/. The chapter endpoint always prepends its own
+ # , so keep the stored content heading-free.
+ for child in list(body.children):
+ if getattr(child, "name", None) is None:
+ continue # NavigableString / text node — skip
+ if not child.get_text(strip=True):
+ child.decompose()
+ continue
+ if child.name in ("h1", "h2", "h3"):
+ child.decompose()
+ break
+
+ return body.decode_contents(), []
+
+
+@router.post("/api/library/convert-to-db/{filename:path}")
+async def convert_to_db(filename: str):
+ """Convert a file-based EPUB to DB storage."""
+ if is_db_filename(filename):
+ return JSONResponse({"error": "Already a DB book"}, status_code=400)
+
+ old_path = resolve_library_path(filename)
+ if old_path is None or not old_path.exists():
+ return JSONResponse({"error": "File not found"}, status_code=404)
+ if old_path.suffix.lower() != ".epub":
+ return JSONResponse({"error": "Only EPUB files can be converted"}, status_code=400)
+
+ with get_db_conn() as conn:
+ with conn.cursor() as cur:
+ cur.execute(
+ "SELECT title, author, publisher, series, series_index, series_suffix "
+ "FROM library WHERE filename = %s",
+ (filename,),
+ )
+ row = cur.fetchone()
+ if not row:
+ return JSONResponse({"error": "Book not in library"}, status_code=404)
+ title, author, publisher, series, series_index, series_suffix = row
+
+ # Extract chapters from EPUB
+ try:
+ spine = _epub_spine(old_path)
+ chapters = []
+ with zf.ZipFile(old_path, "r") as z:
+ for entry in spine:
+ try:
+ xhtml = z.read(entry["href"]).decode("utf-8", errors="replace")
+ except KeyError:
+ continue
+ inner, _ = _epub_body_inner(xhtml, z, entry["href"])
+ if inner.strip():
+ chapters.append({"title": entry["title"], "content_html": inner})
+ except Exception as e:
+ return JSONResponse({"error": f"Failed to extract EPUB: {e}"}, status_code=500)
+
+ if not chapters:
+ return JSONResponse({"error": "No chapters found"}, status_code=400)
+
+ base_fn = make_rel_path(
+ media_type="db",
+ publisher=publisher or "",
+ author=author or "",
+ title=title or "",
+ series=series or "",
+ series_index=series_index or 0,
+ series_suffix=series_suffix or "",
+ ).as_posix()
+
+ with get_db_conn() as conn:
+ with conn:
+ new_fn = ensure_unique_db_filename(conn, base_fn)
+ with conn.cursor() as cur:
+ # Insert new library row
+ cur.execute(
+ """
+ INSERT INTO library (filename, media_type, storage_type, title, author, publisher,
+ has_cover, series, series_index, series_suffix, publication_status,
+ source_url, publish_date, description, archived, want_to_read,
+ needs_review, rating, created_at, updated_at)
+ SELECT %s, media_type, 'db', title, author, publisher,
+ has_cover, series, series_index, series_suffix, publication_status,
+ source_url, publish_date, description, archived, want_to_read,
+ needs_review, rating, created_at, NOW()
+ FROM library WHERE filename = %s
+ """,
+ (new_fn, filename),
+ )
+ # Migrate child tables
+ cur.execute("UPDATE book_tags SET filename = %s WHERE filename = %s", (new_fn, filename))
+ cur.execute("UPDATE reading_progress SET filename = %s WHERE filename = %s", (new_fn, filename))
+ cur.execute(
+ "INSERT INTO reading_sessions (filename, read_at) SELECT %s, read_at FROM reading_sessions WHERE filename = %s",
+ (new_fn, filename),
+ )
+ cur.execute("DELETE FROM reading_sessions WHERE filename = %s", (filename,))
+ cur.execute("UPDATE bookmarks SET filename = %s WHERE filename = %s", (new_fn, filename))
+ cur.execute(
+ "INSERT INTO library_cover_cache (filename, mime_type, thumb_webp, updated_at) "
+ "SELECT %s, mime_type, thumb_webp, updated_at FROM library_cover_cache WHERE filename = %s",
+ (new_fn, filename),
+ )
+ cur.execute("DELETE FROM library_cover_cache WHERE filename = %s", (filename,))
+
+ # Insert chapters
+ for idx, ch in enumerate(chapters):
+ upsert_chapter(conn, new_fn, idx, ch["title"], ch["content_html"])
+
+ with conn.cursor() as cur:
+ cur.execute("DELETE FROM library WHERE filename = %s", (filename,))
+
+ try:
+ old_path.unlink()
+ prune_empty_dirs(old_path.parent)
+ except Exception:
+ pass
+
+ return JSONResponse({"ok": True, "new_filename": new_fn})
+
+
+# ---------------------------------------------------------------------------
+# Fase 5 — DB → EPUB export
+# ---------------------------------------------------------------------------
+
+def _rewrite_db_images_for_epub(content_html: str, seen: dict[str, str]) -> tuple[str, list[dict]]:
+ """Replace /library/db-images/... img src with EPUB-internal paths.
+
+ seen: sha256 → epub_path (deduplication across chapters)
+ Returns (modified_html, new_image_dicts) where dicts have epub_path/data/media_type.
+ """
+ soup = BeautifulSoup(content_html, "html.parser")
+ new_images: list[dict] = []
+ for img in soup.find_all("img"):
+ src = img.get("src", "")
+ if not src.startswith("/library/db-images/"):
+ continue
+ rel = src[len("/library/db-images/"):]
+ img_file = IMAGES_DIR / rel
+ if not img_file.exists():
+ img.decompose()
+ continue
+ sha256 = img_file.stem
+ ext = img_file.suffix.lower()
+ if sha256 not in seen:
+ epub_path = f"OEBPS/Images/{sha256}{ext}"
+ seen[sha256] = epub_path
+ mime = {".jpg": "image/jpeg", ".png": "image/png",
+ ".webp": "image/webp", ".gif": "image/gif"}.get(ext, "image/jpeg")
+ new_images.append({"epub_path": epub_path, "data": img_file.read_bytes(), "media_type": mime})
+ img["src"] = f"../Images/{sha256}{ext}"
+ return str(soup), new_images
+
+
+@router.get("/api/library/export-epub/{filename:path}")
+async def export_epub(filename: str):
+ """Export a DB-stored book as an EPUB download (no file written to disk)."""
