in seen: if video_url in seen:
continue continue
seen.add(video_url) seen.add(video_url)
if _is_valid_url(video_url): if is_valid_url(video_url):
urls.append(video_url) urls.append(video_url)
else: else:
skipped += 1 skipped += 1
@@ -240,7 +256,7 @@ def collect_urls(video_map):
return urls return urls
def build_url_title_map(video_map): def build_url_title_map(video_map: dict[str, Any]) -> dict[str, str]:
url_title = {} url_title = {}
for entry in video_map.values(): for entry in video_map.values():
title = entry.get("title", "") title = entry.get("title", "")
@@ -252,24 +268,44 @@ def build_url_title_map(video_map):
# ── Main ───────────────────────────────────────────────────────────── # ── Main ─────────────────────────────────────────────────────────────
def main():
parser = argparse.ArgumentParser( def main() -> None:
description="Download videos from video_map.json") parser = argparse.ArgumentParser(description="Download videos from video_map.json")
parser.add_argument("--output", "-o", default=DEFAULT_OUTPUT, parser.add_argument(
help=f"Download directory (default: {DEFAULT_OUTPUT})") "--output",
"-o",
default=DEFAULT_OUTPUT,
help=f"Download directory (default: {DEFAULT_OUTPUT})",
)
naming = parser.add_mutually_exclusive_group() naming = parser.add_mutually_exclusive_group()
naming.add_argument("--titles", "-t", action="store_true", naming.add_argument(
help="Use title-based filenames (saved as default for this directory)") "--titles",
naming.add_argument("--original", action="store_true", "-t",
help="Use original CloudFront filenames (saved as default for this directory)") action="store_true",
help="Use title-based filenames (saved as default for this directory)",
)
naming.add_argument(
"--original",
action="store_true",
help="Use original CloudFront filenames (saved as default for this directory)",
)
parser.add_argument("--reorganize", action="store_true", parser.add_argument(
help="Rename existing files to match the current naming mode") "--reorganize",
parser.add_argument("--dry-run", "-n", action="store_true", action="store_true",
help="Preview without making changes") help="Rename existing files to match the current naming mode",
parser.add_argument("--workers", "-w", type=int, default=DEFAULT_WORKERS, )
help=f"Concurrent downloads (default: {DEFAULT_WORKERS})") parser.add_argument(
"--dry-run", "-n", action="store_true", help="Preview without making changes"
)
parser.add_argument(
"--workers",
"-w",
type=int,
default=DEFAULT_WORKERS,
help=f"Concurrent downloads (default: {DEFAULT_WORKERS})",
)
args = parser.parse_args() args = parser.parse_args()
video_map = load_video_map() video_map = load_video_map()
@@ -287,7 +323,8 @@ def main():
if mode_changed and not args.reorganize: if mode_changed and not args.reorganize:
print(f"\n[!] Mode changed from '{saved}' to '{mode}'.") print(f"\n[!] Mode changed from '{saved}' to '{mode}'.")
print( print(
" Use --reorganize to rename existing files, or --dry-run to preview.") " Use --reorganize to rename existing files, or --dry-run to preview."
)
print(" Refusing to download until existing files are reorganized.") print(" Refusing to download until existing files are reorganized.")
return return
reorganize(urls, video_map, args.output, mode, dry_run=args.dry_run) reorganize(urls, video_map, args.output, mode, dry_run=args.dry_run)
@@ -303,7 +340,8 @@ def main():
clashes = find_clashes(urls) clashes = find_clashes(urls)
if clashes: if clashes:
print( print(
f"[+] {len(clashes)} filename clash(es) resolved with subfolders/suffixes") f"[+] {len(clashes)} filename clash(es) resolved with subfolders/suffixes"
)
already = [u for u in urls if paths[u].exists()] already = [u for u in urls if paths[u].exists()]
pending = [u for u in urls if not paths[u].exists()] pending = [u for u in urls if not paths[u].exists()]
@@ -316,8 +354,7 @@ def main():
return return
if args.dry_run: if args.dry_run:
print( print(f"\n[dry-run] Would download {len(pending)} files to {args.output}/")
f"\n[dry-run] Would download {len(pending)} files to {args.output}/")
for url in pending[:20]: for url in pending[:20]:
print(f" → {paths[url].name}") print(f" → {paths[url].name}")
if len(pending) > 20: if len(pending) > 20:
@@ -330,8 +367,7 @@ def main():
sized = {u: s for u, s in remote_sizes.items() if s is not None} sized = {u: s for u, s in remote_sizes.items() if s is not None}
total_bytes = sum(sized.values()) total_bytes = sum(sized.values())
print( print(f"[+] Download size: {fmt_size(total_bytes)} across {len(pending)} files")
f"[+] Download size: {fmt_size(total_bytes)} across {len(pending)} files")
if already: if already:
print(f"[+] Verifying {len(already)} existing files…") print(f"[+] Verifying {len(already)} existing files…")
@@ -344,14 +380,15 @@ def main():
remote = already_sizes.get(url) remote = already_sizes.get(url)
if remote and local != remote: if remote and local != remote:
mismatched += 1 mismatched += 1
print(f"[!] Size mismatch: {dest.name} " print(
f"(local {fmt_size(local)} vs remote {fmt_size(remote)})") f"[!] Size mismatch: {dest.name} "
f"(local {fmt_size(local)} vs remote {fmt_size(remote)})"
)
pending.append(url) pending.append(url)
remote_sizes[url] = remote remote_sizes[url] = remote
if mismatched: if mismatched:
print( print(f"[!] {mismatched} file(s) will be re-downloaded due to size mismatch")
f"[!] {mismatched} file(s) will be re-downloaded due to size mismatch")
print(f"\n[⚡] Downloading with {args.workers} threads…\n") print(f"\n[⚡] Downloading with {args.workers} threads…\n")
@@ -361,7 +398,7 @@ def main():
total = len(pending) total = len(pending)
interrupted = False interrupted = False
def do_download(url): def do_download(url: str) -> tuple[str, tuple[str, int]]:
dest = paths[url] dest = paths[url]
expected = remote_sizes.get(url) expected = remote_sizes.get(url)
return url, download_one(session, url, dest, expected) return url, download_one(session, url, dest, expected)
@@ -376,11 +413,9 @@ def main():
name = paths[url].name name = paths[url].name
if status == "ok" and written > 0: if status == "ok" and written > 0:
print( print(f" [{completed}/{total}] ✓ {name} ({fmt_size(written)})")
f" [{completed}/{total}] ✓ {name} ({fmt_size(written)})")
elif status == "ok": elif status == "ok":
print( print(f" [{completed}/{total}] ✓ {name} (already complete)")
f" [{completed}/{total}] ✓ {name} (already complete)")
elif status == "size_mismatch": elif status == "size_mismatch":
print(f" [{completed}/{total}] ⚠ {name} (size mismatch)") print(f" [{completed}/{total}] ⚠ {name} (size mismatch)")
failed.append(url) failed.append(url)

130
grab_cookie.py
View File

@@ -1,53 +1,25 @@
#!/usr/bin/env python3 #!/usr/bin/env python3
""" """
grab_cookie.py — read the WordPress login cookie from an grab_cookie.py — log in to jailbirdz.com and write the session cookie to .env.
installed browser and write it to .env as WP_LOGIN_COOKIE=name=value.
Requires WP_USERNAME and WP_PASSWORD to be set in the environment or .env.
Usage: Usage:
python grab_cookie.py # tries Firefox, Chrome, Edge, Brave python grab_cookie.py
python grab_cookie.py --browser firefox # explicit browser
""" """
import argparse import os
from pathlib import Path from pathlib import Path
from config import COOKIE_DOMAIN from typing import Literal
import requests
from config import BASE_URL
ENV_FILE = Path(".env") ENV_FILE = Path(".env")
ENV_KEY = "WP_LOGIN_COOKIE" ENV_KEY = "WP_LOGIN_COOKIE"
COOKIE_PREFIX = "wordpress_logged_in_" COOKIE_PREFIX = "wordpress_logged_in_"
BROWSER_NAMES = ["firefox", "chrome", "edge", "brave"]
def update_env(name: str, value: str) -> Literal["updated", "appended", "created"]:
def find_cookie(browser_name):
"""Return (name, value) for the wordpress_logged_in_* cookie, or (None, None)."""
try:
import rookiepy
except ImportError:
raise ImportError("rookiepy not installed — run: pip install rookiepy")
fn = getattr(rookiepy, browser_name, None)
if fn is None:
raise ValueError(f"rookiepy does not support '{browser_name}'.")
try:
cookies = fn([COOKIE_DOMAIN])
except PermissionError:
raise PermissionError(
f"Permission denied reading {browser_name} cookies.\n"
" Close the browser, or on Windows run as Administrator for Chrome/Edge."
