.dockerignore

@@ -1,15 +0,0 @@
-# Exclude runtime config and data directories from the Docker build context.
-# The config/ directory may contain secrets (e.g. twitter-cookies.txt) that are
-# only needed at runtime via a volume mount — they must never reach the builder.
-config/
-docker/
-
-# Development and VCS noise
-.git/
-.gitignore
-
-# Generated build outputs — can be 1.4G (target/) and 243M (node_modules/)
-# after a local dev build; exclude them to keep the build context small.
-target/
-frontend/node_modules/
-frontend/dist/

.gitignore

@@ -19,12 +19,6 @@
 !ARCHIVR-MENTAL-MODEL.md
 !NEXT.md
 
-!Dockerfile
-!.dockerignore
-!docker-compose.yml
-!docker/
-!docker/**
-
 !modules/
 !modules/**
 

Dockerfile

@@ -1,106 +0,0 @@
-# syntax=docker/dockerfile:1
-
-###############################################################################
-# Stage 1 – Build the Rust server and CLI binaries
-###############################################################################
-FROM rust:1.88-slim-bookworm AS builder
-
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    pkg-config \
-    libssl-dev \
-    && rm -rf /var/lib/apt/lists/*
-
-WORKDIR /build
-
-# Layer the dependency build separately for better cache reuse.
-# Stub out every crate so Cargo can resolve and compile all dependencies
-# before we copy the real source.
-COPY Cargo.toml Cargo.lock ./
-COPY crates/archivr-core/Cargo.toml   crates/archivr-core/Cargo.toml
-COPY crates/archivr-server/Cargo.toml crates/archivr-server/Cargo.toml
-COPY crates/archivr-cli/Cargo.toml    crates/archivr-cli/Cargo.toml
-
-RUN mkdir -p \
-        crates/archivr-core/src \
-        crates/archivr-server/src \
-        crates/archivr-cli/src \
-    && touch crates/archivr-core/src/lib.rs \
-    && echo 'fn main() {}' > crates/archivr-server/src/main.rs \
-    && echo 'fn main() {}' > crates/archivr-cli/src/main.rs \
-    && cargo build --release -p archivr-server -p archivr-cli || true
-
-# Build the real binaries; touch source files to force Cargo to relink.
-COPY crates/ crates/
-RUN touch \
-    crates/archivr-core/src/lib.rs \
-    crates/archivr-server/src/main.rs \
-    crates/archivr-cli/src/main.rs \
-    && cargo build --release -p archivr-server -p archivr-cli
-
-###############################################################################
-# Stage 2 – Runtime image
-###############################################################################
-FROM debian:bookworm-slim
-
-# Runtime dependencies:
-#   chromium              used by single-file-cli for full-page archiving
-#   nodejs (20+)          runtime for single-file-cli (requires Node >=20; Debian
-#                         bookworm ships 18, so we install from the NodeSource repo)
-#   ffmpeg                required by yt-dlp to merge separate audio/video streams
-#                         (e.g. YouTube bestvideo+bestaudio format selection)
-#   python3 + pip + venv  twitter scraper
-#   ca-certificates       outbound HTTPS from the server and NodeSource HTTPS
-#   libssl3               OpenSSL linked by the Rust binary
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    curl \
-    ca-certificates \
-    && curl -fsSL https://deb.nodesource.com/setup_20.x | bash - \
-    && apt-get install -y --no-install-recommends \
-    chromium \
-    nodejs \
-    ffmpeg \
-    python3 \
-    python3-pip \
-    python3-venv \
-    libssl3 \
-    && rm -rf /var/lib/apt/lists/*
-
-# Install single-file-cli globally so `single-file` is on PATH.
-RUN npm install -g single-file-cli
-
-# Install yt-dlp and twitter-api-client into an isolated venv to avoid
-# conflicts with Debian's system Python packages.
-RUN python3 -m venv /opt/archivr-venv \
-    && /opt/archivr-venv/bin/pip install --no-cache-dir \
-        yt-dlp \
-        twitter-api-client
-
-# Server and CLI binaries (CLI is needed to run `archivr init` on first setup)
-COPY --from=builder /build/target/release/archivr-server /usr/local/bin/archivr-server
-COPY --from=builder /build/target/release/archivr       /usr/local/bin/archivr
-
-# Pre-built frontend assets (already compiled; no Vite build step needed)
-COPY crates/archivr-server/static/ /usr/share/archivr-server/static/
-
-# Twitter scraper script
-COPY vendor/twitter/scrape_user_tweet_contents.py \
-     /usr/local/lib/archivr/scrape_user_tweet_contents.py
-
-# Wire up env vars that the server (and archivr-core) read at runtime.
-# ARCHIVR_BIND and ARCHIVR_TWITTER_CREDENTIALS_FILE are intentionally left
-# unset here — set them in docker-compose.yml or at `docker run` time.
-ENV ARCHIVR_STATIC_DIR=/usr/share/archivr-server/static \
-    ARCHIVR_CHROME=/usr/bin/chromium \
-    ARCHIVR_SINGLE_FILE=/usr/local/bin/single-file \
-    ARCHIVR_TWEET_PYTHON=/opt/archivr-venv/bin/python3 \
-    ARCHIVR_TWEET_SCRAPER=/usr/local/lib/archivr/scrape_user_tweet_contents.py \
-    ARCHIVR_YT_DLP=/opt/archivr-venv/bin/yt-dlp \
-    ARCHIVR_CHROME_ARGS=--no-sandbox
-
-EXPOSE 8080
-
-# Expects the TOML config at /config/archivr-server.toml (mount a volume).
-# Copy docker/config.example.toml as a starting point.
-# Using CMD (not ENTRYPOINT) so `docker compose run archivr archivr init …`
-# can override the whole command for first-time archive initialisation.
-CMD ["archivr-server", "/config/archivr-server.toml"]