+ if not is_db_filename(filename):
+ return JSONResponse({"error": "Not a DB book"}, status_code=400)
+
+ with get_db_conn() as conn:
+ with conn.cursor() as cur:
+ cur.execute(
+ """SELECT title, author, publisher, series, series_index, publication_status,
+ source_url, description, publish_date
+ FROM library WHERE filename = %s""",
+ (filename,),
+ )
+ meta_row = cur.fetchone()
+ if not meta_row:
+ return JSONResponse({"error": "Not found"}, status_code=404)
+
+ cur.execute(
+ "SELECT tag, tag_type FROM book_tags WHERE filename = %s ORDER BY tag_type, tag",
+ (filename,),
+ )
+ tag_rows = cur.fetchall()
+
+ cur.execute(
+ "SELECT chapter_index, title, content FROM book_chapters "
+ "WHERE filename = %s ORDER BY chapter_index",
+ (filename,),
+ )
+ ch_rows = cur.fetchall()
+
+ cur.execute(
+ "SELECT thumb_webp FROM library_cover_cache WHERE filename = %s",
+ (filename,),
+ )
+ cover_row = cur.fetchone()
+
+ title, author, publisher, series, series_index, pub_status, source_url, description, pub_date = meta_row
+ cover_data: bytes | None = bytes(cover_row[0]) if cover_row and cover_row[0] else None
+
+ genres = [t for t, tp in tag_rows if tp == "genre"]
+ subgenres = [t for t, tp in tag_rows if tp == "subgenre"]
+ tags = [t for t, tp in tag_rows if tp in ("tag", "subject")]
+
+ book_info = {
+ "genres": genres, "subgenres": subgenres, "tags": tags,
+ "description": description or "",
+ "source_url": source_url or "",
+ "publisher": publisher or "",
+ "series": series or "",
+ "series_index": series_index or 1,
+ "publication_status": pub_status or "",
+ "updated_date": pub_date.isoformat() if pub_date else "",
+ }
+
+ seen_images: dict[str, str] = {}
+ chapters = []
+ for ch_idx, ch_title, ch_content in ch_rows:
+ modified_html, new_imgs = _rewrite_db_images_for_epub(ch_content, seen_images)
+ chapter_xhtml = make_chapter_xhtml(ch_title or f"Chapter {ch_idx + 1}", modified_html, ch_idx + 1)
+ chapters.append({"title": ch_title or f"Chapter {ch_idx + 1}", "xhtml": chapter_xhtml, "images": new_imgs})
+
+ try:
+ break_img_data = open("static/break.png", "rb").read()
+ except Exception:
+ break_img_data = b""
+
+ book_id = str(uuid.uuid4())
+ epub_bytes = make_epub(
+ title or "Untitled", author or "Unknown", chapters,
+ cover_data, break_img_data, book_id, book_info,
+ )
+
+ safe_title = re.sub(r'[^\w\-. ]', '', (title or "book")).strip() or "book"
+ return Response(
+ content=epub_bytes,
+ media_type="application/epub+zip",
+ headers={"Content-Disposition": f'attachment; filename="{safe_title}.epub"'},
+ )
+
+
@router.get("/library/read/{filename:path}", response_class=HTMLResponse)
async def reader_page(filename: str, request: Request):
+ with get_db_conn() as conn:
+ with conn.cursor() as cur:
+ cur.execute("SELECT title FROM library WHERE filename = %s", (filename,))
+ row = cur.fetchone()
+
+ if is_db_filename(filename):
+ if not row:
+ return HTMLResponse("Not found", status_code=404)
+ title = row[0] if row[0] else filename
+ return templates.TemplateResponse(request, "reader.html", {
+ "filename": filename,
+ "title": title,
+ "format": "epub",
+ "epub_url": "",
+ })
+
path = resolve_library_path(filename)
if path is None:
return HTMLResponse("Not found", status_code=404)
if not path.exists():
return HTMLResponse("Not found", status_code=404)
- with get_db_conn() as conn:
- with conn.cursor() as cur:
- cur.execute("SELECT title FROM library WHERE filename = %s", (filename,))
- row = cur.fetchone()
- title = row[0] if row and row[0] else filename
+ title = row[0] if row and row[0] else filename
fmt = path.suffix.lower().lstrip(".")
return templates.TemplateResponse(request, "reader.html", {
"filename": filename,
diff --git a/containers/novela/routers/search.py b/containers/novela/routers/search.py
new file mode 100644
index 0000000..8325bb0
--- /dev/null
+++ b/containers/novela/routers/search.py
@@ -0,0 +1,63 @@
+"""search.py — Full-text search over DB-stored book chapters."""
+
+from fastapi import APIRouter, Request
+from fastapi.responses import HTMLResponse, JSONResponse
+from fastapi.templating import Jinja2Templates
+
+from db import get_db_conn
+
+router = APIRouter()
+templates = Jinja2Templates(directory="templates")
+
+
+@router.get("/search", response_class=HTMLResponse)
+async def search_page(request: Request):
+ return templates.TemplateResponse(request, "search.html", {"active": "search"})
+
+
+@router.get("/api/search")
+async def api_search(q: str = ""):
+ q = q.strip()
+ if not q or len(q) > 500:
+ return JSONResponse([])
+ with get_db_conn() as conn:
+ with conn.cursor() as cur:
+ cur.execute(
+ """
+ SELECT
+ l.filename,
+ l.title,
+ l.author,
+ bc.chapter_index,
+ bc.title AS chapter_title,
+ ts_headline(
+ 'simple', bc.content,
+ plainto_tsquery('simple', %s),
+ 'MaxFragments=1, MaxWords=25, MinWords=8, StartSel=, StopSel='
+ ) AS snippet,
+ ts_rank(bc.content_tsv, plainto_tsquery('simple', %s)) AS rank
+ FROM book_chapters bc
+ JOIN library l ON l.filename = bc.filename
+ WHERE (bc.content_tsv @@ plainto_tsquery('simple', %s)
+ OR LOWER(bc.title) LIKE LOWER('%%' || %s || '%%'))
+ AND NOT l.archived
+ ORDER BY rank DESC, bc.chapter_index ASC
+ LIMIT 30
+ """,
+ (q, q, q, q),
+ )
+ rows = cur.fetchall()
+
+ results = [
+ {
+ "filename": r[0],
+ "title": r[1] or "",
+ "author": r[2] or "",
+ "chapter_index": r[3],
+ "chapter_title": r[4] or "",
+ "snippet": r[5] or "",
+ "rank": float(r[6]),
+ }
+ for r in rows
+ ]
+ return JSONResponse(results)
diff --git a/containers/novela/scrapers/__init__.py b/containers/novela/scrapers/__init__.py
index 3fdb823..18fb974 100644
--- a/containers/novela/scrapers/__init__.py
+++ b/containers/novela/scrapers/__init__.py
@@ -1,9 +1,11 @@
from .base import BaseScraper
+from .archiveofourown import ArchiveOfOurOwnScraper
from .awesomedude import AwesomeDudeScraper
from .gayauthors import GayAuthorsScraper
# Register scrapers in priority order (first match wins)
_SCRAPERS: list[type[BaseScraper]] = [
+ ArchiveOfOurOwnScraper,
AwesomeDudeScraper,
GayAuthorsScraper,
]
diff --git a/containers/novela/scrapers/archiveofourown.py b/containers/novela/scrapers/archiveofourown.py
new file mode 100644
index 0000000..f82b02f
--- /dev/null
+++ b/containers/novela/scrapers/archiveofourown.py
@@ -0,0 +1,206 @@
+import re
+from urllib.parse import urljoin
+
+import httpx
+from bs4 import BeautifulSoup
+
+from .base import BaseScraper
+
+AO3_BASE = "https://archiveofourown.org"
+
+
+class ArchiveOfOurOwnScraper(BaseScraper):
+
+ @classmethod
+ def matches(cls, url: str) -> bool:
+ return "archiveofourown.org" in url
+
+ def _work_base_url(self, url: str) -> str:
+ """Strip chapter segment and query string; return /works/NNNNNN base URL."""
