feat(browse): add SingleFile browse-page snapshot cache via MinIO
- New MinIO bucket 'libnovel-browse' (MINIO_BUCKET_BROWSE env) for storing self-contained HTML snapshots of novelfire browse pages - Store interface gains SaveBrowsePage / GetBrowsePage / BrowsePageKey methods - handleBrowse is now cache-first: serves from MinIO snapshot when available, then fires a background triggerBrowseSnapshot goroutine to populate cache on live-fetch (de-duplicated, 90s timeout) - New 'save-browse' CLI subcommand to bulk-capture pages via SingleFile CLI - Dockerfile: downloads pinned single-file-x86_64-linux binary (v2.0.83), adds gcompat + libstdc++ to Alpine runtime for glibc compatibility - docker-compose: adds libnovel-browse bucket init and SINGLEFILE_PATH env - .gitignore: exclude scraper/scraper build artifact
This commit is contained in:
@@ -12,15 +12,30 @@ COPY . .
|
||||
RUN CGO_ENABLED=0 GOOS=linux GOARCH=amd64 \
|
||||
go build -ldflags="-s -w" -o /scraper ./cmd/scraper
|
||||
|
||||
# ── single-file binary stage ───────────────────────────────────────────────────
|
||||
# Download the official pre-compiled single-file-cli binary (Deno-compiled,
|
||||
# statically linked for Linux x86_64 glibc). We pin to a specific version so
|
||||
# image builds are reproducible; bump this ARG to upgrade.
|
||||
FROM alpine:3.20 AS singlefile-downloader
|
||||
ARG SINGLEFILE_VERSION=2.0.83
|
||||
RUN apk add --no-cache wget ca-certificates && \
|
||||
wget -q -O /single-file \
|
||||
"https://github.com/gildas-lormeau/single-file-cli/releases/download/v${SINGLEFILE_VERSION}/single-file-x86_64-linux" && \
|
||||
chmod +x /single-file
|
||||
|
||||
# ── Runtime stage ──────────────────────────────────────────────────────────────
|
||||
FROM alpine:3.20
|
||||
|
||||
# ca-certificates is required for HTTPS requests to novelfire.net.
|
||||
RUN apk add --no-cache ca-certificates tzdata
|
||||
# ca-certificates: HTTPS to novelfire.net
|
||||
# gcompat: glibc compatibility shim so the glibc-linked single-file binary
|
||||
# runs on musl/Alpine without needing a full glibc image.
|
||||
# libstdc++: required by the Deno runtime embedded in single-file
|
||||
RUN apk add --no-cache ca-certificates tzdata gcompat libstdc++
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY --from=builder /scraper /app/scraper
|
||||
COPY --from=singlefile-downloader /single-file /usr/local/bin/single-file
|
||||
|
||||
# Create the default static output directory.
|
||||
RUN mkdir -p /app/static/books
|
||||
@@ -36,6 +51,7 @@ ENV BROWSERLESS_STRATEGY=content
|
||||
ENV SCRAPER_WORKERS=0
|
||||
ENV SCRAPER_STATIC_ROOT=/app/static/books
|
||||
ENV SCRAPER_HTTP_ADDR=:8080
|
||||
ENV SINGLEFILE_PATH=/usr/local/bin/single-file
|
||||
|
||||
EXPOSE 8080
|
||||
|
||||
|
||||
Reference in New Issue
Block a user