bvandeusen
544e30bfb9
The native downloader used the Windows-safe sanitize_segment, but gallery-dl on Linux (path-restrict auto→'/', path-remove default control chars, path-strip auto→'') replaces ONLY '/' and deletes control chars — the Windows-forbidden set (<>:"|?*) and trailing dots/spaces stay RAW in on-disk titles. Any pixiv title with those chars would therefore miss the tier-2 disk-skip and re-download the whole work at cutover (seen-ledger starts empty). Replace sanitize_segment with gdl_clean_filename, a byte-exact mirror of gallery-dl 1.32.5 build_filename (verified against path.py). Directory + template already matched; this closes the last parity gap. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
263 lines
11 KiB
Python
263 lines
11 KiB
Python
"""Native Pixiv media downloader — the Pixiv counterpart to
|
||
patreon_downloader / subscribestar_downloader.
|
||
|
||
Given a normalized Pixiv work and its resolved `MediaItem`s
|
||
(pixiv_client.extract_media), download the originals to gallery-dl's on-disk
|
||
layout (so pre-cutover gallery-dl downloads are recognized on disk and not
|
||
re-fetched), write the post-first sidecars the importer consumes, and report
|
||
per-media outcomes.
|
||
|
||
On-disk layout (matches FC's gallery-dl pixiv config, PLATFORM_DEFAULTS:
|
||
base-directory `<images_root>/<artist_slug>/pixiv` + `directory:
|
||
["{category}"]` + filename `{id}_{title[:50]}_{num:>02}.{extension}`):
|
||
|
||
<images_root>/<artist_slug>/pixiv/pixiv/<id>_<title50>_<NN>.<ext>
|
||
|
||
— note the intentional DOUBLE `pixiv` segment: gallery-dl appended
|
||
`{category}` under a base-directory that already ended in the platform name,
|
||
and tier-2 disk-skip parity requires reproducing that exactly. The layout is
|
||
FLAT (no per-post directory), so the post-first record is `_post_<id>.json`
|
||
in the same directory (the id suffix prevents the collisions a bare
|
||
`_post.json` would have here; phase 3 receives explicit post_record_paths, so
|
||
the name is a convention, not a discovery key).
|
||
|
||
Simpler than Patreon (no Mux/yt-dlp video branch) — the one special file is
|
||
the ugoira frame zip, downloaded as-is; FC's archive-containment import
|
||
extracts the frames, and the frame DELAYS ride the post record (the zip
|
||
carries none — a future ugoira→video conversion needs them).
|
||
|
||
PURE: no DB; the seen-skip is an injected predicate. FC runs on a plain-HTTP
|
||
homelab; nothing here uses a secure-context Web API.
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import json
|
||
import logging
|
||
import re
|
||
import time
|
||
from collections.abc import Callable
|
||
from pathlib import Path
|
||
|
||
import requests
|
||
|
||
from .native_ingest_common import (
|
||
BaseNativeDownloader,
|
||
MediaOutcome,
|
||
PostRecordOutcome,
|
||
)
|
||
from .pixiv_client import PIXIV_APP_HEADERS, rating_label
|
||
|
||
log = logging.getLogger(__name__)
|
||
|
||
# Control chars (0x00–0x1f + 0x7f DEL) — gallery-dl's default `path-remove`.
|
||
_GDL_PATH_REMOVE_RE = re.compile(r"[\x00-\x1f\x7f]")
|
||
|
||
|
||
def gdl_clean_filename(name: str) -> str:
|
||
"""Reproduce gallery-dl's on-disk filename EXACTLY as it wrote it on this
|
||
Linux host, so the tier-2 disk-skip recognizes pre-cutover files instead of
|
||
re-downloading them.
|
||
|
||
gallery-dl's PathFormat.build_filename is `clean_path(clean_segment(name))`.
|
||
On Linux (verified against gallery-dl 1.32.5 path.py) the defaults resolve to:
|
||
- path-restrict "auto" → "/" → clean_segment replaces ONLY "/" → "_"
|
||
- path-remove "\\x00-\\x1f\\x7f" → clean_path DELETES control chars
|
||
- path-strip "auto" → "" → NO trailing dot/space stripping
|
||
Crucially it does NOT touch the Windows-forbidden set (<>:"|?*) — those stay
|
||
raw in titles on disk. A stricter sanitizer here would rename any such title,
|
||
miss the on-disk match, and re-pull the whole work. Order mirrors gallery-dl
|
||
(segment inner, path outer); for these disjoint char sets it's commutative.