+ m = re.search(r"(https?://[^/]+/works/\d+)", url)
+ return m.group(1) if m else url.rstrip("/")
+
+ async def login(self, client: httpx.AsyncClient, username: str, password: str) -> bool:
+ r = await client.get(AO3_BASE + "/users/login")
+ soup = BeautifulSoup(r.text, "html.parser")
+ token_el = soup.find("input", {"name": "authenticity_token"})
+ token = token_el["value"] if token_el else ""
+ resp = await client.post(
+ AO3_BASE + "/users/login",
+ data={
+ "user[login]": username,
+ "user[password]": password,
+ "authenticity_token": token,
+ "commit": "Log in",
+ },
+ )
+ # Successful login redirects away from the login page
+ return "/users/login" not in str(resp.url)
+
+ async def fetch_book_info(self, client: httpx.AsyncClient, url: str) -> dict:
+ base_url = self._work_base_url(url)
+ r = await client.get(base_url, params={"view_adult": "true"})
+ soup = BeautifulSoup(r.text, "html.parser")
+
+ # Title
+ title_el = soup.find("h2", class_="title")
+ book_title = title_el.get_text(strip=True) if title_el else "Unknown title"
+
+ # Author — can be multiple; Anonymous if no author link
+ byline = soup.find("h3", class_="byline")
+ if byline:
+ author_links = byline.find_all("a", rel="author")
+ author = ", ".join(a.get_text(strip=True) for a in author_links) if author_links else "Anonymous"
+ else:
+ author = "Anonymous"
+
+ # Tags from dl.work.meta.group
+ meta_dl = soup.find("dl", class_="work")
+
+ def _tag_list(dl, css_class: str) -> list[str]:
+ dd = dl.find("dd", class_=css_class) if dl else None
+ return [a.get_text(strip=True) for a in dd.find_all("a")] if dd else []
+
+ fandoms = _tag_list(meta_dl, "fandom")
+ ratings = _tag_list(meta_dl, "rating")
+ categories = _tag_list(meta_dl, "category")
+ relationships = _tag_list(meta_dl, "relationship")
+ characters = _tag_list(meta_dl, "character")
+ freeform_tags = _tag_list(meta_dl, "freeform")
+
+ # Series
+ series = ""
+ series_index_hint = 0
+ if meta_dl:
+ series_dd = meta_dl.find("dd", class_="series")
+ if series_dd:
+ series_link = series_dd.find("a")
+ if series_link:
+ series = series_link.get_text(strip=True)
+ pos_span = series_dd.find("span", class_="position")
+ if pos_span:
+ m = re.search(r"Part\s+(\d+)", pos_span.get_text(), re.I)
+ if m:
+ series_index_hint = int(m.group(1))
+
+ # Stats (nested dl.stats inside the meta dl)
+ published = ""
+ updated_date = ""
+ publication_status = ""
+ if meta_dl:
+ stats_dl = meta_dl.find("dl", class_="stats")
+ if stats_dl:
+ pub_dd = stats_dl.find("dd", class_="published")
+ if pub_dd:
+ published = pub_dd.get_text(strip=True)
+
+ status_dt = stats_dl.find("dt", class_="status")
+ status_dd = stats_dl.find("dd", class_="status")
+ if status_dt and status_dd:
+ updated_date = status_dd.get_text(strip=True)
+ if "Completed" in status_dt.get_text():
+ publication_status = "Complete"
+ else:
+ publication_status = "Ongoing"
+ else:
+ # No status entry — determine from chapters count (N/N = complete)
+ updated_date = published
+ chapters_dd = stats_dl.find("dd", class_="chapters")
+ if chapters_dd:
+ m = re.match(r"(\d+)/(\d+|\?)", chapters_dd.get_text(strip=True))
+ if m:
+ if m.group(2) == "?":
+ publication_status = "Ongoing"
+ elif m.group(1) == m.group(2):
+ publication_status = "Complete"
+
+ # Summary
+ description = ""
+ summary_div = soup.find("div", class_="summary")
+ if summary_div:
+ userstuff = summary_div.find("blockquote", class_="userstuff")
+ if userstuff:
+ paras = [p.get_text(strip=True) for p in userstuff.find_all("p") if p.get_text().strip()]
+ description = "\n\n".join(paras) if paras else userstuff.get_text(strip=True)
+
+ # Chapter list via /navigate
+ chapter_links = []
+ chapter_method = "html_scan"
+ try:
+ nr = await client.get(base_url + "/navigate", params={"view_adult": "true"})
+ nsoup = BeautifulSoup(nr.text, "html.parser")
+ chapter_ol = nsoup.find("ol", class_="chapter")
+ if chapter_ol:
+ for li in chapter_ol.find_all("li"):
+ a = li.find("a", href=True)
+ if a:
+ chapter_links.append({
+ "url": urljoin(AO3_BASE, a["href"]),
+ "title": a.get_text(strip=True),
+ })
+ except Exception:
+ pass
+
+ # Fallback: single-chapter work — the work page itself is the content
+ if not chapter_links:
+ chapter_method = "fallback_numeric"
+ chapter_links.append({"url": base_url, "title": book_title})
+
+ # Map to Novela tag structure:
+ # fandoms → genres
+ # ratings + categories → subgenres
+ # relationships + characters + freeform → tags
+ return {
+ "title": book_title,
+ "author": author,
+ "publisher": "Archive of Our Own",
+ "series": series,
+ "series_index_hint": series_index_hint,
+ "genres": fandoms,
+ "subgenres": ratings + categories,
+ "tags": relationships + characters + freeform_tags,
+ "description": description,
+ "updated_date": updated_date,
+ "publication_status": publication_status,
+ "source_url": base_url,
+ "chapters": chapter_links,
+ "chapter_method": chapter_method,
+ }
+
+ async def fetch_chapter(self, client: httpx.AsyncClient, ch: dict) -> dict:
+ r = await client.get(ch["url"], params={"view_adult": "true"})
+ soup = BeautifulSoup(r.text, "html.parser")
+
+ # Chapter title and optional summary from the chapter preface
+ title = ch["title"]
+ chapter_summary_bq = None
+ chapters_div = soup.find("div", id="chapters")
+ if chapters_div:
+ chapter_div = chapters_div.find("div", class_="chapter")
+ if chapter_div:
+ title_el = chapter_div.find("h3", class_="title")
+ if title_el:
+ raw = title_el.get_text(strip=True)
+ if raw:
+ title = raw
+ summary_div = chapter_div.find("div", class_="summary")
+ if summary_div:
+ chapter_summary_bq = summary_div.find("blockquote", class_="userstuff")
+
+ # Content: div.userstuff inside #chapters (excludes author notes)
+ content_el = None
+ if chapters_div:
+ content_el = chapters_div.find("div", class_="userstuff")
+ if not content_el:
+ content_el = soup.find("div", attrs={"role": "article"})
+
+ # Prepend chapter summary as blockquote before story content
+ if chapter_summary_bq and content_el:
+ content_el.insert(0, chapter_summary_bq)
+
+ return {
+ "title": title,
+ "content_el": content_el,
+ "selector_id": content_el.get("id") if content_el else None,
+ "selector_class": " ".join(content_el.get("class", [])) if content_el else None,
+ }
diff --git a/containers/novela/static/conversion.js b/containers/novela/static/conversion.js
index 12ba5ab..7e8b37b 100644
--- a/containers/novela/static/conversion.js
+++ b/containers/novela/static/conversion.js
@@ -71,9 +71,14 @@ function connectConversionStream(job_id) {
document.querySelectorAll('.chapter-item').forEach(el => el.className = 'chapter-item done');
document.getElementById('result-meta').innerHTML =
`${esc(d.title)}
${d.chapters} chapters successfully converted`;
- document.getElementById('download-btn').onclick = () => {
- window.location = `/download/${encodeURIComponent(d.filename)}`;
- };
+ const dlBtn = document.getElementById('download-btn');
+ if (d.storage_type === 'db') {
+ dlBtn.querySelector('span') && (dlBtn.querySelector('span').textContent = 'Export EPUB');
+ dlBtn.onclick = () => { window.location = `/api/library/export-epub/${encodeURIComponent(d.filename)}`; };
+ } else {
+ dlBtn.querySelector('span') && (dlBtn.querySelector('span').textContent = 'Download EPUB');
+ dlBtn.onclick = () => { window.location = `/download/${encodeURIComponent(d.filename)}`; };
+ }
document.getElementById('book-detail-btn').onclick = () => {
window.location = `/library/book/${encodeURIComponent(d.filename)}`;
};
diff --git a/containers/novela/static/editor.css b/containers/novela/static/editor.css
index 21ee86b..e61dd1c 100644
--- a/containers/novela/static/editor.css
+++ b/containers/novela/static/editor.css