)
except Exception as e:
raise RuntimeError(f"Could not read {browser_name} cookies: {e}")
for c in cookies:
if c.get("name", "").startswith(COOKIE_PREFIX):
return c["name"], c["value"]
return None, None
def update_env(name, value):
"""Write WP_LOGIN_COOKIE=name=value into .env, replacing any existing line.""" """Write WP_LOGIN_COOKIE=name=value into .env, replacing any existing line."""
new_line = f"{ENV_KEY}={name}={value}\n" new_line = f"{ENV_KEY}={name}={value}\n"
@@ -55,7 +27,8 @@ def update_env(name, value):
text = ENV_FILE.read_text(encoding="utf-8") text = ENV_FILE.read_text(encoding="utf-8")
lines = text.splitlines(keepends=True) lines = text.splitlines(keepends=True)
for i, line in enumerate(lines): for i, line in enumerate(lines):
if line.startswith(f"{ENV_KEY}=") or line.strip() == ENV_KEY: key, sep, _ = line.partition("=")
if key.strip() == ENV_KEY and sep:
lines[i] = new_line lines[i] = new_line
ENV_FILE.write_text("".join(lines), encoding="utf-8") ENV_FILE.write_text("".join(lines), encoding="utf-8")
return "updated" return "updated"
@@ -69,46 +42,65 @@ def update_env(name, value):
return "created" return "created"
def main(): def login_and_get_cookie(username: str, password: str) -> tuple[str, str]:
parser = argparse.ArgumentParser( """POST to wp-admin/admin-ajax.php (xootix action) and return (cookie_name, cookie_value).
description=f"Copy the {COOKIE_DOMAIN} login cookie from your browser into .env."
No browser needed — the xootix login endpoint takes plain form fields and returns
the wordpress_logged_in_* cookie directly in the response Set-Cookie headers.
"""
session = requests.Session()
r = session.post(
f"{BASE_URL}/wp-admin/admin-ajax.php",
data={
"xoo-el-username": username,
"xoo-el-password": password,
"xoo-el-rememberme": "forever",
"_xoo_el_form": "login",
"xoo_el_redirect": "/",
"action": "xoo_el_form_action",
"display": "popup",
},
headers={
"Referer": f"{BASE_URL}/",
"Origin": BASE_URL,
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:147.0) Gecko/20100101 Firefox/147.0",
},
timeout=30,
) )
parser.add_argument( r.raise_for_status()
"--browser", "-b", result = r.json()
choices=BROWSER_NAMES, if result.get("error"):
metavar="BROWSER", raise RuntimeError(f"Login rejected by server: {result.get('notice', result)}")
help=f"Browser to read from: {', '.join(BROWSER_NAMES)} (default: try all in order)",
for name, value in session.cookies.items():
if name.startswith(COOKIE_PREFIX):
return name, value
raise RuntimeError(
"Server accepted login but no wordpress_logged_in_* cookie was set.\n"
" Check that WP_USERNAME and WP_PASSWORD are correct."
) )
args = parser.parse_args()
order = [args.browser] if args.browser else BROWSER_NAMES
cookie_name = cookie_value = None def _auto_login() -> None:
for browser in order: username = os.environ.get("WP_USERNAME", "").strip()
print(f"[…] Trying {browser}…") password = os.environ.get("WP_PASSWORD", "").strip()
try: if not username or not password:
cookie_name, cookie_value = find_cookie(browser)
except ImportError as e:
raise SystemExit(f"[!] {e}")
except (ValueError, PermissionError, RuntimeError) as e:
print(f"[!] {e}")
continue
if cookie_name:
print(f"[+] Found in {browser}: {cookie_name}")
break
print(f" No {COOKIE_PREFIX}* cookie found in {browser}.")
if not cookie_name:
raise SystemExit( raise SystemExit(
f"\n[!] No {COOKIE_PREFIX}* cookie found in any browser.\n" "[!] WP_USERNAME and WP_PASSWORD must be set in the environment or .env — see .env.example."
f" Make sure you are logged into {COOKIE_DOMAIN}, then re-run.\n"
" Or set WP_LOGIN_COOKIE manually in .env — see .env.example."
) )
try:
cookie_name, cookie_value = login_and_get_cookie(username, password)
except RuntimeError as e:
raise SystemExit(f"[!] {e}")
print(f"[+] Login succeeded: {cookie_name}")
action = update_env(cookie_name, cookie_value) action = update_env(cookie_name, cookie_value)
print(f"[✓] {ENV_KEY} {action} in {ENV_FILE}.") print(f"[✓] {ENV_KEY} {action} in {ENV_FILE}.")
def main() -> None:
_auto_login()
if __name__ == "__main__": if __name__ == "__main__":
main() main()

340
main.py
View File

@@ -7,27 +7,36 @@ import asyncio
import tempfile import tempfile
import requests import requests
from pathlib import Path, PurePosixPath from pathlib import Path, PurePosixPath
from typing import Any, Optional
from urllib.parse import urlparse from urllib.parse import urlparse
from dotenv import load_dotenv from dotenv import load_dotenv
from playwright.async_api import async_playwright from playwright.async_api import async_playwright, BrowserContext
from check_clashes import VIDEO_EXTS from check_clashes import VIDEO_EXTS, load_video_map, is_valid_url, VIDEO_MAP_FILE, expects_video
from config import BASE_URL from config import BASE_URL
from grab_cookie import login_and_get_cookie, update_env
load_dotenv() load_dotenv()
def _is_video_url(url): def _is_video_url(url: str) -> bool:
"""True if `url` ends with a recognised video extension (case-insensitive, path only).""" """True if `url` ends with a recognised video extension (case-insensitive, path only)."""
return PurePosixPath(urlparse(url).path).suffix.lower() in VIDEO_EXTS return PurePosixPath(urlparse(url).path).suffix.lower() in VIDEO_EXTS
WP_API = f"{BASE_URL}/wp-json/wp/v2" WP_API = f"{BASE_URL}/wp-json/wp/v2"
SKIP_TYPES = { SKIP_TYPES = {
"attachment", "nav_menu_item", "wp_block", "wp_template", "attachment",
"wp_template_part", "wp_global_styles", "wp_navigation", "nav_menu_item",
"wp_font_family", "wp_font_face", "wp_block",
"wp_template",
"wp_template_part",
"wp_global_styles",
"wp_navigation",
"wp_font_family",
"wp_font_face",
} }
VIDEO_MAP_FILE = "video_map.json"
MAX_WORKERS = 4 MAX_WORKERS = 4
API_HEADERS = { API_HEADERS = {
@@ -37,22 +46,53 @@ API_HEADERS = {
} }
def _get_login_cookie(): def _probe_cookie(name: str, value: str) -> bool:
raw = os.environ.get("WP_LOGIN_COOKIE", "").strip() # strip accidental whitespace """HEAD request to a members-only video page. Returns True if the cookie is still valid."""
if not raw: video_map = load_video_map()
raise RuntimeError( probe_url = next((url for url in video_map if expects_video(url)), None)
"WP_LOGIN_COOKIE not set. Copy it from your browser into .env — see .env.example.") if probe_url is None:
return False # no video URLs yet — can't validate, fall through to re-auth
r = requests.head(
probe_url,
headers={"Cookie": f"{name}={value}", "User-Agent": API_HEADERS["User-Agent"]},
allow_redirects=False,
timeout=10,
)
return r.status_code == 200
def _get_login_cookie() -> tuple[str, str]:
username = os.environ.get("WP_USERNAME", "").strip()
password = os.environ.get("WP_PASSWORD", "").strip()
has_credentials = bool(username and password)
raw = os.environ.get("WP_LOGIN_COOKIE", "").strip()
if raw:
name, _, value = raw.partition("=") name, _, value = raw.partition("=")
if not value: if value and name.startswith("wordpress_logged_in_"):
raise RuntimeError( if not has_credentials:
"WP_LOGIN_COOKIE looks malformed (no '=' found). Expected: name=value") return name, value # cookie-only mode — trust it
if not name.startswith("wordpress_logged_in_"): print("[+] Cookie found — validating…")
raise RuntimeError( if _probe_cookie(name, value):
"WP_LOGIN_COOKIE doesn't look right — expected a wordpress_logged_in_... cookie.") print("[✓] Cookie still valid — skipping login.")
return name, value return name, value
print("[!] Cookie expired — re-authenticating…")
if has_credentials:
cookie_name, cookie_value = login_and_get_cookie(username, password)
action = update_env(cookie_name, cookie_value)
print(f"[✓] Logged in: {cookie_name} ({action} in .env)")
return cookie_name, cookie_value
raise RuntimeError(
"No credentials or cookie found. Set either:\n"
" • WP_USERNAME + WP_PASSWORD (recommended — always gets a fresh cookie)\n"
" • WP_LOGIN_COOKIE (fallback — may expire mid-run)\n"
"See .env.example."
)
def discover_content_types(session): def discover_content_types(session: requests.Session) -> list[tuple[str, str, str]]:
"""Query /wp-json/wp/v2/types and return a list of (name, rest_base, type_slug) for content types worth scraping.""" """Query /wp-json/wp/v2/types and return a list of (name, rest_base, type_slug) for content types worth scraping."""
r = session.get(f"{WP_API}/types", timeout=30) r = session.get(f"{WP_API}/types", timeout=30)
r.raise_for_status() r.raise_for_status()
@@ -69,7 +109,12 @@ def discover_content_types(session):
return targets return targets
def fetch_all_posts_for_type(session, type_name, rest_base, type_slug): def fetch_all_posts_for_type(
session: requests.Session,
type_name: str,
rest_base: str,
type_slug: str,
) -> list[tuple[str, str, str]]:
"""Paginate one content type and return (url, title, description) tuples. """Paginate one content type and return (url, title, description) tuples.