|
||
"""
|
||
return _GDL_PATH_REMOVE_RE.sub("", name.replace("/", "_"))
|
||
|
||
# Enrichment keys copied verbatim from the app-API work dict into the post
|
||
# record (they're already JSON scalars/objects). Everything lands in
|
||
# Post.raw_metadata via the importer, so the archive keeps pixiv's stats and
|
||
# structure without a schema change.
|
||
_WORK_PASSTHROUGH_KEYS = (
|
||
"type",
|
||
"page_count",
|
||
"width",
|
||
"height",
|
||
"total_view",
|
||
"total_bookmarks",
|
||
"total_comments",
|
||
"is_bookmarked",
|
||
"illust_ai_type",
|
||
"series",
|
||
)
|
||
|
||
|
||
class PixivDownloader(BaseNativeDownloader):
|
||
"""Download resolved Pixiv media to gallery-dl's on-disk layout.
|
||
Subclasses BaseNativeDownloader for the shared streaming GET
|
||
(transient-retry + Range-resume) and validation/quarantine. PURE: no DB."""
|
||
|
||
def __init__(
|
||
self,
|
||
images_root: Path,
|
||
cookies_path: str | None = None,
|
||
*,
|
||
validate: bool = True,
|
||
rate_limit: float = 0.0,
|
||
session: requests.Session | None = None,
|
||
):
|
||
super().__init__(
|
||
images_root, cookies_path, platform="pixiv",
|
||
validate=validate, rate_limit=rate_limit, session=session,
|
||
)
|
||
if session is None:
|
||
# i.pximg.net 403s any GET without the app Referer; mirror the
|
||
# client's full app-header profile (gallery-dl serves media off
|
||
# the same session it drives the API with). An injected session
|
||
# (tests) owns its own headers.
|
||
self.session.headers.update(PIXIV_APP_HEADERS)
|
||
|
||
# -- public ------------------------------------------------------------
|
||
|
||
def download_post(
|
||
self,
|
||
post: dict,
|
||
media_items: list,
|
||
artist_slug: str,
|
||
*,
|
||
is_seen: Callable[[object], bool] = lambda m: False,
|
||
should_stop: Callable[[], bool] = lambda: False,
|
||
recapture: bool = False,
|
||
) -> list[MediaOutcome]:
|
||
"""Download every media item of one work; return per-item outcomes.
|
||
Mirrors SubscribeStarDownloader.download_post (two-tier skip, mid-post
|
||
time-box, recapture surfacing)."""
|
||
flat_dir = self._flat_dir(artist_slug)
|
||
outcomes: list[MediaOutcome] = []
|
||
for media in media_items:
|
||
if should_stop():
|
||
break
|
||
try:
|
||
outcomes.append(
|
||
self._download_one(
|
||
post, media, flat_dir, artist_slug, is_seen,
|
||
recapture=recapture,
|
||
)
|
||
)
|
||
except Exception as exc: # resilient: isolate one item's failure
|
||
log.warning(
|
||
"Pixiv media failed (work %s, %s): %s",
|
||
post.get("id"), getattr(media, "media_id", "?"), exc,
|
||
)
|
||
outcomes.append(
|
||
MediaOutcome(media=media, status="error", path=None, error=str(exc))
|
||
)
|
||
return outcomes
|
||
|
||
def _flat_dir(self, artist_slug: str) -> Path:
|
||
# Double platform segment — gallery-dl layout parity (module docstring).
|
||
return self.images_root / artist_slug / "pixiv" / "pixiv"
|
||
|
||
# -- per-item ----------------------------------------------------------
|
||
|
||
def _download_one(
|
||
self,
|
||
post: dict,
|
||
media,
|
||
flat_dir: Path,
|
||
artist_slug: str,
|
||
is_seen: Callable[[object], bool],
|
||
*,
|
||
recapture: bool = False,
|
||
) -> MediaOutcome:
|
||
seen = is_seen(media)
|
||
if seen and not recapture:
|
||
return MediaOutcome(media=media, status="skipped_seen", path=None, error=None)