@@ -30,6 +30,13 @@ html, body { height: 100%; background: var(--bg); color: var(--text); font-famil
text-align: center; overflow: hidden; text-overflow: ellipsis; white-space: nowrap;
}
+.chapter-title-input {
+ flex: 1; font-size: 0.72rem; font-family: var(--mono); color: var(--text);
+ background: var(--surface2); border: 1px solid var(--border); border-radius: var(--radius);
+ padding: 0.25rem 0.5rem; outline: none; min-width: 0;
+}
+.chapter-title-input:focus { border-color: var(--accent); }
+
.header-actions { display: flex; align-items: center; gap: 0.5rem; flex-shrink: 0; }
.save-status {
diff --git a/containers/novela/static/editor.js b/containers/novela/static/editor.js
index 9ca9d63..78c9626 100644
--- a/containers/novela/static/editor.js
+++ b/containers/novela/static/editor.js
@@ -1,20 +1,26 @@
require.config({ paths: { vs: 'https://cdn.jsdelivr.net/npm/monaco-editor@0.45.0/min/vs' } });
-const { filename } = EDITOR;
+const { filename, is_db } = EDITOR;
let editor = null;
let chapters = [];
let currentIndex = -1;
let dirty = new Set(); // indices with unsaved changes
let pendingContent = new Map(); // index -> modified content not yet saved
+let pendingTitles = new Map(); // index -> modified title not yet saved (DB only)
let loadingChapter = false; // suppress dirty events during setValue
let saving = false;
// ── Init Monaco ───────────────────────────────────────────────────────────────
require(['vs/editor/editor.main'], function () {
+ if (is_db) {
+ document.getElementById('header-chapter').style.display = 'none';
+ document.getElementById('chapter-title-input').style.display = '';
+ }
+
editor = monaco.editor.create(document.getElementById('editor-pane'), {
- language: 'xml',
+ language: is_db ? 'html' : 'xml',
theme: 'vs-dark',
wordWrap: 'on',
minimap: { enabled: true },
@@ -39,6 +45,19 @@ require(['vs/editor/editor.main'], function () {
// Ctrl+S / Cmd+S
editor.addCommand(monaco.KeyMod.CtrlCmd | monaco.KeyCode.KeyS, saveChapter);
+ if (is_db) {
+ document.getElementById('chapter-title-input').addEventListener('input', () => {
+ if (currentIndex >= 0) {
+ pendingTitles.set(currentIndex, document.getElementById('chapter-title-input').value);
+ dirty.add(currentIndex);
+ renderChapterList();
+ setStatus('dirty', 'Unsaved changes');
+ document.getElementById('btn-save').disabled = false;
+ updateSaveAll();
+ }
+ });
+ }
+
loadChapterList();
});
@@ -57,6 +76,7 @@ async function loadChapterList(targetIndex = 0) {
currentIndex = -1;
dirty.clear();
pendingContent.clear();
+ pendingTitles.clear();
renderChapterList();
document.getElementById('header-chapter').textContent = 'No chapters';
document.getElementById('btn-save').disabled = true;
@@ -94,6 +114,11 @@ async function switchChapter(index) {
if (dirty.has(currentIndex) && editor) {
pendingContent.set(currentIndex, editor.getValue());
}
+ // Preserve title input for DB books
+ if (is_db && currentIndex >= 0) {
+ const inp = document.getElementById('chapter-title-input');
+ if (inp) pendingTitles.set(currentIndex, inp.value);
+ }
loadChapter(index);
}
@@ -102,19 +127,19 @@ async function loadChapter(index) {
document.getElementById('btn-save').disabled = true;
document.getElementById('btn-break').disabled = true;
document.getElementById('btn-del-page').disabled = true;
- document.getElementById('header-chapter').textContent = 'Loading…';
+ if (!is_db) document.getElementById('header-chapter').textContent = 'Loading…';
let content, title;
if (pendingContent.has(index)) {
content = pendingContent.get(index);
- title = chapters[index]?.title ?? '';
+ title = pendingTitles.has(index) ? pendingTitles.get(index) : (chapters[index]?.title ?? '');
} else {
const resp = await fetch(`/api/edit/chapter/${index}/${encodeURIComponent(filename)}`);
if (!resp.ok) { setStatus('error', 'Load failed'); return; }
const data = await resp.json();
content = data.content;
- title = data.title;
+ title = pendingTitles.has(index) ? pendingTitles.get(index) : data.title;
}
currentIndex = index;
@@ -123,6 +148,7 @@ async function loadChapter(index) {
editor.setValue(content);
editor.setScrollTop(0);
loadingChapter = false;
+ editor.focus();
// Restore dirty state based on whether we loaded from pending cache
if (dirty.has(index)) {
@@ -134,7 +160,11 @@ async function loadChapter(index) {
}
renderChapterList();
- document.getElementById('header-chapter').textContent = title;
+ if (is_db) {
+ document.getElementById('chapter-title-input').value = title;
+ } else {
+ document.getElementById('header-chapter').textContent = title;
+ }
document.getElementById('btn-break').disabled = false;
document.getElementById('btn-del-page').disabled = chapters.length <= 1;
updateSaveAll();
@@ -149,18 +179,28 @@ async function saveChapter() {
setStatus('saving', 'Saving…');
try {
+ const saveBody = { content: editor.getValue() };
+ if (is_db) {
+ const inp = document.getElementById('chapter-title-input');
+ saveBody.title = inp ? inp.value.trim() : (pendingTitles.get(currentIndex) || '');
+ }
const resp = await fetch(
`/api/edit/chapter/${currentIndex}/${encodeURIComponent(filename)}`,
{
method: 'POST',
headers: { 'Content-Type': 'application/json' },
- body: JSON.stringify({ content: editor.getValue() }),
+ body: JSON.stringify(saveBody),
}
);
const data = await resp.json();
if (data.ok) {
dirty.delete(currentIndex);
pendingContent.delete(currentIndex);
+ if (is_db && chapters[currentIndex]) {
+ const saved = pendingTitles.get(currentIndex) || chapters[currentIndex].title;
+ chapters[currentIndex].title = saved || chapters[currentIndex].title;
+ pendingTitles.delete(currentIndex);
+ }
renderChapterList();
setStatus('saved', 'Saved');
setTimeout(() => setStatus('', ''), 2000);
@@ -186,9 +226,13 @@ async function saveAllChapters() {
if (btn) btn.disabled = true;
setStatus('saving', 'Saving all…');
- // Flush current editor content into pendingContent first
+ // Flush current editor content and title into pending caches first
if (currentIndex >= 0 && dirty.has(currentIndex)) {
pendingContent.set(currentIndex, editor.getValue());
+ if (is_db) {
+ const inp = document.getElementById('chapter-title-input');
+ if (inp) pendingTitles.set(currentIndex, inp.value);
+ }
}
const indices = [...dirty];
@@ -196,21 +240,29 @@ async function saveAllChapters() {
const content = pendingContent.has(i)
? pendingContent.get(i)
: (i === currentIndex ? editor.getValue() : null);
- if (!content) continue;
+ // For DB books, a title-only change has no pendingContent — still need to save
+ const hasTitleChange = is_db && pendingTitles.has(i);
+ if (!content && !hasTitleChange) continue;
try {
+ const saveBody = { content: content || '' };
+ if (is_db) saveBody.title = pendingTitles.has(i) ? pendingTitles.get(i) : (chapters[i]?.title || '');
const resp = await fetch(
`/api/edit/chapter/${i}/${encodeURIComponent(filename)}`,
{
method: 'POST',
headers: { 'Content-Type': 'application/json' },
- body: JSON.stringify({ content }),
+ body: JSON.stringify(saveBody),
}
);
const data = await resp.json();
if (data.ok) {
dirty.delete(i);
pendingContent.delete(i);
+ if (is_db && chapters[i]) {
+ chapters[i].title = pendingTitles.get(i) || chapters[i].title;
+ pendingTitles.delete(i);
+ }
}
} catch {
setStatus('error', `Save failed on chapter ${i + 1}`);
@@ -251,10 +303,11 @@ function updateSaveAll() {
function insertBreak() {
if (!editor || currentIndex < 0) return;
+ const breakSrc = is_db ? '/static/break.png' : '../Images/break.png';
const pos = editor.getPosition();
editor.executeEdits('insert-break', [{
range: new monaco.Range(pos.lineNumber, pos.column, pos.lineNumber, pos.column),
- text: '\n
, so keep the stored content heading-free.