Uses the `link` field when available; falls back to building from slug.""" Uses the `link` field when available; falls back to building from slug."""
url_prefix = type_slug.replace("_", "-") url_prefix = type_slug.replace("_", "-")
@@ -96,11 +141,15 @@ def fetch_all_posts_for_type(session, type_name, rest_base, type_slug):
else: else:
continue continue
title_obj = post.get("title", {}) title_obj = post.get("title", {})
title = title_obj.get("rendered", "") if isinstance( title = (
title_obj, dict) else str(title_obj) title_obj.get("rendered", "")
if isinstance(title_obj, dict)
else str(title_obj)
)
content_obj = post.get("content", {}) content_obj = post.get("content", {})
content_html = content_obj.get( content_html = (
"rendered", "") if isinstance(content_obj, dict) else "" content_obj.get("rendered", "") if isinstance(content_obj, dict) else ""
)
description = html_to_text(content_html) if content_html else "" description = html_to_text(content_html) if content_html else ""
results.append((link, title, description)) results.append((link, title, description))
print(f" {type_name} page {page}: {len(data)} items") print(f" {type_name} page {page}: {len(data)} items")
@@ -109,21 +158,25 @@ def fetch_all_posts_for_type(session, type_name, rest_base, type_slug):
return results return results
def fetch_post_urls_from_api(headers): def fetch_post_urls_from_api(headers: dict[str, str]) -> list[str]:
"""Auto-discover all content types via the WP REST API and collect every post URL. """Auto-discover all content types via the WP REST API and collect every post URL.
Also builds video_map.json with titles pre-populated.""" Also builds video_map.json with titles pre-populated."""
print("[+] video_map.json empty or missing — discovering content types from REST API…") print(
"[+] video_map.json empty or missing — discovering content types from REST API…"
)
session = requests.Session() session = requests.Session()
session.headers.update(headers) session.headers.update(headers)
targets = discover_content_types(session) targets = discover_content_types(session)
print( print(
f"[+] Found {len(targets)} content types: {', '.join(name for name, _, _ in targets)}\n") f"[+] Found {len(targets)} content types: {', '.join(name for name, _, _ in targets)}\n"
)
all_results = [] all_results = []
for type_name, rest_base, type_slug in targets: for type_name, rest_base, type_slug in targets:
type_results = fetch_all_posts_for_type( type_results = fetch_all_posts_for_type(
session, type_name, rest_base, type_slug) session, type_name, rest_base, type_slug
)
all_results.extend(type_results) all_results.extend(type_results)
seen = set() seen = set()
@@ -135,8 +188,11 @@ def fetch_post_urls_from_api(headers):
seen.add(url) seen.add(url)
deduped_urls.append(url) deduped_urls.append(url)
if url not in video_map: if url not in video_map:
video_map[url] = {"title": title, video_map[url] = {
"description": description, "videos": []} "title": title,
"description": description,
"videos": [],
}
else: else:
if not video_map[url].get("title"): if not video_map[url].get("title"):
video_map[url]["title"] = title video_map[url]["title"] = title
@@ -145,18 +201,25 @@ def fetch_post_urls_from_api(headers):
save_video_map(video_map) save_video_map(video_map)
print( print(
f"\n[+] Discovered {len(deduped_urls)} unique URLs → saved to {VIDEO_MAP_FILE}") f"\n[+] Discovered {len(deduped_urls)} unique URLs → saved to {VIDEO_MAP_FILE}"
print( )
f"[+] Pre-populated {len(video_map)} entries in {VIDEO_MAP_FILE}") print(f"[+] Pre-populated {len(video_map)} entries in {VIDEO_MAP_FILE}")
return deduped_urls return deduped_urls
def fetch_metadata_from_api(video_map, urls, headers): def fetch_metadata_from_api(
video_map: dict[str, Any],
urls: list[str],
headers: dict[str, str],
) -> None:
"""Populate missing titles and descriptions in video_map from the REST API.""" """Populate missing titles and descriptions in video_map from the REST API."""
missing = [u for u in urls missing = [
u
for u in urls
if u not in video_map if u not in video_map
or not video_map[u].get("title") or not video_map[u].get("title")
or not video_map[u].get("description")] or not video_map[u].get("description")
]
if not missing: if not missing:
return return
@@ -168,7 +231,8 @@ def fetch_metadata_from_api(video_map, urls, headers):
for type_name, rest_base, type_slug in targets: for type_name, rest_base, type_slug in targets:
type_results = fetch_all_posts_for_type( type_results = fetch_all_posts_for_type(
session, type_name, rest_base, type_slug) session, type_name, rest_base, type_slug
)
for url, title, description in type_results: for url, title, description in type_results:
if url in video_map: if url in video_map:
if not video_map[url].get("title"): if not video_map[url].get("title"):
@@ -176,18 +240,20 @@ def fetch_metadata_from_api(video_map, urls, headers):
if not video_map[url].get("description"): if not video_map[url].get("description"):
video_map[url]["description"] = description video_map[url]["description"] = description
else: else:
video_map[url] = {"title": title, video_map[url] = {
"description": description, "videos": []} "title": title,
"description": description,
"videos": [],
}
save_video_map(video_map) save_video_map(video_map)
populated_t = sum(1 for u in urls if video_map.get(u, {}).get("title")) populated_t = sum(1 for u in urls if video_map.get(u, {}).get("title"))
populated_d = sum(1 for u in urls if video_map.get( populated_d = sum(1 for u in urls if video_map.get(u, {}).get("description"))
u, {}).get("description"))
print(f"[+] Titles populated: {populated_t}/{len(urls)}") print(f"[+] Titles populated: {populated_t}/{len(urls)}")
print(f"[+] Descriptions populated: {populated_d}/{len(urls)}") print(f"[+] Descriptions populated: {populated_d}/{len(urls)}")
def load_post_urls(headers): def load_post_urls(headers: dict[str, str]) -> list[str]:
vm = load_video_map() vm = load_video_map()
if vm: if vm:
print(f"[+] {VIDEO_MAP_FILE} found — loading {len(vm)} post URLs.") print(f"[+] {VIDEO_MAP_FILE} found — loading {len(vm)} post URLs.")
@@ -195,48 +261,40 @@ def load_post_urls(headers):
return fetch_post_urls_from_api(headers) return fetch_post_urls_from_api(headers)
def html_to_text(html_str): def html_to_text(html_str: str) -> str:
"""Strip HTML tags, decode entities, and collapse whitespace into clean plain text.""" """Strip HTML tags, decode entities, and collapse whitespace into clean plain text."""
import html import html
text = re.sub(r'<br\s*/?>', '\n', html_str)
text = text.replace('</p>', '\n\n') text = re.sub(r"<br\s*/?>", "\n", html_str)
text = re.sub(r'<[^>]+>', '', text) text = text.replace("</p>", "\n\n")
text = re.sub(r"<[^>]+>", "", text)
text = html.unescape(text) text = html.unescape(text)
lines = [line.strip() for line in text.splitlines()] lines = [line.strip() for line in text.splitlines()]
text = '\n'.join(lines) text = "\n".join(lines)
text = re.sub(r'\n{3,}', '\n\n', text) text = re.sub(r"\n{3,}", "\n\n", text)
return text.strip() return text.strip()
def extract_mp4_from_html(html): def extract_mp4_from_html(html: str) -> list[str]:
candidates = re.findall(r'https?://[^\s"\'<>]+', html) candidates = re.findall(r'https?://[^\s"\'<>]+', html)
return [u for u in candidates if _is_video_url(u)] return [u for u in candidates if _is_video_url(u)]
def extract_title_from_html(html): def extract_title_from_html(html: str) -> Optional[str]:
m = re.search( m = re.search(r'<h1[^>]*class="entry-title"[^>]*>(.*?)</h1>', html, re.DOTALL)
r'<h1[^>]*class="entry-title"[^>]*>(.*?)</h1>', html, re.DOTALL)
if m: if m:
title = re.sub(r'<[^>]+>', '', m.group(1)).strip() title = re.sub(r"<[^>]+>", "", m.group(1)).strip()
return title return title
m = re.search(r'<title>(.*?)(?:\s*[-–|].*)?</title>', html, re.DOTALL) m = re.search(r"<title>(.*?)(?:\s*[-–|].*)?</title>", html, re.DOTALL)
if m: if m:
return m.group(1).strip() return m.group(1).strip()
return None return None
def load_video_map(): def save_video_map(video_map: dict[str, Any]) -> None:
if Path(VIDEO_MAP_FILE).exists(): fd, tmp_path = tempfile.mkstemp(
try: dir=Path(VIDEO_MAP_FILE).resolve().parent, suffix=".tmp"
with open(VIDEO_MAP_FILE, encoding="utf-8") as f: )
return json.load(f)
except (json.JSONDecodeError, OSError):
return {}
return {}
def save_video_map(video_map):
fd, tmp_path = tempfile.mkstemp(dir=Path(VIDEO_MAP_FILE).resolve().parent, suffix=".tmp")
try: try:
with os.fdopen(fd, "w", encoding="utf-8") as f: with os.fdopen(fd, "w", encoding="utf-8") as f:
json.dump(video_map, f, indent=2, ensure_ascii=False) json.dump(video_map, f, indent=2, ensure_ascii=False)
@@ -250,19 +308,30 @@ def save_video_map(video_map):
def _expects_video(url):
return "/pinkcuffs-videos/" in url
MAX_RETRIES = 2 MAX_RETRIES = 2
async def worker(worker_id, queue, context, known, async def worker(
total, retry_counts, video_map, map_lock, shutdown_event): worker_id: int,
queue: asyncio.Queue[tuple[int, str]],
context: BrowserContext,
known: set[str],
total: int,
retry_counts: dict[int, int],
video_map: dict[str, Any],
map_lock: asyncio.Lock,
shutdown_event: asyncio.Event,
reauth_lock: asyncio.Lock,
reauth_done: list[bool],
cookie_domain: str,
) -> None:
page = await context.new_page() page = await context.new_page()
video_hits = set() video_hits = set()
page.on("response", lambda resp: video_hits.add(resp.url) if _is_video_url(resp.url) else None) page.on(
"response",
lambda resp: video_hits.add(resp.url) if _is_video_url(resp.url) else None,
)
try: try:
while not shutdown_event.is_set(): while not shutdown_event.is_set():
@@ -279,11 +348,11 @@ async def worker(worker_id, queue, context, known,
await page.goto(url, wait_until="networkidle", timeout=60000) await page.goto(url, wait_until="networkidle", timeout=60000)
except Exception as e: except Exception as e:
print(f"[W{worker_id}] Navigation error: {e}") print(f"[W{worker_id}] Navigation error: {e}")
if _expects_video(url) and attempt < MAX_RETRIES: if expects_video(url) and attempt < MAX_RETRIES:
retry_counts[idx] = attempt + 1 retry_counts[idx] = attempt + 1
queue.put_nowait((idx, url)) queue.put_nowait((idx, url))
print(f"[W{worker_id}] Re-queued for retry.") print(f"[W{worker_id}] Re-queued for retry.")
