mirror of
https://github.com/kuhyx/testsAndMisc.git
synced 2026-11-10 22:47:02 +01:00
Krzysztof kuhy Rudnicki
89ed9bc95d
New package. Walks every thread on 4chan's /wsg/, downloads each video it has
not seen, and reviews them one at a time: mpv embedded in a Tk window via --wid
with Keep/Pass/Undo directly beneath the picture.
Dedupe is structural rather than a convention. Every post carrying a file also
carries md5 -- base64 MD5 of the whole file -- so it is the sqlite primary key.
An already-seen video costs zero bytes to skip and a byte-identical repost in
another thread collapses onto the existing row. Verified against a live file:
the API's Nz9OEKdMuMZEdYE6eLTKmA== matched base64(md5(bytes)) exactly.
Undo is unbounded and survives quitting: the verdict trail lives in the index,
not in memory, so yesterday's decisions can still be taken back.
No downloaded video is ever deleted. A pass moves the file to trash/ and leaves
it there; files.apply_move refuses to overwrite an existing destination, so the
guarantee holds by construction rather than per caller.
Three bugs only running it could find, each caught from evidence rather than
guesswork:
- the video stayed black: a <Configure> handler set mpv's geometry, fighting
the automatic sizing --wid already does
- playback never advanced: refresh() ran every tick and re-sent loadfile ~7x
a second, restarting the video continuously
- it froze on one video around the 26th while filenames kept advancing: mpv
pushes an event stream down the same socket and nothing drained it, so the
buffer filled and mpv stopped reading commands. Isolated to command #35
without a drain thread; all 60 honoured with one.
A five-lens review then found nine more, all reproduced before fixing: a failed
mpv start stranded the non-daemon worker forever; undo could clobber a file in
incoming/; a NUL-bearing md5 poisoned the index permanently; an oversized int
killed the worker with no event; gzip bombs on both hosts were accepted; the
board endpoints were fetched unconditionally forever; and Session.missing could
corrupt the undo trail.
mpv runs as a subprocess over its JSON IPC socket rather than via python-mpv,
which resolves libmpv at import time and would fail on CI while passing here.
Third-party surface is requests alone, already declared.
277 package tests, 100% branch coverage on all 22 modules, no suppressions.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
105 lines
3.7 KiB
Python
105 lines
3.7 KiB
Python
"""Fixed configuration for the /wsg/ grabber.
|
|
|
|
Values here are deliberately plain data so the pure planning helpers in
|
|
:mod:`python_pkg.wsg_grabber.scanner` can be exercised without touching the
|
|
network, the filesystem or a display.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from types import MappingProxyType
|
|
from typing import TYPE_CHECKING, Final
|
|
|
|
if TYPE_CHECKING:
|
|
from collections.abc import Mapping
|
|
|
|
BOARD: Final[str] = "wsg"
|
|
# The only board this tool targets.
|
|
|
|
API_HOST: Final[str] = "https://a.4cdn.org"
|
|
MEDIA_HOST: Final[str] = "https://i.4cdn.org"
|
|
BOARDS_URL: Final[str] = "https://boards.4chan.org/"
|
|
|
|
THREADS_URL: Final[str] = f"{API_HOST}/{BOARD}/threads.json"
|
|
ARCHIVE_URL: Final[str] = f"{API_HOST}/{BOARD}/archive.json"
|
|
|
|
VIDEO_EXTENSIONS: Final[frozenset[str]] = frozenset({".webm", ".mp4", ".gif"})