crates/archivr-core/src/downloader/singlefile.rs

@@ -68,30 +68,18 @@ fn save_with(
     // without a writable user-data-dir. Using a subdirectory of temp_dir
     // keeps it isolated and it gets cleaned up with the rest of the temp dir.
     let chrome_data_dir = temp_dir.join("chrome-data");
-    // Build the browser-args JSON array. Start with the flags always required,
+    let browser_args = format!(
-    // then append any extra flags from ARCHIVR_CHROME_ARGS (space-separated).
+        "[\"--disable-web-security\",\"--user-data-dir={}\"]",
-    // Docker containers running as root need "--no-sandbox" here because
+        chrome_data_dir.display()
-    // Chromium refuses to start as root without it.
+    );
-    let mut chrome_flags = vec![
-        "--disable-web-security".to_string(),
-        format!("--user-data-dir={}", chrome_data_dir.display()),
-    ];
-    if let Ok(extra) = std::env::var("ARCHIVR_CHROME_ARGS") {
-        chrome_flags.extend(extra.split_whitespace().filter(|s| !s.is_empty()).map(str::to_string));
-    }
-    let quoted: Vec<String> = chrome_flags
-        .iter()
-        .map(|f| format!("\"{}\"", f.replace('\\', "\\\\").replace('"', "\\\"")))
-        .collect();
-    let browser_args = format!("[{}]", quoted.join(","));
 
     let out = Command::new(single_file)
         .arg(url)
         .arg(&out_file)
         .arg(format!("--browser-executable-path={chrome}"))
         .arg("--browser-headless")
-        .arg("--browser-wait-until=networkAlmostIdle")
+        .arg("--browser-wait-until=networkidle2")
-        // Extra delay after networkAlmostIdle: Cloudflare Fonts injects @font-face
+        // Extra delay after networkidle2: Cloudflare Fonts injects @font-face
         // CSS after HTML parse, so the font hook needs more time to see it.
         .arg("--browser-wait-delay=2000")
         // Realistic UA: some origins block headless Chrome's default UA string.