elif not _expects_video(url): elif not expects_video(url):
async with map_lock: async with map_lock:
entry = video_map.get(url, {}) entry = video_map.get(url, {})
entry["scraped_at"] = int(time.time()) entry["scraped_at"] = int(time.time())
@@ -291,7 +360,48 @@ async def worker(worker_id, queue, context, known,
save_video_map(video_map) save_video_map(video_map)
else: else:
print( print(
f"[W{worker_id}] Still failing after {MAX_RETRIES} retries — will retry next run.") f"[W{worker_id}] Still failing after {MAX_RETRIES} retries — will retry next run."
)
continue
if "NoDirectAccessAllowed" in page.url:
recovered = False
async with reauth_lock:
if not reauth_done[0]:
username = os.environ.get("WP_USERNAME", "").strip()
password = os.environ.get("WP_PASSWORD", "").strip()
if username and password:
print(f"[W{worker_id}] Cookie expired — re-authenticating…")
try:
new_name, new_value = await asyncio.to_thread(
login_and_get_cookie, username, password
)
update_env(new_name, new_value)
await context.add_cookies([{
"name": new_name,
"value": new_value,
"domain": cookie_domain,
"path": "/",
"httpOnly": True,
"secure": True,
"sameSite": "None",
}])
reauth_done[0] = True
recovered = True
print(f"[W{worker_id}] Re-auth succeeded — re-queuing.")
except Exception as e:
print(f"[W{worker_id}] Re-auth failed: {e}")
shutdown_event.set()
else:
print(
f"[W{worker_id}] Cookie expired. "
"Set WP_USERNAME + WP_PASSWORD in .env for auto re-auth."
)
shutdown_event.set()
else:
recovered = True # another worker already re-authed
if recovered:
queue.put_nowait((idx, url))
continue continue
await asyncio.sleep(1.5) await asyncio.sleep(1.5)
@@ -301,9 +411,15 @@ async def worker(worker_id, queue, context, known,
found = set(html_videos) | set(video_hits) found = set(html_videos) | set(video_hits)
video_hits.clear() video_hits.clear()
all_videos = [m for m in found if m not in ( all_videos = [
m
for m in found
if is_valid_url(m)
and m
not in (
f"{BASE_URL}/wp-content/plugins/easy-video-player/lib/blank.mp4", f"{BASE_URL}/wp-content/plugins/easy-video-player/lib/blank.mp4",
)] )
]
async with map_lock: async with map_lock:
new_found = found - known new_found = found - known
@@ -312,7 +428,8 @@ async def worker(worker_id, queue, context, known,
known.update(new_found) known.update(new_found)
elif all_videos: elif all_videos:
print( print(
f"[W{worker_id}] {len(all_videos)} video(s) already known — skipping write.") f"[W{worker_id}] {len(all_videos)} video(s) already known — skipping write."
)
else: else:
print(f"[W{worker_id}] No video found on page.") print(f"[W{worker_id}] No video found on page.")
@@ -322,7 +439,7 @@ async def worker(worker_id, queue, context, known,
existing_videos = set(entry.get("videos", [])) existing_videos = set(entry.get("videos", []))
existing_videos.update(all_videos) existing_videos.update(all_videos)
entry["videos"] = sorted(existing_videos) entry["videos"] = sorted(existing_videos)
mark_done = bool(all_videos) or not _expects_video(url) mark_done = bool(all_videos) or not expects_video(url)
if mark_done: if mark_done:
entry["scraped_at"] = int(time.time()) entry["scraped_at"] = int(time.time())
video_map[url] = entry video_map[url] = entry
@@ -333,19 +450,21 @@ async def worker(worker_id, queue, context, known,
retry_counts[idx] = attempt + 1 retry_counts[idx] = attempt + 1
queue.put_nowait((idx, url)) queue.put_nowait((idx, url))
print( print(
f"[W{worker_id}] Re-queued for retry ({attempt + 1}/{MAX_RETRIES}).") f"[W{worker_id}] Re-queued for retry ({attempt + 1}/{MAX_RETRIES})."
)
else: else:
print( print(
f"[W{worker_id}] No video after {MAX_RETRIES} retries — will retry next run.") f"[W{worker_id}] No video after {MAX_RETRIES} retries — will retry next run."
)
finally: finally:
await page.close() await page.close()
async def run(): async def run() -> None:
shutdown_event = asyncio.Event() shutdown_event = asyncio.Event()
loop = asyncio.get_running_loop() loop = asyncio.get_running_loop()
def _handle_shutdown(signum, _frame): def _handle_shutdown(signum: int, _frame: object) -> None:
print(f"\n[!] Signal {signum} received — finishing active pages then exiting…") print(f"\n[!] Signal {signum} received — finishing active pages then exiting…")
loop.call_soon_threadsafe(shutdown_event.set) loop.call_soon_threadsafe(shutdown_event.set)
@@ -362,10 +481,13 @@ async def run():
urls = load_post_urls(req_headers) urls = load_post_urls(req_headers)
video_map = load_video_map() video_map = load_video_map()
if any(u not in video_map if any(
u not in video_map
or not video_map[u].get("title") or not video_map[u].get("title")
or not video_map[u].get("description") or not video_map[u].get("description")
for u in urls if _expects_video(u)): for u in urls
if expects_video(u)
):
fetch_metadata_from_api(video_map, urls, req_headers) fetch_metadata_from_api(video_map, urls, req_headers)
known = {u for entry in video_map.values() for u in entry.get("videos", [])} known = {u for entry in video_map.values() for u in entry.get("videos", [])}
@@ -377,7 +499,7 @@ async def run():
entry = video_map.get(u, {}) entry = video_map.get(u, {})
if not entry.get("scraped_at"): if not entry.get("scraped_at"):
pending.append((i, u)) pending.append((i, u))
elif _expects_video(u) and not entry.get("videos"): elif expects_video(u) and not entry.get("videos"):
pending.append((i, u)) pending.append((i, u))
needs_map += 1 needs_map += 1
@@ -388,26 +510,31 @@ async def run():
if done_count: if done_count:
remaining_new = len(pending) - needs_map remaining_new = len(pending) - needs_map
print( print(
f"[↻] Resuming: {done_count} done, {remaining_new} new + {needs_map} needing map data.") f"[↻] Resuming: {done_count} done, {remaining_new} new + {needs_map} needing map data."
)
if not pending: if not pending:
print("[✓] All URLs already processed and mapped.") print("[✓] All URLs already processed and mapped.")
return return
print( print(
f"[⚡] Running with {min(MAX_WORKERS, len(pending))} concurrent workers.\n") f"[⚡] Running with {min(MAX_WORKERS, len(pending))} concurrent workers.\n"
)
queue = asyncio.Queue() queue: asyncio.Queue[tuple[int, str]] = asyncio.Queue()
for item in pending: for item in pending:
queue.put_nowait(item) queue.put_nowait(item)
map_lock = asyncio.Lock() map_lock = asyncio.Lock()
retry_counts = {} reauth_lock = asyncio.Lock()
reauth_done: list[bool] = [False]
retry_counts: dict[int, int] = {}
async with async_playwright() as p: async with async_playwright() as p:
browser = await p.firefox.launch(headless=True) browser = await p.firefox.launch(headless=True)
context = await browser.new_context() context = await browser.new_context()
_cookie_domain = urlparse(BASE_URL).netloc _parsed = urlparse(BASE_URL)
_cookie_domain = _parsed.hostname or _parsed.netloc
site_cookies = [ site_cookies = [
{ {
"name": cookie_name, "name": cookie_name,
@@ -416,23 +543,35 @@ async def run():
"path": "/", "path": "/",
"httpOnly": True, "httpOnly": True,
"secure": True, "secure": True,
"sameSite": "None" "sameSite": "None",
}, },
{ {
"name": "eav-age-verified", "name": "eav-age-verified",
"value": "1", "value": "1",
"domain": _cookie_domain, "domain": _cookie_domain,
"path": "/" "path": "/",
} },
] ]
await context.add_cookies(site_cookies) await context.add_cookies(site_cookies) # type: ignore[arg-type]
num_workers = min(MAX_WORKERS, len(pending)) num_workers = min(MAX_WORKERS, len(pending))
workers = [ workers = [
asyncio.create_task( asyncio.create_task(
worker(i, queue, context, known, worker(
total, retry_counts, video_map, map_lock, shutdown_event) i,
queue,
context,
known,
total,
retry_counts,
video_map,
map_lock,
shutdown_event,
reauth_lock,
reauth_done,
_cookie_domain,
)
) )
for i in range(num_workers) for i in range(num_workers)
] ]
@@ -442,7 +581,8 @@ async def run():
mapped = sum(1 for v in video_map.values() if v.get("videos")) mapped = sum(1 for v in video_map.values() if v.get("videos"))
print( print(
f"\n[+] Video map: {mapped} posts with videos, {len(video_map)} total entries.") f"\n[+] Video map: {mapped} posts with videos, {len(video_map)} total entries."