+ for child in list(body.children):
+ if getattr(child, "name", None) is None:
+ continue # NavigableString / text node — skip
+ if not child.get_text(strip=True):
+ child.decompose()
+ continue
+ if child.name in ("h1", "h2", "h3"):
+ child.decompose()
+ break
+
+ return body.decode_contents(), []
+
+
+@router.post("/api/library/convert-to-db/{filename:path}")
+async def convert_to_db(filename: str):
+ """Convert a file-based EPUB to DB storage."""
+ if is_db_filename(filename):
+ return JSONResponse({"error": "Already a DB book"}, status_code=400)
+
+ old_path = resolve_library_path(filename)
+ if old_path is None or not old_path.exists():
+ return JSONResponse({"error": "File not found"}, status_code=404)
+ if old_path.suffix.lower() != ".epub":
+ return JSONResponse({"error": "Only EPUB files can be converted"}, status_code=400)
+
+ with get_db_conn() as conn:
+ with conn.cursor() as cur:
+ cur.execute(
+ "SELECT title, author, publisher, series, series_index, series_suffix "
+ "FROM library WHERE filename = %s",
+ (filename,),
+ )
+ row = cur.fetchone()
+ if not row:
+ return JSONResponse({"error": "Book not in library"}, status_code=404)
+ title, author, publisher, series, series_index, series_suffix = row
+
+ # Extract chapters from EPUB
+ try:
+ spine = _epub_spine(old_path)
+ chapters = []
+ with zf.ZipFile(old_path, "r") as z:
+ for entry in spine:
+ try:
+ xhtml = z.read(entry["href"]).decode("utf-8", errors="replace")
+ except KeyError:
+ continue
+ inner, _ = _epub_body_inner(xhtml, z, entry["href"])
+ if inner.strip():
+ chapters.append({"title": entry["title"], "content_html": inner})
+ except Exception as e:
+ return JSONResponse({"error": f"Failed to extract EPUB: {e}"}, status_code=500)
+
+ if not chapters:
+ return JSONResponse({"error": "No chapters found"}, status_code=400)
+
+ base_fn = make_rel_path(
+ media_type="db",
+ publisher=publisher or "",
+ author=author or "",
+ title=title or "",
+ series=series or "",
+ series_index=series_index or 0,
+ series_suffix=series_suffix or "",
+ ).as_posix()
+
+ with get_db_conn() as conn:
+ with conn:
+ new_fn = ensure_unique_db_filename(conn, base_fn)
+ with conn.cursor() as cur:
+ # Insert new library row
+ cur.execute(
+ """
+ INSERT INTO library (filename, media_type, storage_type, title, author, publisher,
+ has_cover, series, series_index, series_suffix, publication_status,
+ source_url, publish_date, description, archived, want_to_read,
+ needs_review, rating, created_at, updated_at)
+ SELECT %s, media_type, 'db', title, author, publisher,
+ has_cover, series, series_index, series_suffix, publication_status,
+ source_url, publish_date, description, archived, want_to_read,
+ needs_review, rating, created_at, NOW()
+ FROM library WHERE filename = %s
+ """,
+ (new_fn, filename),
+ )
+ # Migrate child tables
+ cur.execute("UPDATE book_tags SET filename = %s WHERE filename = %s", (new_fn, filename))
+ cur.execute("UPDATE reading_progress SET filename = %s WHERE filename = %s", (new_fn, filename))
+ cur.execute(
+ "INSERT INTO reading_sessions (filename, read_at) SELECT %s, read_at FROM reading_sessions WHERE filename = %s",
+ (new_fn, filename),
+ )
+ cur.execute("DELETE FROM reading_sessions WHERE filename = %s", (filename,))
+ cur.execute("UPDATE bookmarks SET filename = %s WHERE filename = %s", (new_fn, filename))
+ cur.execute(
+ "INSERT INTO library_cover_cache (filename, mime_type, thumb_webp, updated_at) "
+ "SELECT %s, mime_type, thumb_webp, updated_at FROM library_cover_cache WHERE filename = %s",
+ (new_fn, filename),
+ )
+ cur.execute("DELETE FROM library_cover_cache WHERE filename = %s", (filename,))
+
+ # Insert chapters
+ for idx, ch in enumerate(chapters):
+ upsert_chapter(conn, new_fn, idx, ch["title"], ch["content_html"])
+
+ with conn.cursor() as cur:
+ cur.execute("DELETE FROM library WHERE filename = %s", (filename,))
+
+ try:
+ old_path.unlink()
+ prune_empty_dirs(old_path.parent)
+ except Exception:
+ pass
+
+ return JSONResponse({"ok": True, "new_filename": new_fn})
+
+
+# ---------------------------------------------------------------------------
+# Fase 5 — DB → EPUB export
+# ---------------------------------------------------------------------------
+
+def _rewrite_db_images_for_epub(content_html: str, seen: dict[str, str]) -> tuple[str, list[dict]]:
+ """Replace /library/db-images/... img src with EPUB-internal paths.
+
+ seen: sha256 → epub_path (deduplication across chapters)
+ Returns (modified_html, new_image_dicts) where dicts have epub_path/data/media_type.
+ """
+ soup = BeautifulSoup(content_html, "html.parser")
+ new_images: list[dict] = []
+ for img in soup.find_all("img"):
+ src = img.get("src", "")
+ if not src.startswith("/library/db-images/"):
+ continue
+ rel = src[len("/library/db-images/"):]
+ img_file = IMAGES_DIR / rel
+ if not img_file.exists():
+ img.decompose()
+ continue
+ sha256 = img_file.stem
+ ext = img_file.suffix.lower()
+ if sha256 not in seen:
+ epub_path = f"OEBPS/Images/{sha256}{ext}"
+ seen[sha256] = epub_path
+ mime = {".jpg": "image/jpeg", ".png": "image/png",
+ ".webp": "image/webp", ".gif": "image/gif"}.get(ext, "image/jpeg")
+ new_images.append({"epub_path": epub_path, "data": img_file.read_bytes(), "media_type": mime})
+ img["src"] = f"../Images/{sha256}{ext}"
+ return str(soup), new_images
+
+
+@router.get("/api/library/export-epub/{filename:path}")
+async def export_epub(filename: str):
+ """Export a DB-stored book as an EPUB download (no file written to disk)."""