|
|
# /wsg/ serves all three. A live catalogue sample was 55% webm, 37% mp4, 8%
|
|
# gif, so filtering to {".webm", ".gif"} would silently drop a third of it.
|
|
|
|
# i.4cdn.org answers a bare request with 429 once it has seen a burst, so the
|
|
# session presents itself as a browser following a link from the board. The
|
|
# cookies 4chan sets in response (``__cf_bm``, ``_cfuvid``) are why a single
|
|
# long-lived Session is mandatory rather than merely efficient.
|
|
USER_AGENT: Final[str] = (
|
|
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 "
|
|
"(KHTML, like Gecko) Chrome/140.0.0.0 Safari/537.36"
|
|
)
|
|
API_HEADERS: Final[Mapping[str, str]] = MappingProxyType(
|
|
{
|
|
"User-Agent": USER_AGENT,
|
|
"Accept": "application/json,text/plain,*/*;q=0.8",
|
|
"Accept-Language": "en-US,en;q=0.9",
|
|
# Ask for no compression so a hostile or compromised host cannot turn a
|
|
# few hundred KB on the wire into gigabytes of decoded JSON.
|
|
"Accept-Encoding": "identity",
|
|
"Referer": BOARDS_URL,
|
|
},
|
|
)
|
|
MEDIA_HEADERS: Final[Mapping[str, str]] = MappingProxyType(
|
|
{
|
|
"User-Agent": USER_AGENT,
|
|
"Accept": "video/webm,video/mp4,image/gif,video/*;q=0.9,*/*;q=0.5",
|
|
"Accept-Language": "en-US,en;q=0.9",
|
|
# Never gzip a webm: it cannot compress and it breaks Range resumption.
|
|
"Accept-Encoding": "identity",
|
|
"Referer": BOARDS_URL,
|
|
"Sec-Fetch-Dest": "video",
|
|
"Sec-Fetch-Mode": "no-cors",
|
|
"Sec-Fetch-Site": "cross-site",
|
|
},
|
|
)
|
|
|
|
MIN_REQUEST_INTERVAL_S: Final[float] = 1.0
|
|
# The 4chan API rules state at most one request per second.
|
|
|
|
BACKOFF_BASE_S: Final[float] = 2.0
|
|
BACKOFF_CAP_S: Final[float] = 120.0
|
|
MAX_ATTEMPTS: Final[int] = 3
|
|
# Download attempts before a file is written off as ``gone``.
|
|
|
|
CONNECT_TIMEOUT_S: Final[float] = 10.0
|
|
READ_TIMEOUT_S: Final[float] = 30.0
|
|
CHUNK_BYTES: Final[int] = 65536
|
|
|
|
# Refuse an API response larger than this; the real ones are ~300 KB.
|
|
MAX_JSON_BYTES: Final[int] = 32 * 1024 * 1024
|
|
|
|
# How far a download may exceed its advertised size before it is abandoned.
|
|
SIZE_SLACK_BYTES: Final[int] = 1024 * 1024
|
|
|
|
SCHEMA_VERSION: Final[int] = 3
|
|
DB_TIMEOUT_S: Final[float] = 30.0
|
|
DB_BUSY_TIMEOUT_MS: Final[int] = 5000
|
|
|
|
POLL_INTERVAL_MS: Final[int] = 150
|
|
# How often the Tk loop drains the downloader's event queue.
|
|
|
|
IDLE_POLL_S: Final[float] = 1.0
|
|
# How long the worker sleeps per tick once the board is exhausted.
|
|
|
|
IDLE_RESCAN_S: Final[float] = 60.0
|
|
# How long a finished sweep stays quiet before the board is walked again.
|
|
|
|
JOIN_TIMEOUT_S: Final[float] = 10.0
|
|
IPC_READY_TIMEOUT_S: Final[float] = 10.0
|
|
|
|
CONTROL_BAR_HEIGHT_PX: Final[int] = 96
|
|
WINDOW_WIDTH_PX: Final[int] = 1100
|
|
WINDOW_HEIGHT_PX: Final[int] = 800
|
|
|
|
KEEP_KEYS: Final[tuple[str, ...]] = ("<k>", "<Right>")
|
|
PASS_KEYS: Final[tuple[str, ...]] = ("<j>", "<space>", "<Left>")
|
|
UNDO_KEYS: Final[tuple[str, ...]] = ("<u>", "<BackSpace>")
|
|
QUIT_KEYS: Final[tuple[str, ...]] = ("<q>", "<Escape>")
|