)
if not shutdown_event.is_set(): if not shutdown_event.is_set():
print(f"[✓] Completed. Full map in {VIDEO_MAP_FILE}") print(f"[✓] Completed. Full map in {VIDEO_MAP_FILE}")
@@ -454,7 +594,7 @@ async def run():
signal.signal(signal.SIGTERM, signal.SIG_DFL) signal.signal(signal.SIGTERM, signal.SIG_DFL)
def main(): def main() -> None:
try: try:
asyncio.run(run()) asyncio.run(run())
except KeyboardInterrupt: except KeyboardInterrupt:

1
requirements.txt
View File

@@ -1,4 +1,3 @@
playwright==1.58.0 playwright==1.58.0
python-dotenv==1.2.1 python-dotenv==1.2.1
Requests==2.32.5 Requests==2.32.5
rookiepy==0.5.6

37
total_size.py
View File

@@ -4,16 +4,35 @@ Importable function:
summarize_sizes(sizes) - return dict with total, smallest, largest, average, failed summarize_sizes(sizes) - return dict with total, smallest, largest, average, failed
""" """
from typing import Optional, TypedDict
from check_clashes import fmt_size, fetch_sizes, load_video_map, VIDEO_MAP_FILE from check_clashes import fmt_size, fetch_sizes, load_video_map, VIDEO_MAP_FILE
def summarize_sizes(sizes): class SizeStats(TypedDict):
sized: int
total: int
total_bytes: int
smallest: int
largest: int
average: int
failed: list[str]
def summarize_sizes(sizes: dict[str, Optional[int]]) -> SizeStats:
"""Given {url: size_or_None}, return a stats dict.""" """Given {url: size_or_None}, return a stats dict."""
known = {u: s for u, s in sizes.items() if s is not None} known = {u: s for u, s in sizes.items() if s is not None}
failed = [u for u, s in sizes.items() if s is None] failed = [u for u, s in sizes.items() if s is None]
if not known: if not known:
return {"sized": 0, "total": len(sizes), "total_bytes": 0, return {
"smallest": 0, "largest": 0, "average": 0, "failed": failed} "sized": 0,
"total": len(sizes),
"total_bytes": 0,
"smallest": 0,
"largest": 0,
"average": 0,
"failed": failed,
}
total_bytes = sum(known.values()) total_bytes = sum(known.values())
return { return {
"sized": len(known), "sized": len(known),
@@ -28,14 +47,20 @@ def summarize_sizes(sizes):
# --------------- CLI --------------- # --------------- CLI ---------------
def _progress(done, total):
def _progress(done: int, total: int) -> None:
if done % 200 == 0 or done == total: if done % 200 == 0 or done == total:
print(f" {done}/{total}") print(f" {done}/{total}")
def main(): def main() -> None:
vm = load_video_map() vm = load_video_map()
urls = [u for entry in vm.values() for u in entry.get("videos", []) if u.startswith("http")] urls: list[str] = [
u
for entry in vm.values()
for u in entry.get("videos", [])
if u.startswith("http")
]
print(f"[+] {len(urls)} URLs in {VIDEO_MAP_FILE}") print(f"[+] {len(urls)} URLs in {VIDEO_MAP_FILE}")
print("[+] Fetching file sizes (20 threads)…\n") print("[+] Fetching file sizes (20 threads)…\n")

287
upload.py
View File

@@ -26,13 +26,13 @@ from pathlib import Path
import re import re
import sys import sys
import time import time
from typing import Any, Callable, cast
import requests import requests
from dotenv import load_dotenv from dotenv import load_dotenv
from check_clashes import fmt_size, url_to_filename, VIDEO_EXTS from check_clashes import fmt_size, url_to_filename, VIDEO_EXTS, load_video_map
from download import ( from download import (
load_video_map,
collect_urls, collect_urls,
get_paths_for_mode, get_paths_for_mode,
read_mode, read_mode,
@@ -52,21 +52,21 @@ PT_NAME_MAX = 120
# ── Text helpers ───────────────────────────────────────────────────── # ── Text helpers ─────────────────────────────────────────────────────
def clean_description(raw):
def clean_description(raw: str) -> str:
"""Strip WordPress shortcodes and HTML from a description.""" """Strip WordPress shortcodes and HTML from a description."""
if not raw: if not raw:
return "" return ""
text = re.sub(r'\[/?[^\]]+\]', '', raw) text = re.sub(r"\[/?[^\]]+\]", "", raw)
text = re.sub(r'<[^>]+>', '', text) text = re.sub(r"<[^>]+>", "", text)
text = html.unescape(text) text = html.unescape(text)
text = re.sub(r'\n{3,}', '\n\n', text).strip() text = re.sub(r"\n{3,}", "\n\n", text).strip()
return text[:10000] return text[:10000]
def make_pt_name(title, fallback_filename): def make_pt_name(title: str, fallback_filename: str) -> str:
"""Build a PeerTube-safe video name (3-120 chars).""" """Build a PeerTube-safe video name (3-120 chars)."""
name = html.unescape(title).strip( name = html.unescape(title).strip() if title else Path(fallback_filename).stem
) if title else Path(fallback_filename).stem
if len(name) > PT_NAME_MAX: if len(name) > PT_NAME_MAX:
name = name[: PT_NAME_MAX - 1].rstrip() + "\u2026" name = name[: PT_NAME_MAX - 1].rstrip() + "\u2026"
while len(name) < 3: while len(name) < 3:
@@ -76,7 +76,8 @@ def make_pt_name(title, fallback_filename):
# ── PeerTube API ───────────────────────────────────────────────────── # ── PeerTube API ─────────────────────────────────────────────────────
def get_oauth_token(base, username, password):
def get_oauth_token(base: str, username: str, password: str) -> str:
r = requests.get(f"{base}/api/v1/oauth-clients/local", timeout=15) r = requests.get(f"{base}/api/v1/oauth-clients/local", timeout=15)
r.raise_for_status() r.raise_for_status()
client = r.json() client = r.json()
@@ -93,26 +94,36 @@ def get_oauth_token(base, username, password):
timeout=15, timeout=15,
) )
r.raise_for_status() r.raise_for_status()
return r.json()["access_token"] data_any: Any = r.json()
data = cast(dict[str, Any], data_any)
token = data.get("access_token")
if not isinstance(token, str) or not token:
raise RuntimeError("PeerTube token response missing access_token")
return token
def api_headers(token): def api_headers(token: str) -> dict[str, str]:
return {"Authorization": f"Bearer {token}"} return {"Authorization": f"Bearer {token}"}
def get_channel_id(base, token, channel_name): def get_channel_id(base: str, token: str, channel_name: str) -> int:
r = requests.get( r = requests.get(
f"{base}/api/v1/video-channels/{channel_name}", f"{base}/api/v1/video-channels/{channel_name}",
headers=api_headers(token), headers=api_headers(token),
timeout=15, timeout=15,
) )
r.raise_for_status() r.raise_for_status()
return r.json()["id"] data_any: Any = r.json()
data = cast(dict[str, Any], data_any)
cid = data.get("id")
if not isinstance(cid, int):
raise RuntimeError("PeerTube channel response missing id")
return cid
def get_channel_video_names(base, token, channel_name): def get_channel_video_names(base: str, token: str, channel_name: str) -> Counter[str]:
"""Paginate through the channel and return a Counter of video names.""" """Paginate through the channel and return a Counter of video names."""
counts = Counter() counts: Counter[str] = Counter()
start = 0 start = 0
while True: while True:
r = requests.get( r = requests.get(
@@ -135,8 +146,16 @@ CHUNK_SIZE = 10 * 1024 * 1024 # 10 MB
MAX_RETRIES = 5 MAX_RETRIES = 5
def _init_resumable(base, token, channel_id, filepath, filename, name, def _init_resumable(
description="", nsfw=False): base: str,
token: str,
channel_id: int,
filepath: Path,
filename: str,
name: str,
description: str = "",
nsfw: bool = False,
) -> tuple[str, int]:
"""POST to create a resumable upload session. Returns upload URL.""" """POST to create a resumable upload session. Returns upload URL."""
file_size = Path(filepath).stat().st_size file_size = Path(filepath).stat().st_size
metadata = { metadata = {
@@ -171,7 +190,7 @@ def _init_resumable(base, token, channel_id, filepath, filename, name,
return location, file_size return location, file_size
def _query_offset(upload_url, token, file_size): def _query_offset(upload_url: str, token: str, file_size: int) -> int:
"""Ask the server how many bytes it has received so far.""" """Ask the server how many bytes it has received so far."""