+ if not is_db_filename(filename):
+ return JSONResponse({"error": "Not a DB book"}, status_code=400)
+
+ with get_db_conn() as conn:
+ with conn.cursor() as cur:
+ cur.execute(
+ """SELECT title, author, publisher, series, series_index, publication_status,
+ source_url, description, publish_date
+ FROM library WHERE filename = %s""",
+ (filename,),
+ )
+ meta_row = cur.fetchone()
+ if not meta_row:
+ return JSONResponse({"error": "Not found"}, status_code=404)
+
+ cur.execute(
+ "SELECT tag, tag_type FROM book_tags WHERE filename = %s ORDER BY tag_type, tag",
+ (filename,),
+ )
+ tag_rows = cur.fetchall()
+
+ cur.execute(
+ "SELECT chapter_index, title, content FROM book_chapters "
+ "WHERE filename = %s ORDER BY chapter_index",
+ (filename,),
+ )
+ ch_rows = cur.fetchall()
+
+ cur.execute(
+ "SELECT thumb_webp FROM library_cover_cache WHERE filename = %s",
+ (filename,),
+ )
+ cover_row = cur.fetchone()
+
+ title, author, publisher, series, series_index, pub_status, source_url, description, pub_date = meta_row
+ cover_data: bytes | None = bytes(cover_row[0]) if cover_row and cover_row[0] else None
+
+ genres = [t for t, tp in tag_rows if tp == "genre"]
+ subgenres = [t for t, tp in tag_rows if tp == "subgenre"]
+ tags = [t for t, tp in tag_rows if tp in ("tag", "subject")]
+
+ book_info = {
+ "genres": genres, "subgenres": subgenres, "tags": tags,
+ "description": description or "",
+ "source_url": source_url or "",
+ "publisher": publisher or "",
+ "series": series or "",
+ "series_index": series_index or 1,
+ "publication_status": pub_status or "",
+ "updated_date": pub_date.isoformat() if pub_date else "",
+ }
+
+ seen_images: dict[str, str] = {}
+ chapters = []
+ for ch_idx, ch_title, ch_content in ch_rows:
+ modified_html, new_imgs = _rewrite_db_images_for_epub(ch_content, seen_images)
+ chapter_xhtml = make_chapter_xhtml(ch_title or f"Chapter {ch_idx + 1}", modified_html, ch_idx + 1)
+ chapters.append({"title": ch_title or f"Chapter {ch_idx + 1}", "xhtml": chapter_xhtml, "images": new_imgs})
+
+ try:
+ break_img_data = open("static/break.png", "rb").read()
+ except Exception:
+ break_img_data = b""
+
+ book_id = str(uuid.uuid4())
+ epub_bytes = make_epub(
+ title or "Untitled", author or "Unknown", chapters,
+ cover_data, break_img_data, book_id, book_info,
+ )
+
+ safe_title = re.sub(r'[^\w\-. ]', '', (title or "book")).strip() or "book"
+ return Response(
+ content=epub_bytes,
+ media_type="application/epub+zip",
+ headers={"Content-Disposition": f'attachment; filename="{safe_title}.epub"'},
+ )
+
+
@router.get("/library/read/{filename:path}", response_class=HTMLResponse)
async def reader_page(filename: str, request: Request):
+ with get_db_conn() as conn:
+ with conn.cursor() as cur:
+ cur.execute("SELECT title FROM library WHERE filename = %s", (filename,))
+ row = cur.fetchone()
+
+ if is_db_filename(filename):
+ if not row:
+ return HTMLResponse("Not found", status_code=404)
+ title = row[0] if row[0] else filename
+ return templates.TemplateResponse(request, "reader.html", {
+ "filename": filename,
+ "title": title,
+ "format": "epub",
+ "epub_url": "",
+ })
+
path = resolve_library_path(filename)
if path is None:
return HTMLResponse("Not found", status_code=404)
if not path.exists():
return HTMLResponse("Not found", status_code=404)
- with get_db_conn() as conn:
- with conn.cursor() as cur:
- cur.execute("SELECT title FROM library WHERE filename = %s", (filename,))
- row = cur.fetchone()
- title = row[0] if row and row[0] else filename
+ title = row[0] if row and row[0] else filename
fmt = path.suffix.lower().lstrip(".")
return templates.TemplateResponse(request, "reader.html", {
"filename": filename,
diff --git a/containers/novela/routers/search.py b/containers/novela/routers/search.py
new file mode 100644
index 0000000..8325bb0
--- /dev/null
+++ b/containers/novela/routers/search.py
@@ -0,0 +1,63 @@
+"""search.py — Full-text search over DB-stored book chapters."""
+
+from fastapi import APIRouter, Request
+from fastapi.responses import HTMLResponse, JSONResponse
+from fastapi.templating import Jinja2Templates
+
+from db import get_db_conn
+
+router = APIRouter()
+templates = Jinja2Templates(directory="templates")
+
+
+@router.get("/search", response_class=HTMLResponse)
+async def search_page(request: Request):
+ return templates.TemplateResponse(request, "search.html", {"active": "search"})
+
+
+@router.get("/api/search")
+async def api_search(q: str = ""):
+ q = q.strip()
+ if not q or len(q) > 500:
+ return JSONResponse([])
+ with get_db_conn() as conn:
+ with conn.cursor() as cur:
+ cur.execute(
+ """
+ SELECT
+ l.filename,
+ l.title,
+ l.author,
+ bc.chapter_index,
+ bc.title AS chapter_title,
+ ts_headline(
+ 'simple', bc.content,
+ plainto_tsquery('simple', %s),
+ 'MaxFragments=1, MaxWords=25, MinWords=8, StartSel=, StopSel='
+ ) AS snippet,
+ ts_rank(bc.content_tsv, plainto_tsquery('simple', %s)) AS rank
+ FROM book_chapters bc
+ JOIN library l ON l.filename = bc.filename
+ WHERE (bc.content_tsv @@ plainto_tsquery('simple', %s)
+ OR LOWER(bc.title) LIKE LOWER('%%' || %s || '%%'))
+ AND NOT l.archived
+ ORDER BY rank DESC, bc.chapter_index ASC
+ LIMIT 30
+ """,
+ (q, q, q, q),
+ )
+ rows = cur.fetchall()
+
+ results = [
+ {
+ "filename": r[0],
+ "title": r[1] or "",
+ "author": r[2] or "",
+ "chapter_index": r[3],
+ "chapter_title": r[4] or "",
+ "snippet": r[5] or "",
+ "rank": float(r[6]),
+ }
+ for r in rows
+ ]
+ return JSONResponse(results)
diff --git a/containers/novela/scrapers/__init__.py b/containers/novela/scrapers/__init__.py
index 3fdb823..18fb974 100644
--- a/containers/novela/scrapers/__init__.py
+++ b/containers/novela/scrapers/__init__.py
@@ -1,9 +1,11 @@
from .base import BaseScraper
+from .archiveofourown import ArchiveOfOurOwnScraper
from .awesomedude import AwesomeDudeScraper
from .gayauthors import GayAuthorsScraper
# Register scrapers in priority order (first match wins)
_SCRAPERS: list[type[BaseScraper]] = [
+ ArchiveOfOurOwnScraper,
AwesomeDudeScraper,
GayAuthorsScraper,
]
diff --git a/containers/novela/scrapers/archiveofourown.py b/containers/novela/scrapers/archiveofourown.py
new file mode 100644
index 0000000..f82b02f
--- /dev/null
+++ b/containers/novela/scrapers/archiveofourown.py
@@ -0,0 +1,206 @@
+import re
+from urllib.parse import urljoin
+
+import httpx
+from bs4 import BeautifulSoup
+
+from .base import BaseScraper
+
+AO3_BASE = "https://archiveofourown.org"
+
+
+class ArchiveOfOurOwnScraper(BaseScraper):
+
+ @classmethod
+ def matches(cls, url: str) -> bool:
+ return "archiveofourown.org" in url
+
+ def _work_base_url(self, url: str) -> str:
+ """Strip chapter segment and query string; return /works/NNNNNN base URL."""