docker-compose.yml

@@ -1,23 +0,0 @@
-services:
-  archivr:
-    build: .
-    image: archivr-server:latest
-    restart: unless-stopped
-    ports:
-      - "8080:8080"
-    environment:
-      # Listen on all interfaces inside the container so the port mapping works.
-      ARCHIVR_BIND: "0.0.0.0:8080"
-      # Uncomment and set this to enable Twitter/X archiving.
-      # The file must be accessible inside the container (e.g. in the config volume).
-      # ARCHIVR_TWITTER_CREDENTIALS_FILE: /config/twitter-cookies.txt
-    volumes:
-      # Mount a directory containing archivr-server.toml as read-only config.
-      # Copy docker/config.example.toml to ./config/archivr-server.toml to start.
-      - ./config:/config:ro
-      # Persistent volume for the auth database and archive directories.
-      # The paths inside must match archive_path values in your TOML config.
-      - archivr-data:/data
-
-volumes:
-  archivr-data:

docker/config.example.toml

@@ -1,32 +0,0 @@
-# archivr-server.toml — example configuration for Docker deployment.
-#
-# Copy this file to ./config/archivr-server.toml (next to docker-compose.yml),
-# edit it to suit your setup, then run:
-#
-#   docker compose up -d
-#
-# The bind address defaults to 127.0.0.1:8080. When running under Docker,
-# set ARCHIVR_BIND=0.0.0.0:8080 in the environment (docker-compose.yml does
-# this already) — the env var takes precedence over the value below.
-
-# bind = "0.0.0.0:8080"
-
-# Path to the server-level authentication database.
-# Must be on a persistent volume so it survives container restarts.
-auth_db_path = "/data/archivr-auth.sqlite"
-
-# Define one or more archives.
-# archive_path must point to the .archivr directory created by `archivr init`,
-# on the persistent data volume (/data by default).
-# Initialize each archive before starting the server (see Docker quickstart step 2).
-
-[[archives]]
-id = "main"
-label = "Main Archive"
-archive_path = "/data/archives/main/.archivr"
-
-# Add more archives as needed:
-# [[archives]]
-# id = "videos"
-# label = "Videos"
-# archive_path = "/data/archives/videos/.archivr"

docs/README.md

@@ -205,17 +205,12 @@ A `Dockerfile` and `docker-compose.yml` are provided for self-hosting without Ni
    # edit config/archivr-server.toml — set archive id, label, and archive_path
    ```
 
-2. Initialize each archive on the persistent data volume before the first start.
+2. Create the archive directory on the persistent data volume before the first start:
-   The image includes the `archivr` CLI for this purpose:
 
    ```sh
-   docker compose run --rm archivr archivr init /data/archives/main /data/archives/main/.archivr/store --name "Main Archive"
+   docker compose run --rm archivr mkdir -p /data/archives/main
    ```
 
-   This creates `/data/archives/main/.archivr/` with the metadata the server requires.
-   A bare `mkdir` is not enough — the server reads `name` and `store_path` files that
-   only `archivr init` writes.
-
 3. Start the server:
 
    ```sh
@@ -229,12 +224,7 @@ A `Dockerfile` and `docker-compose.yml` are provided for self-hosting without Ni
 | Mount | Purpose |
 |-------|---------|
 | `./config` (read-only) | Directory containing `archivr-server.toml` |
-| `archivr-data` named volume | Auth database (`/data/archivr-auth.sqlite`) and archive directories |
+| `archivr-data` named volume | Auth database and archive directories |
-
-> **Important:** `auth_db_path` must be set explicitly in `archivr-server.toml` to a
-> path on the writable data volume (e.g. `/data/archivr-auth.sqlite`). If left unset,
-> the server defaults to writing the auth database next to the config file — which is
-> on the read-only `/config` mount and will fail. The example config sets this correctly.
 
 **Twitter/X archiving**
 
@@ -300,11 +290,6 @@ dependencies (Chromium, Node.js, Python) land in the final layer.
 - `ARCHIVR_CHROME`
   - Optional.
   - Overrides the Chromium/Chrome executable passed to `single-file` via `--browser-executable-path`. Set automatically by the Nix wrapper and the Docker image. Default: `chromium`.
-- `ARCHIVR_CHROME_ARGS`
-  - Optional.
-  - Space-separated extra flags appended to Chromium's `--browser-args`. The Docker
-    image sets this to `--no-sandbox` because Chromium refuses to run as root without
-    it. Leave unset when running natively (Nix, Linux desktop).
 - `ARCHIVR_TWITTER_CREDENTIALS_FILE`
   - Required for tweet/thread scraping inputs such as `tweet:ID` and `x:thread:ID`.
   - Must point to a cookies file for the vendored scraper.