r = requests.put( r = requests.put(
upload_url, upload_url,
@@ -193,8 +212,15 @@ def _query_offset(upload_url, token, file_size):
return 0 return 0
def upload_video(base, token, channel_id, filepath, name, def upload_video(
description="", nsfw=False): base: str,
token: str,
channel_id: int,
filepath: Path,
name: str,
description: str = "",
nsfw: bool = False,
) -> tuple[bool, str | None]:
"""Resumable chunked upload. Returns (ok, uuid).""" """Resumable chunked upload. Returns (ok, uuid)."""
filepath = Path(filepath) filepath = Path(filepath)
filename = filepath.name filename = filepath.name
@@ -202,8 +228,14 @@ def upload_video(base, token, channel_id, filepath, name,
try: try:
upload_url, _ = _init_resumable( upload_url, _ = _init_resumable(
base, token, channel_id, filepath, filename, base,
name, description, nsfw, token,
channel_id,
filepath,
filename,
name,
description,
nsfw,
) )
except Exception as e: except Exception as e:
print(f" Init failed: {e}") print(f" Init failed: {e}")
@@ -221,8 +253,11 @@ def upload_video(base, token, channel_id, filepath, name,
chunk = f.read(chunk_len) chunk = f.read(chunk_len)
pct = int(100 * (end + 1) / file_size) pct = int(100 * (end + 1) / file_size)
print(f" {fmt_size(offset)}/{fmt_size(file_size)} ({pct}%)", print(
end="\r", flush=True) f" {fmt_size(offset)}/{fmt_size(file_size)} ({pct}%)",
end="\r",
flush=True,
)
try: try:
r = requests.put( r = requests.put(
@@ -239,12 +274,13 @@ def upload_video(base, token, channel_id, filepath, name,
except (requests.ConnectionError, requests.Timeout) as e: except (requests.ConnectionError, requests.Timeout) as e:
retries += 1 retries += 1
if retries > MAX_RETRIES: if retries > MAX_RETRIES:
print( print(f"\n Upload failed after {MAX_RETRIES} retries: {e}")
f"\n Upload failed after {MAX_RETRIES} retries: {e}")
return False, None return False, None
wait = min(2**retries, 60) wait = min(2**retries, 60)
print(f"\n Connection error, retry {retries}/{MAX_RETRIES} " print(
f"in {wait}s ...") f"\n Connection error, retry {retries}/{MAX_RETRIES} "
f"in {wait}s ..."
)
time.sleep(wait) time.sleep(wait)
try: try:
offset = _query_offset(upload_url, token, file_size) offset = _query_offset(upload_url, token, file_size)
@@ -261,8 +297,7 @@ def upload_video(base, token, channel_id, filepath, name,
retries = 0 retries = 0
elif r.status_code == 200: elif r.status_code == 200:
print( print(f" {fmt_size(file_size)}/{fmt_size(file_size)} (100%)")
f" {fmt_size(file_size)}/{fmt_size(file_size)} (100%)")
uuid = r.json().get("video", {}).get("uuid") uuid = r.json().get("video", {}).get("uuid")
return True, uuid return True, uuid
@@ -270,11 +305,9 @@ def upload_video(base, token, channel_id, filepath, name,
retry_after = int(r.headers.get("Retry-After", 10)) retry_after = int(r.headers.get("Retry-After", 10))
retries += 1 retries += 1
if retries > MAX_RETRIES: if retries > MAX_RETRIES:
print( print(f"\n Upload failed: server returned {r.status_code}")
f"\n Upload failed: server returned {r.status_code}")
return False, None return False, None
print( print(f"\n Server {r.status_code}, retry in {retry_after}s ...")
f"\n Server {r.status_code}, retry in {retry_after}s ...")
time.sleep(retry_after) time.sleep(retry_after)
try: try:
offset = _query_offset(upload_url, token, file_size) offset = _query_offset(upload_url, token, file_size)
@@ -301,7 +334,7 @@ _STATE = {
} }
def get_video_state(base, token, uuid): def get_video_state(base: str, token: str, uuid: str) -> tuple[int, str]:
r = requests.get( r = requests.get(
f"{base}/api/v1/videos/{uuid}", f"{base}/api/v1/videos/{uuid}",
headers=api_headers(token), headers=api_headers(token),
@@ -312,7 +345,7 @@ def get_video_state(base, token, uuid):
return state["id"], state.get("label", "") return state["id"], state.get("label", "")
def wait_for_published(base, token, uuid, poll_interval): def wait_for_published(base: str, token: str, uuid: str, poll_interval: int) -> int:
"""Block until the video reaches state 1 (Published) or a failure state.""" """Block until the video reaches state 1 (Published) or a failure state."""
started = time.monotonic() started = time.monotonic()
while True: while True:
@@ -329,8 +362,10 @@ def wait_for_published(base, token, uuid, poll_interval):
try: try:
sid, label = get_video_state(base, token, uuid) sid, label = get_video_state(base, token, uuid)
except requests.exceptions.RequestException as e: except requests.exceptions.RequestException as e:
print(f" -> Poll error ({e.__class__.__name__}) " print(
f"after {elapsed_str}, retrying in {poll_interval}s …") f" -> Poll error ({e.__class__.__name__}) "
f"after {elapsed_str}, retrying in {poll_interval}s …"
)
time.sleep(poll_interval) time.sleep(poll_interval)
continue continue
@@ -343,13 +378,16 @@ def wait_for_published(base, token, uuid, poll_interval):
print(f" -> FAILED: {display}") print(f" -> FAILED: {display}")
return sid return sid
print(f" -> {display} … {elapsed_str} elapsed (next check in {poll_interval}s)") print(
f" -> {display} … {elapsed_str} elapsed (next check in {poll_interval}s)"
)
time.sleep(poll_interval) time.sleep(poll_interval)
# ── State tracker ──────────────────────────────────────────────────── # ── State tracker ────────────────────────────────────────────────────
def load_uploaded(input_dir):
def load_uploaded(input_dir: str) -> set[Path]:
path = Path(input_dir) / UPLOADED_FILE path = Path(input_dir) / UPLOADED_FILE
if not path.exists(): if not path.exists():
return set() return set()
@@ -357,36 +395,58 @@ def load_uploaded(input_dir):
return {Path(line.strip()) for line in f if line.strip()} return {Path(line.strip()) for line in f if line.strip()}
def mark_uploaded(input_dir, rel_path): def mark_uploaded(input_dir: str, rel_path: Path) -> None:
with open(Path(input_dir) / UPLOADED_FILE, "a") as f: with open(Path(input_dir) / UPLOADED_FILE, "a") as f:
f.write(f"{rel_path}\n") f.write(f"{rel_path}\n")
# ── File / metadata helpers ───────────────────────────────────────── # ── File / metadata helpers ─────────────────────────────────────────
def build_path_to_meta(video_map, input_dir):
"""Map each expected download path (relative) to {title, description}.""" def build_path_to_meta(
video_map: dict[str, Any],
input_dir: str,
) -> dict[Path, dict[str, str]]:
"""Map each expected download path (relative) to {title, description, original_filename}."""
urls = collect_urls(video_map) urls = collect_urls(video_map)
mode = read_mode(input_dir) or MODE_ORIGINAL mode = read_mode(input_dir) or MODE_ORIGINAL
paths = get_paths_for_mode(mode, urls, video_map, input_dir)
url_meta = {} get_paths_typed = cast(
for entry in video_map.values(): Callable[[str, list[str], dict[str, Any], str], dict[str, Path]],
t = entry.get("title", "") get_paths_for_mode,
d = entry.get("description", "") )
for video_url in entry.get("videos", []): paths = get_paths_typed(mode, urls, video_map, input_dir)
if video_url not in url_meta:
url_meta[video_url] = {"title": t, "description": d}
result = {} url_meta: dict[str, dict[str, str]] = {}
for entry_any in video_map.values():
entry = cast(dict[str, Any], entry_any)
t = entry.get("title")
d = entry.get("description")
title = t if isinstance(t, str) else ""
desc = d if isinstance(d, str) else ""
videos_any = entry.get("videos", [])
if isinstance(videos_any, list):
for video_url_any in videos_any:
if not isinstance(video_url_any, str):
continue
if video_url_any not in url_meta:
url_meta[video_url_any] = {"title": title, "description": desc}
result: dict[Path, dict[str, str]] = {}
for url, abs_path in paths.items(): for url, abs_path in paths.items():
rel = Path(abs_path).relative_to(input_dir) rel = abs_path.relative_to(input_dir)
meta = url_meta.get(url, {"title": "", "description": ""}) meta = url_meta.get(url, {"title": "", "description": ""})
result[rel] = {**meta, "original_filename": url_to_filename(url)} result[rel] = {
"title": meta.get("title", ""),
"description": meta.get("description", ""),
"original_filename": url_to_filename(url),
}
return result return result
def find_videos(input_dir): def find_videos(input_dir: str) -> set[Path]:
"""Walk input_dir and return a set of relative paths for all video files.""" """Walk input_dir and return a set of relative paths for all video files."""
found = set() found = set()
for root, dirs, files in os.walk(input_dir): for root, dirs, files in os.walk(input_dir):
@@ -399,7 +459,12 @@ def find_videos(input_dir):
# ── Channel match helpers ───────────────────────────────────────────── # ── Channel match helpers ─────────────────────────────────────────────
def _channel_match(rel, path_meta, existing):
def _channel_match(
rel: Path,
path_meta: dict[Path, dict[str, str]],
existing: set[str],
) -> tuple[bool, str]:
"""Return (matched, name) for a local file against the channel name set. """Return (matched, name) for a local file against the channel name set.