|
||
|
||
# The client's filename already carries the {id}_{title50}_{NN} shape
|
||
# (raw title, gallery-dl-template order); clean it to the byte-exact
|
||
# name gallery-dl wrote on disk so tier-2 disk-skip matches (else a
|
||
# re-download of the whole work). See gdl_clean_filename.
|
||
media_path = flat_dir / gdl_clean_filename(media.filename)
|
||
|
||
if media_path.exists(): # tier-2: already on disk
|
||
return MediaOutcome(
|
||
media=media, status="skipped_disk", path=media_path, error=None
|
||
)
|
||
# recapture: a seen item not on disk is NOT re-downloaded (recovery's job).
|
||
if seen:
|
||
return MediaOutcome(media=media, status="skipped_seen", path=None, error=None)
|
||
|
||
flat_dir.mkdir(parents=True, exist_ok=True)
|
||
if self._rate_limit > 0:
|
||
time.sleep(self._rate_limit)
|
||
|
||
out_path = self._fetch_get(media.url, media_path)
|
||
reason, quarantine_dest = self._validate_path(out_path, artist_slug, media.url)
|
||
if reason is not None:
|
||
return MediaOutcome(
|
||
media=media, status="quarantined", path=quarantine_dest, error=reason,
|
||
)
|
||
self._write_minimal_sidecar(post, out_path, source_url=media.url)
|
||
return MediaOutcome(media=media, status="downloaded", path=out_path, error=None)
|
||
|
||
# -- post record ---------------------------------------------------------
|
||
|
||
def write_post_record(self, post: dict, artist_slug: str) -> PostRecordOutcome:
|
||
"""Write the post-first `_post_<id>.json` — the sole writer of the post
|
||
body/metadata on the native path. Beyond the standard body fields, the
|
||
record carries pixiv's own structure (tags + EN translations, rating,
|
||
series, view/bookmark counts, AI flag, dimensions, author, ugoira frame
|
||
delays) so the archive keeps what the platform knows about the work."""
|
||
attrs = post.get("attributes") or {}
|
||
work = post.get("_work") or {}
|
||
title = attrs.get("title") if isinstance(attrs.get("title"), str) else None
|
||
post_type = attrs.get("post_type") if isinstance(attrs.get("post_type"), str) else None
|
||
pid = str(post.get("id") or "")
|
||
if not pid:
|
||
return PostRecordOutcome(
|
||
path=None, post_type=post_type, title=title, body_chars=0,
|
||
)
|
||
|
||
content = attrs.get("content")
|
||
content = content if isinstance(content, str) else ""
|
||
data: dict = {
|
||
"category": "pixiv",
|
||
"id": pid,
|
||
"title": title or "",
|
||
"content": content,
|
||
"published_at": attrs.get("published_at"),
|
||
# The post permalink is synthesized by platforms/pixiv.py
|
||
# derive_post_url from `id` at parse time — no url key here.
|
||
"rating": rating_label(work.get("x_restrict")),
|
||
}
|
||
for key in _WORK_PASSTHROUGH_KEYS:
|
||
if key in work:
|
||
data[key] = work[key]
|
||
tags = work.get("tags")
|
||
if isinstance(tags, list):
|
||
data["tags"] = [
|
||
{
|
||
"name": t.get("name"),
|
||
"translated_name": t.get("translated_name"),
|
||
}
|
||
for t in tags
|
||
if isinstance(t, dict)
|
||
]
|
||
user = work.get("user")
|
||
if isinstance(user, dict):
|
||
data["user"] = {
|
||
"id": user.get("id"),
|
||
"account": user.get("account"),
|
||
"name": user.get("name"),
|
||
}
|
||
# Memoized by extract_media's ugoira branch; the zip has no timings.
|
||
frames = work.get("_ugoira_frames")
|
||
if frames:
|
||
data["ugoira_frames"] = frames
|
||
|
||
flat_dir = self._flat_dir(artist_slug)
|
||
flat_dir.mkdir(parents=True, exist_ok=True)
|
||
path = flat_dir / f"_post_{pid}.json"
|
||
path.write_text(json.dumps(data, indent=2, ensure_ascii=False))
|
||
return PostRecordOutcome(
|
||
path=path, post_type=post_type, title=title, body_chars=len(content),
|
||
)
|