+ m = re.search(r"(https?://[^/]+/works/\d+)", url)
+ return m.group(1) if m else url.rstrip("/")
+
+ async def login(self, client: httpx.AsyncClient, username: str, password: str) -> bool:
+ r = await client.get(AO3_BASE + "/users/login")
+ soup = BeautifulSoup(r.text, "html.parser")
+ token_el = soup.find("input", {"name": "authenticity_token"})
+ token = token_el["value"] if token_el else ""
+ resp = await client.post(
+ AO3_BASE + "/users/login",
+ data={
+ "user[login]": username,
+ "user[password]": password,
+ "authenticity_token": token,
+ "commit": "Log in",
+ },
+ )
+ # Successful login redirects away from the login page
+ return "/users/login" not in str(resp.url)
+
+ async def fetch_book_info(self, client: httpx.AsyncClient, url: str) -> dict:
+ base_url = self._work_base_url(url)
+ r = await client.get(base_url, params={"view_adult": "true"})
+ soup = BeautifulSoup(r.text, "html.parser")
+
+ # Title
+ title_el = soup.find("h2", class_="title")
+ book_title = title_el.get_text(strip=True) if title_el else "Unknown title"
+
+ # Author — can be multiple; Anonymous if no author link
+ byline = soup.find("h3", class_="byline")
+ if byline:
+ author_links = byline.find_all("a", rel="author")
+ author = ", ".join(a.get_text(strip=True) for a in author_links) if author_links else "Anonymous"
+ else:
+ author = "Anonymous"
+
+ # Tags from dl.work.meta.group
+ meta_dl = soup.find("dl", class_="work")
+
+ def _tag_list(dl, css_class: str) -> list[str]:
+ dd = dl.find("dd", class_=css_class) if dl else None
+ return [a.get_text(strip=True) for a in dd.find_all("a")] if dd else []
+
+ fandoms = _tag_list(meta_dl, "fandom")
+ ratings = _tag_list(meta_dl, "rating")
+ categories = _tag_list(meta_dl, "category")
+ relationships = _tag_list(meta_dl, "relationship")
+ characters = _tag_list(meta_dl, "character")
+ freeform_tags = _tag_list(meta_dl, "freeform")
+
+ # Series
+ series = ""
+ series_index_hint = 0
+ if meta_dl:
+ series_dd = meta_dl.find("dd", class_="series")
+ if series_dd:
+ series_link = series_dd.find("a")
+ if series_link:
+ series = series_link.get_text(strip=True)
+ pos_span = series_dd.find("span", class_="position")
+ if pos_span:
+ m = re.search(r"Part\s+(\d+)", pos_span.get_text(), re.I)
+ if m:
+ series_index_hint = int(m.group(1))
+
+ # Stats (nested dl.stats inside the meta dl)
+ published = ""
+ updated_date = ""
+ publication_status = ""
+ if meta_dl:
+ stats_dl = meta_dl.find("dl", class_="stats")
+ if stats_dl:
+ pub_dd = stats_dl.find("dd", class_="published")
+ if pub_dd:
+ published = pub_dd.get_text(strip=True)
+
+ status_dt = stats_dl.find("dt", class_="status")
+ status_dd = stats_dl.find("dd", class_="status")
+ if status_dt and status_dd:
+ updated_date = status_dd.get_text(strip=True)
+ if "Completed" in status_dt.get_text():
+ publication_status = "Complete"
+ else:
+ publication_status = "Ongoing"
+ else:
+ # No status entry — determine from chapters count (N/N = complete)
+ updated_date = published
+ chapters_dd = stats_dl.find("dd", class_="chapters")
+ if chapters_dd:
+ m = re.match(r"(\d+)/(\d+|\?)", chapters_dd.get_text(strip=True))
+ if m:
+ if m.group(2) == "?":
+ publication_status = "Ongoing"
+ elif m.group(1) == m.group(2):
+ publication_status = "Complete"
+
+ # Summary
+ description = ""
+ summary_div = soup.find("div", class_="summary")
+ if summary_div:
+ userstuff = summary_div.find("blockquote", class_="userstuff")
+ if userstuff:
+ paras = [p.get_text(strip=True) for p in userstuff.find_all("p") if p.get_text().strip()]
+ description = "\n\n".join(paras) if paras else userstuff.get_text(strip=True)
+
+ # Chapter list via /navigate
+ chapter_links = []
+ chapter_method = "html_scan"
+ try:
+ nr = await client.get(base_url + "/navigate", params={"view_adult": "true"})
+ nsoup = BeautifulSoup(nr.text, "html.parser")
+ chapter_ol = nsoup.find("ol", class_="chapter")
+ if chapter_ol:
+ for li in chapter_ol.find_all("li"):
+ a = li.find("a", href=True)
+ if a:
+ chapter_links.append({
+ "url": urljoin(AO3_BASE, a["href"]),
+ "title": a.get_text(strip=True),
+ })
+ except Exception:
+ pass
+
+ # Fallback: single-chapter work — the work page itself is the content
+ if not chapter_links:
+ chapter_method = "fallback_numeric"
+ chapter_links.append({"url": base_url, "title": book_title})
+
+ # Map to Novela tag structure:
+ # fandoms → genres
+ # ratings + categories → subgenres
+ # relationships + characters + freeform → tags
+ return {
+ "title": book_title,
+ "author": author,
+ "publisher": "Archive of Our Own",
+ "series": series,
+ "series_index_hint": series_index_hint,
+ "genres": fandoms,
+ "subgenres": ratings + categories,
+ "tags": relationships + characters + freeform_tags,
+ "description": description,
+ "updated_date": updated_date,
+ "publication_status": publication_status,
+ "source_url": base_url,
+ "chapters": chapter_links,
+ "chapter_method": chapter_method,
+ }
+
+ async def fetch_chapter(self, client: httpx.AsyncClient, ch: dict) -> dict:
+ r = await client.get(ch["url"], params={"view_adult": "true"})
+ soup = BeautifulSoup(r.text, "html.parser")
+
+ # Chapter title and optional summary from the chapter preface
+ title = ch["title"]
+ chapter_summary_bq = None
+ chapters_div = soup.find("div", id="chapters")
+ if chapters_div:
+ chapter_div = chapters_div.find("div", class_="chapter")
+ if chapter_div:
+ title_el = chapter_div.find("h3", class_="title")
+ if title_el:
+ raw = title_el.get_text(strip=True)
+ if raw:
+ title = raw
+ summary_div = chapter_div.find("div", class_="summary")
+ if summary_div:
+ chapter_summary_bq = summary_div.find("blockquote", class_="userstuff")
+
+ # Content: div.userstuff inside #chapters (excludes author notes)
+ content_el = None
+ if chapters_div:
+ content_el = chapters_div.find("div", class_="userstuff")
+ if not content_el:
+ content_el = soup.find("div", attrs={"role": "article"})
+
+ # Prepend chapter summary as blockquote before story content
+ if chapter_summary_bq and content_el:
+ content_el.insert(0, chapter_summary_bq)
+
+ return {
+ "title": title,
+ "content_el": content_el,
+ "selector_id": content_el.get("id") if content_el else None,
+ "selector_class": " ".join(content_el.get("class", [])) if content_el else None,
+ }
diff --git a/containers/novela/static/conversion.js b/containers/novela/static/conversion.js
index 12ba5ab..7e8b37b 100644
--- a/containers/novela/static/conversion.js
+++ b/containers/novela/static/conversion.js
@@ -71,9 +71,14 @@ function connectConversionStream(job_id) {
document.querySelectorAll('.chapter-item').forEach(el => el.className = 'chapter-item done');
document.getElementById('result-meta').innerHTML =
`${esc(d.title)}
${d.chapters} chapters successfully converted`;
- document.getElementById('download-btn').onclick = () => {
- window.location = `/download/${encodeURIComponent(d.filename)}`;
- };
+ const dlBtn = document.getElementById('download-btn');
+ if (d.storage_type === 'db') {
+ dlBtn.querySelector('span') && (dlBtn.querySelector('span').textContent = 'Export EPUB');
+ dlBtn.onclick = () => { window.location = `/api/library/export-epub/${encodeURIComponent(d.filename)}`; };
+ } else {
+ dlBtn.querySelector('span') && (dlBtn.querySelector('span').textContent = 'Download EPUB');
+ dlBtn.onclick = () => { window.location = `/download/${encodeURIComponent(d.filename)}`; };
+ }
document.getElementById('book-detail-btn').onclick = () => {
window.location = `/library/book/${encodeURIComponent(d.filename)}`;
};
diff --git a/containers/novela/static/editor.css b/containers/novela/static/editor.css
index 21ee86b..e61dd1c 100644
--- a/containers/novela/static/editor.css