Checks both the title-derived name and the original-filename-derived name Checks both the title-derived name and the original-filename-derived name
@@ -409,38 +474,62 @@ def _channel_match(rel, path_meta, existing):
""" """
meta = path_meta.get(rel, {}) meta = path_meta.get(rel, {})
name = make_pt_name(meta.get("title", ""), rel.name) name = make_pt_name(meta.get("title", ""), rel.name)
orig_fn = meta.get("original_filename", "") orig_fn = meta.get("original_filename", "")
raw_name = make_pt_name("", orig_fn) if orig_fn else None raw_name: str | None = make_pt_name("", orig_fn) if orig_fn else None
matched = name in existing or (raw_name and raw_name != name and raw_name in existing)
matched = name in existing
if not matched and raw_name is not None and raw_name != name:
matched = raw_name in existing
return matched, name return matched, name
# ── CLI ────────────────────────────────────────────────────────────── # ── CLI ──────────────────────────────────────────────────────────────
def main():
def main() -> None:
ap = argparse.ArgumentParser( ap = argparse.ArgumentParser(
description="Upload videos to PeerTube with transcoding-aware batching", description="Upload videos to PeerTube with transcoding-aware batching",
) )
ap.add_argument("--input", "-i", default=DEFAULT_OUTPUT, ap.add_argument(
help=f"Directory with downloaded videos (default: {DEFAULT_OUTPUT})") "--input",
ap.add_argument("--url", "-i",
help="PeerTube instance URL (or set PEERTUBE_URL env var)") default=DEFAULT_OUTPUT,
ap.add_argument("--username", "-U", help=f"Directory with downloaded videos (default: {DEFAULT_OUTPUT})",
help="PeerTube username (or set PEERTUBE_USER env var)") )
ap.add_argument("--password", "-p", ap.add_argument("--url", help="PeerTube instance URL (or set PEERTUBE_URL env var)")
help="PeerTube password (or set PEERTUBE_PASSWORD env var)") ap.add_argument(
ap.add_argument("--channel", "-C", "--username", "-U", help="PeerTube username (or set PEERTUBE_USER env var)"
help="Channel to upload to (or set PEERTUBE_CHANNEL env var)") )
ap.add_argument("--batch-size", "-b", type=int, default=DEFAULT_BATCH_SIZE, ap.add_argument(
help="Videos to upload before waiting for transcoding (default: 1)") "--password", "-p", help="PeerTube password (or set PEERTUBE_PASSWORD env var)"
ap.add_argument("--poll-interval", type=int, default=DEFAULT_POLL, )
help=f"Seconds between state polls (default: {DEFAULT_POLL})") ap.add_argument(
ap.add_argument("--skip-wait", action="store_true", "--channel", "-C", help="Channel to upload to (or set PEERTUBE_CHANNEL env var)"
help="Upload everything without waiting for transcoding") )
ap.add_argument("--nsfw", action="store_true", ap.add_argument(
help="Mark videos as NSFW") "--batch-size",
ap.add_argument("--dry-run", "-n", action="store_true", "-b",
help="Preview what would be uploaded") type=int,
default=DEFAULT_BATCH_SIZE,
help="Videos to upload before waiting for transcoding (default: 1)",
)
ap.add_argument(
"--poll-interval",
type=int,
default=DEFAULT_POLL,
help=f"Seconds between state polls (default: {DEFAULT_POLL})",
)
ap.add_argument(
"--skip-wait",
action="store_true",
help="Upload everything without waiting for transcoding",
)
ap.add_argument("--nsfw", action="store_true", help="Mark videos as NSFW")
ap.add_argument(
"--dry-run", "-n", action="store_true", help="Preview what would be uploaded"
)
args = ap.parse_args() args = ap.parse_args()
url = args.url or os.environ.get("PEERTUBE_URL") url = args.url or os.environ.get("PEERTUBE_URL")
@@ -449,12 +538,16 @@ def main():
password = args.password or os.environ.get("PEERTUBE_PASSWORD") password = args.password or os.environ.get("PEERTUBE_PASSWORD")
if not args.dry_run: if not args.dry_run:
missing = [label for label, val in [ missing = [
label
for label, val in [
("--url / PEERTUBE_URL", url), ("--url / PEERTUBE_URL", url),
("--username / PEERTUBE_USER", username), ("--username / PEERTUBE_USER", username),
("--channel / PEERTUBE_CHANNEL", channel), ("--channel / PEERTUBE_CHANNEL", channel),
("--password / PEERTUBE_PASSWORD", password), ("--password / PEERTUBE_PASSWORD", password),
] if not val] ]
if not val
]
if missing: if missing:
for label in missing: for label in missing:
print(f"[!] Required: {label}") print(f"[!] Required: {label}")
@@ -468,7 +561,8 @@ def main():
unmatched = on_disk - set(path_meta.keys()) unmatched = on_disk - set(path_meta.keys())
if unmatched: if unmatched:
print( print(
f"[!] {len(unmatched)} file(s) on disk not in video_map (will use filename as title)") f"[!] {len(unmatched)} file(s) on disk not in video_map (will use filename as title)"
)
for rel in unmatched: for rel in unmatched:
path_meta[rel] = {"title": "", "description": ""} path_meta[rel] = {"title": "", "description": ""}
@@ -493,10 +587,14 @@ def main():
sz = (Path(args.input) / rel).stat().st_size sz = (Path(args.input) / rel).stat().st_size
total_bytes += sz total_bytes += sz
print(f" [{fmt_size(sz):>10}] {name}") print(f" [{fmt_size(sz):>10}] {name}")
print( print(f"\n Total: {fmt_size(total_bytes)} across {len(pending)} videos")
f"\n Total: {fmt_size(total_bytes)} across {len(pending)} videos")
return return
assert url is not None
assert username is not None
assert channel is not None
assert password is not None
# ── authenticate ── # ── authenticate ──
base = url.rstrip("/") base = url.rstrip("/")
if not base.startswith("http"): if not base.startswith("http"):
@@ -533,7 +631,9 @@ def main():
if _channel_match(rel, path_meta, existing)[0]: if _channel_match(rel, path_meta, existing)[0]:
pre_matched.append(rel) pre_matched.append(rel)
if pre_matched: if pre_matched:
print(f"\n[+] Pre-sweep: {len(pre_matched)} local file(s) already on channel — marking uploaded") print(
f"\n[+] Pre-sweep: {len(pre_matched)} local file(s) already on channel — marking uploaded"
)
for rel in pre_matched: for rel in pre_matched:
mark_uploaded(args.input, rel) mark_uploaded(args.input, rel)
pending = [rel for rel in pending if rel not in set(pre_matched)] pending = [rel for rel in pending if rel not in set(pre_matched)]
@@ -548,7 +648,8 @@ def main():
# ── flush batch if full ── # ── flush batch if full ──
if not args.skip_wait and len(batch) >= args.batch_size: if not args.skip_wait and len(batch) >= args.batch_size:
print( print(
f"\n[+] Waiting for {len(batch)} video(s) to finish processing ...") f"\n[+] Waiting for {len(batch)} video(s) to finish processing ..."
)
for uuid, bname in batch: for uuid, bname in batch:
print(f"\n [{bname}]") print(f"\n [{bname}]")
wait_for_published(base, token, uuid, args.poll_interval) wait_for_published(base, token, uuid, args.poll_interval)
@@ -568,18 +669,17 @@ def main():
print(f"\n[{total_up + 1}/{len(pending)}] {name}") print(f"\n[{total_up + 1}/{len(pending)}] {name}")
print(f" File: {rel} ({fmt_size(sz)})") print(f" File: {rel} ({fmt_size(sz)})")
ok, uuid = upload_video( ok, uuid_opt = upload_video(base, token, channel_id, filepath, name, desc, nsfw)
base, token, channel_id, filepath, name, desc, nsfw)
if not ok: if not ok:
continue continue
print(f" Uploaded uuid={uuid}") print(f" Uploaded uuid={uuid_opt}")
mark_uploaded(args.input, rel) mark_uploaded(args.input, rel)
total_up += 1 total_up += 1
existing.add(name) existing.add(name)
if uuid: if uuid_opt is not None:
batch.append((uuid, name)) batch.append((uuid_opt, name))
# ── wait for final batch ── # ── wait for final batch ──
if batch and not args.skip_wait: if batch and not args.skip_wait:
@@ -589,8 +689,7 @@ def main():
wait_for_published(base, token, uuid, args.poll_interval) wait_for_published(base, token, uuid, args.poll_interval)
except KeyboardInterrupt: except KeyboardInterrupt:
print( print(f"\n\n[!] Interrupted after {total_up} uploads. Re-run to continue.")
f"\n\n[!] Interrupted after {total_up} uploads. Re-run to continue.")
sys.exit(130) sys.exit(130)
print(f"\n{'=' * 50}") print(f"\n{'=' * 50}")

14
video_map.json
View File

@@ -2144,7 +2144,7 @@
] ]
}, },
"https://www.jailbirdz.com/pinkcuffs-videos/sunday-august-4th-live-show/": { "https://www.jailbirdz.com/pinkcuffs-videos/sunday-august-4th-live-show/": {
"title": "Sunday August 4th Live Show!!!!!", "title": "Page Not Found",
"description": "[vc_row type=”in_container” full_screen_row_position=”middle” column_margin=”default” column_direction=”default” column_direction_tablet=”default” column_direction_phone=”default” scene_position=”center” text_color=”dark” text_align=”left” row_border_radius=”none” row_border_radius_applies=”bg” overflow=”visible” overlay_strength=”0.3″ gradient_direction=”left_to_right” shape_divider_position=”bottom” bg_image_animation=”none”][vc_column column_padding=”no-extra-padding” column_padding_tablet=”inherit” column_padding_phone=”inherit” column_padding_position=”all” column_element_direction_desktop=”default” column_element_spacing=”default” desktop_text_alignment=”default” tablet_text_alignment=”default” phone_text_alignment=”default” background_color_opacity=”1″ background_hover_color_opacity=”1″ column_backdrop_filter=”none” column_shadow=”none” column_border_radius=”none” column_link_target=”_self” column_position=”default” gradient_direction=”left_to_right” overlay_strength=”0.3″ width=”1/1″ tablet_width_inherit=”default” animation_type=”default” bg_image_animation=”none” border_type=”simple” column_border_width=”none” column_border_style=”solid”][vc_column_text]Live show with Mia Brooks and Autumn! BOTH models will be getting cuffed up this show 🙂 Click to Watch Show[/vc_column_text][/vc_column][/vc_row]", "description": "[vc_row type=”in_container” full_screen_row_position=”middle” column_margin=”default” column_direction=”default” column_direction_tablet=”default” column_direction_phone=”default” scene_position=”center” text_color=”dark” text_align=”left” row_border_radius=”none” row_border_radius_applies=”bg” overflow=”visible” overlay_strength=”0.3″ gradient_direction=”left_to_right” shape_divider_position=”bottom” bg_image_animation=”none”][vc_column column_padding=”no-extra-padding” column_padding_tablet=”inherit” column_padding_phone=”inherit” column_padding_position=”all” column_element_direction_desktop=”default” column_element_spacing=”default” desktop_text_alignment=”default” tablet_text_alignment=”default” phone_text_alignment=”default” background_color_opacity=”1″ background_hover_color_opacity=”1″ column_backdrop_filter=”none” column_shadow=”none” column_border_radius=”none” column_link_target=”_self” column_position=”default” gradient_direction=”left_to_right” overlay_strength=”0.3″ width=”1/1″ tablet_width_inherit=”default” animation_type=”default” bg_image_animation=”none” border_type=”simple” column_border_width=”none” column_border_style=”solid”][vc_column_text]Live show with Mia Brooks and Autumn! BOTH models will be getting cuffed up this show 🙂 Click to Watch Show[/vc_column_text][/vc_column][/vc_row]",
"videos": [] "videos": []
}, },
@@ -2317,7 +2317,7 @@
] ]
}, },
"https://www.jailbirdz.com/pinkcuffs-videos/sunday-show-this-week/": { "https://www.jailbirdz.com/pinkcuffs-videos/sunday-show-this-week/": {
"title": "Sunday Show This week!", "title": "Page Not Found",
"description": "[vc_row type=”in_container” full_screen_row_position=”middle” column_margin=”default” column_direction=”default” column_direction_tablet=”default” column_direction_phone=”default” scene_position=”center” text_color=”dark” text_align=”left” row_border_radius=”none” row_border_radius_applies=”bg” overflow=”visible” overlay_strength=”0.3″ gradient_direction=”left_to_right” shape_divider_position=”bottom” bg_image_animation=”none”][vc_column column_padding=”no-extra-padding” column_padding_tablet=”inherit” column_padding_phone=”inherit” column_padding_position=”all” column_element_direction_desktop=”default” column_element_spacing=”default” desktop_text_alignment=”default” tablet_text_alignment=”default” phone_text_alignment=”default” background_color_opacity=”1″ background_hover_color_opacity=”1″ column_backdrop_filter=”none” column_shadow=”none” column_border_radius=”none” column_link_target=”_self” column_position=”default” gradient_direction=”left_to_right” overlay_strength=”0.3″ width=”1/1″ tablet_width_inherit=”default” animation_type=”default” bg_image_animation=”none” border_type=”simple” column_border_width=”none” column_border_style=”solid”][vc_column_text]Come watch Mia brooks Arrest and Cuff up Zoe Jade!\n\nLink To View Show[/vc_column_text][/vc_column][/vc_row]", "description": "[vc_row type=”in_container” full_screen_row_position=”middle” column_margin=”default” column_direction=”default” column_direction_tablet=”default” column_direction_phone=”default” scene_position=”center” text_color=”dark” text_align=”left” row_border_radius=”none” row_border_radius_applies=”bg” overflow=”visible” overlay_strength=”0.3″ gradient_direction=”left_to_right” shape_divider_position=”bottom” bg_image_animation=”none”][vc_column column_padding=”no-extra-padding” column_padding_tablet=”inherit” column_padding_phone=”inherit” column_padding_position=”all” column_element_direction_desktop=”default” column_element_spacing=”default” desktop_text_alignment=”default” tablet_text_alignment=”default” phone_text_alignment=”default” background_color_opacity=”1″ background_hover_color_opacity=”1″ column_backdrop_filter=”none” column_shadow=”none” column_border_radius=”none” column_link_target=”_self” column_position=”default” gradient_direction=”left_to_right” overlay_strength=”0.3″ width=”1/1″ tablet_width_inherit=”default” animation_type=”default” bg_image_animation=”none” border_type=”simple” column_border_width=”none” column_border_style=”solid”][vc_column_text]Come watch Mia brooks Arrest and Cuff up Zoe Jade!\n\nLink To View Show[/vc_column_text][/vc_column][/vc_row]",
"videos": [] "videos": []
}, },
@@ -7754,7 +7754,6 @@
"description": "Officer Jackie Jupiter is hard at work just doing her job when a couple of mischievous little rookies decide to make her day more interesting. Officer Maggie and Officer Serendipity decided to swing by and see how Officer Jackie was doing on their day off. They go into her office and get into some trouble. Come see what happens in this part 1!", "description": "Officer Jackie Jupiter is hard at work just doing her job when a couple of mischievous little rookies decide to make her day more interesting. Officer Maggie and Officer Serendipity decided to swing by and see how Officer Jackie was doing on their day off. They go into her office and get into some trouble. Come see what happens in this part 1!",
"scraped_at": 1771809265, "scraped_at": 1771809265,
"videos": [ "videos": [
"http://prisonteens.s3.amazonaws.com/2020/Jackie Jupiter/corrupt cops caught part1.mp4</a><a href=",
"https://d1nqppmcfahrr7.cloudfront.net/2020/Jackie%20Jupiter/corrupt%20cops%20caught%20part1.mp4" "https://d1nqppmcfahrr7.cloudfront.net/2020/Jackie%20Jupiter/corrupt%20cops%20caught%20part1.mp4"
] ]
}, },
@@ -8275,7 +8274,6 @@
"description": "Officer Lisa pulls over Jade and Nathalie for running a light. The girls are surprised when she comes back after running their information and asks them to get out of the vehicle. Come see what happens in Part 1!", "description": "Officer Lisa pulls over Jade and Nathalie for running a light. The girls are surprised when she comes back after running their information and asks them to get out of the vehicle. Come see what happens in Part 1!",
"scraped_at": 1771809265, "scraped_at": 1771809265,
"videos": [ "videos": [
"http://prisonteens.s3.amazonaws.com/2019/Lisa/OfficerLisaCarArrestPart1.mp4 car ride</a><a href=",
"https://d1nqppmcfahrr7.cloudfront.net/2019/Lisa/OfficerLisaCarArrestPart1.mp4" "https://d1nqppmcfahrr7.cloudfront.net/2019/Lisa/OfficerLisaCarArrestPart1.mp4"
] ]
}, },
@@ -11021,5 +11019,13 @@
"videos": [ "videos": [
"https://d1nqppmcfahrr7.cloudfront.net/2020/Persephone/serendipity%20and%20persephone%20part1.mp4" "https://d1nqppmcfahrr7.cloudfront.net/2020/Persephone/serendipity%20and%20persephone%20part1.mp4"
] ]
},
"https://www.jailbirdz.com/pinkcuffs-videos/kay-is-under-investigation-then-lilly-sneaks-into-the-cop-car-pt4/": {
"title": "Kay Is Under Investigation —Then Lilly Sneaks Into the Cop Car pt4",
"description": "Lilly and Kay Bunny remain nude and chained to the bench when Officer Luna Lux notices Kay chewing gum. Luna confiscates it and announces that both women will face additional restraints as punishment. Lilly protests that it’s unfair, but Luna only chuckles.\n\nLuna uncuffs and stands Kay Bunny up, walking her over to another room then repeats the same process for Lilly. Afterward, Luna uncuffs them and hands them lime-green jumpsuits. With hands on their heads, both are fitted with waist chains, front cuffs, and shackles.\n\nLuna then walks them to their cell. Both remain restrained overnight, sharing a small cot, trying to get comfortable. The series ends with them awaiting the next day.",
"videos": [
"https://d1nqppmcfahrr7.cloudfront.net/2026/LunaLux/LillyRedKayBunniept4.mp4"
],
"scraped_at": 1772204332
} }
} }