+++ b/containers/novela/static/editor.css
@@ -30,6 +30,13 @@ html, body { height: 100%; background: var(--bg); color: var(--text); font-famil
text-align: center; overflow: hidden; text-overflow: ellipsis; white-space: nowrap;
}
+.chapter-title-input {
+ flex: 1; font-size: 0.72rem; font-family: var(--mono); color: var(--text);
+ background: var(--surface2); border: 1px solid var(--border); border-radius: var(--radius);
+ padding: 0.25rem 0.5rem; outline: none; min-width: 0;
+}
+.chapter-title-input:focus { border-color: var(--accent); }
+
.header-actions { display: flex; align-items: center; gap: 0.5rem; flex-shrink: 0; }
.save-status {
diff --git a/containers/novela/static/editor.js b/containers/novela/static/editor.js
index 9ca9d63..78c9626 100644
--- a/containers/novela/static/editor.js
+++ b/containers/novela/static/editor.js
@@ -1,20 +1,26 @@
require.config({ paths: { vs: 'https://cdn.jsdelivr.net/npm/monaco-editor@0.45.0/min/vs' } });
-const { filename } = EDITOR;
+const { filename, is_db } = EDITOR;
let editor = null;
let chapters = [];
let currentIndex = -1;
let dirty = new Set(); // indices with unsaved changes
let pendingContent = new Map(); // index -> modified content not yet saved
+let pendingTitles = new Map(); // index -> modified title not yet saved (DB only)
let loadingChapter = false; // suppress dirty events during setValue
let saving = false;
// ── Init Monaco ───────────────────────────────────────────────────────────────
require(['vs/editor/editor.main'], function () {
+ if (is_db) {
+ document.getElementById('header-chapter').style.display = 'none';
+ document.getElementById('chapter-title-input').style.display = '';
+ }
+
editor = monaco.editor.create(document.getElementById('editor-pane'), {
- language: 'xml',
+ language: is_db ? 'html' : 'xml',
theme: 'vs-dark',
wordWrap: 'on',
minimap: { enabled: true },
@@ -39,6 +45,19 @@ require(['vs/editor/editor.main'], function () {
// Ctrl+S / Cmd+S
editor.addCommand(monaco.KeyMod.CtrlCmd | monaco.KeyCode.KeyS, saveChapter);
+ if (is_db) {
+ document.getElementById('chapter-title-input').addEventListener('input', () => {
+ if (currentIndex >= 0) {
+ pendingTitles.set(currentIndex, document.getElementById('chapter-title-input').value);
+ dirty.add(currentIndex);
+ renderChapterList();
+ setStatus('dirty', 'Unsaved changes');
+ document.getElementById('btn-save').disabled = false;
+ updateSaveAll();
+ }
+ });
+ }
+
loadChapterList();
});
@@ -57,6 +76,7 @@ async function loadChapterList(targetIndex = 0) {
currentIndex = -1;
dirty.clear();
pendingContent.clear();
+ pendingTitles.clear();
renderChapterList();
document.getElementById('header-chapter').textContent = 'No chapters';
document.getElementById('btn-save').disabled = true;
@@ -94,6 +114,11 @@ async function switchChapter(index) {
if (dirty.has(currentIndex) && editor) {
pendingContent.set(currentIndex, editor.getValue());
}
+ // Preserve title input for DB books
+ if (is_db && currentIndex >= 0) {
+ const inp = document.getElementById('chapter-title-input');
+ if (inp) pendingTitles.set(currentIndex, inp.value);
+ }
loadChapter(index);
}
@@ -102,19 +127,19 @@ async function loadChapter(index) {
document.getElementById('btn-save').disabled = true;
document.getElementById('btn-break').disabled = true;
document.getElementById('btn-del-page').disabled = true;
- document.getElementById('header-chapter').textContent = 'Loading…';
+ if (!is_db) document.getElementById('header-chapter').textContent = 'Loading…';
let content, title;
if (pendingContent.has(index)) {
content = pendingContent.get(index);
- title = chapters[index]?.title ?? '';
+ title = pendingTitles.has(index) ? pendingTitles.get(index) : (chapters[index]?.title ?? '');
} else {
const resp = await fetch(`/api/edit/chapter/${index}/${encodeURIComponent(filename)}`);
if (!resp.ok) { setStatus('error', 'Load failed'); return; }
const data = await resp.json();
content = data.content;
- title = data.title;
+ title = pendingTitles.has(index) ? pendingTitles.get(index) : data.title;
}
currentIndex = index;
@@ -123,6 +148,7 @@ async function loadChapter(index) {
editor.setValue(content);
editor.setScrollTop(0);
loadingChapter = false;
+ editor.focus();
// Restore dirty state based on whether we loaded from pending cache
if (dirty.has(index)) {
@@ -134,7 +160,11 @@ async function loadChapter(index) {
}
renderChapterList();
- document.getElementById('header-chapter').textContent = title;
+ if (is_db) {
+ document.getElementById('chapter-title-input').value = title;
+ } else {
+ document.getElementById('header-chapter').textContent = title;
+ }
document.getElementById('btn-break').disabled = false;
document.getElementById('btn-del-page').disabled = chapters.length <= 1;
updateSaveAll();
@@ -149,18 +179,28 @@ async function saveChapter() {
setStatus('saving', 'Saving…');
try {
+ const saveBody = { content: editor.getValue() };
+ if (is_db) {
+ const inp = document.getElementById('chapter-title-input');
+ saveBody.title = inp ? inp.value.trim() : (pendingTitles.get(currentIndex) || '');
+ }
const resp = await fetch(
`/api/edit/chapter/${currentIndex}/${encodeURIComponent(filename)}`,
{
method: 'POST',
headers: { 'Content-Type': 'application/json' },
- body: JSON.stringify({ content: editor.getValue() }),
+ body: JSON.stringify(saveBody),
}
);
const data = await resp.json();
if (data.ok) {
dirty.delete(currentIndex);
pendingContent.delete(currentIndex);
+ if (is_db && chapters[currentIndex]) {
+ const saved = pendingTitles.get(currentIndex) || chapters[currentIndex].title;
+ chapters[currentIndex].title = saved || chapters[currentIndex].title;
+ pendingTitles.delete(currentIndex);
+ }
renderChapterList();
setStatus('saved', 'Saved');
setTimeout(() => setStatus('', ''), 2000);
@@ -186,9 +226,13 @@ async function saveAllChapters() {
if (btn) btn.disabled = true;
setStatus('saving', 'Saving all…');
- // Flush current editor content into pendingContent first
+ // Flush current editor content and title into pending caches first
if (currentIndex >= 0 && dirty.has(currentIndex)) {
pendingContent.set(currentIndex, editor.getValue());
+ if (is_db) {
+ const inp = document.getElementById('chapter-title-input');
+ if (inp) pendingTitles.set(currentIndex, inp.value);
+ }
}
const indices = [...dirty];
@@ -196,21 +240,29 @@ async function saveAllChapters() {
const content = pendingContent.has(i)
? pendingContent.get(i)
: (i === currentIndex ? editor.getValue() : null);
- if (!content) continue;
+ // For DB books, a title-only change has no pendingContent — still need to save
+ const hasTitleChange = is_db && pendingTitles.has(i);
+ if (!content && !hasTitleChange) continue;
try {
+ const saveBody = { content: content || '' };
+ if (is_db) saveBody.title = pendingTitles.has(i) ? pendingTitles.get(i) : (chapters[i]?.title || '');
const resp = await fetch(
`/api/edit/chapter/${i}/${encodeURIComponent(filename)}`,
{
method: 'POST',
headers: { 'Content-Type': 'application/json' },
- body: JSON.stringify({ content }),
+ body: JSON.stringify(saveBody),
}
);
const data = await resp.json();
if (data.ok) {
dirty.delete(i);
pendingContent.delete(i);
+ if (is_db && chapters[i]) {
+ chapters[i].title = pendingTitles.get(i) || chapters[i].title;
+ pendingTitles.delete(i);
+ }
}
} catch {
setStatus('error', `Save failed on chapter ${i + 1}`);
@@ -251,10 +303,11 @@ function updateSaveAll() {
function insertBreak() {
if (!editor || currentIndex < 0) return;
+ const breakSrc = is_db ? '/static/break.png' : '../Images/break.png';
const pos = editor.getPosition();
editor.executeEdits('insert-break', [{
range: new monaco.Range(pos.lineNumber, pos.column, pos.lineNumber, pos.column),
- text: '\n