feat(server): add OSS webclaw-server REST API binary (closes #29)
Self-hosters hitting docs/self-hosting were promised three binaries
but the OSS Docker image only shipped two. webclaw-server lived in
the closed-source hosted-platform repo, which couldn't be opened. This
adds a minimal axum REST API in the OSS repo so self-hosting actually
works without pretending to ship the cloud platform.
Crate at crates/webclaw-server/. Stateless, no database, no job queue,
single binary. Endpoints: GET /health, POST /v1/{scrape, crawl, map,
batch, extract, summarize, diff, brand}. JSON shapes mirror
api.webclaw.io for the endpoints OSS can support, so swapping between
self-hosted and hosted is a base-URL change.
Auth: optional bearer token via WEBCLAW_API_KEY / --api-key. Comparison
is constant-time (subtle::ConstantTimeEq). Open mode (no key) is
allowed and binds 127.0.0.1 by default; the Docker image flips
WEBCLAW_HOST=0.0.0.0 so the container is reachable out of the box.
Hard caps to keep naive callers from OOMing the process: crawl capped
at 500 pages synchronously, batch capped at 100 URLs / 20 concurrent.
For unbounded crawls or anti-bot bypass the docs point users at the
hosted API.
Dockerfile + Dockerfile.ci updated to copy webclaw-server into
/usr/local/bin and EXPOSE 3000. Workspace version bumped to 0.4.0
(new public binary).
2026-04-22 12:25:11 +02:00
|
|
|
//! POST /v1/diff — compare current page content against a prior snapshot.
|
|
|
|
|
//!
|
|
|
|
|
//! Caller passes either a full prior `ExtractionResult` or the minimal
|
|
|
|
|
//! `{ markdown, metadata }` shape used by the hosted API. We re-fetch
|
|
|
|
|
//! the URL, extract, and run `webclaw_core::diff::diff` over the pair.
|
|
|
|
|
|
|
|
|
|
use axum::{Json, extract::State};
|
|
|
|
|
use serde::Deserialize;
|
|
|
|
|
use serde_json::{Value, json};
|
|
|
|
|
use webclaw_core::{Content, ExtractionResult, Metadata, diff::diff};
|
|
|
|
|
|
|
|
|
|
use crate::{error::ApiError, state::AppState};
|
|
|
|
|
|
|
|
|
|
#[derive(Debug, Deserialize)]
|
|
|
|
|
pub struct DiffRequest {
|
|
|
|
|
pub url: String,
|
|
|
|
|
pub previous: PreviousSnapshot,
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// Either a full prior extraction, or the minimal `{ markdown, metadata }`
|
|
|
|
|
/// shape returned by /v1/scrape. Untagged so callers can send whichever
|
|
|
|
|
/// they have on hand.
|
|
|
|
|
#[derive(Debug, Deserialize)]
|
|
|
|
|
#[serde(untagged)]
|
|
|
|
|
pub enum PreviousSnapshot {
|
|
|
|
|
Full(ExtractionResult),
|
|
|
|
|
Minimal {
|
|
|
|
|
#[serde(default)]
|
|
|
|
|
markdown: String,
|
|
|
|
|
#[serde(default)]
|
|
|
|
|
metadata: Option<Metadata>,
|
|
|
|
|
},
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
impl PreviousSnapshot {
|
|
|
|
|
fn into_extraction(self) -> ExtractionResult {
|
|
|
|
|
match self {
|
|
|
|
|
Self::Full(r) => r,
|
|
|
|
|
Self::Minimal { markdown, metadata } => ExtractionResult {
|
|
|
|
|
metadata: metadata.unwrap_or_else(empty_metadata),
|
|
|
|
|
content: Content {
|
|
|
|
|
markdown,
|
|
|
|
|
plain_text: String::new(),
|
|
|
|
|
links: Vec::new(),
|
|
|
|
|
images: Vec::new(),
|
|
|
|
|
code_blocks: Vec::new(),
|
|
|
|
|
raw_html: None,
|
|
|
|
|
},
|
|
|
|
|
domain_data: None,
|
|
|
|
|
structured_data: Vec::new(),
|
|
|
|
|
},
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
fn empty_metadata() -> Metadata {
|
|
|
|
|
Metadata {
|
|
|
|
|
title: None,
|
|
|
|
|
description: None,
|
|
|
|
|
author: None,
|
|
|
|
|
published_date: None,
|
|
|
|
|
language: None,
|
|
|
|
|
url: None,
|
|
|
|
|
site_name: None,
|
|
|
|
|
image: None,
|
|
|
|
|
favicon: None,
|
|
|
|
|
word_count: 0,
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
pub async fn diff_route(
|
|
|
|
|
State(state): State<AppState>,
|
|
|
|
|
Json(req): Json<DiffRequest>,
|
|
|
|
|
) -> Result<Json<Value>, ApiError> {
|
|
|
|
|
if req.url.trim().is_empty() {
|
|
|
|
|
return Err(ApiError::bad_request("`url` is required"));
|
|
|
|
|
}
|
2026-05-04 14:30:06 +02:00
|
|
|
let url = webclaw_fetch::url_security::validate_public_http_url(&req.url).await?;
|
feat(server): add OSS webclaw-server REST API binary (closes #29)
Self-hosters hitting docs/self-hosting were promised three binaries
but the OSS Docker image only shipped two. webclaw-server lived in
the closed-source hosted-platform repo, which couldn't be opened. This
adds a minimal axum REST API in the OSS repo so self-hosting actually
works without pretending to ship the cloud platform.
Crate at crates/webclaw-server/. Stateless, no database, no job queue,
single binary. Endpoints: GET /health, POST /v1/{scrape, crawl, map,
batch, extract, summarize, diff, brand}. JSON shapes mirror
api.webclaw.io for the endpoints OSS can support, so swapping between
self-hosted and hosted is a base-URL change.
Auth: optional bearer token via WEBCLAW_API_KEY / --api-key. Comparison
is constant-time (subtle::ConstantTimeEq). Open mode (no key) is
allowed and binds 127.0.0.1 by default; the Docker image flips
WEBCLAW_HOST=0.0.0.0 so the container is reachable out of the box.
Hard caps to keep naive callers from OOMing the process: crawl capped
at 500 pages synchronously, batch capped at 100 URLs / 20 concurrent.
For unbounded crawls or anti-bot bypass the docs point users at the
hosted API.
Dockerfile + Dockerfile.ci updated to copy webclaw-server into
/usr/local/bin and EXPOSE 3000. Workspace version bumped to 0.4.0
(new public binary).
2026-04-22 12:25:11 +02:00
|
|
|
|
2026-05-04 14:30:06 +02:00
|
|
|
let current = state.fetch().fetch_and_extract(url.as_str()).await?;
|
feat(server): add OSS webclaw-server REST API binary (closes #29)
Self-hosters hitting docs/self-hosting were promised three binaries
but the OSS Docker image only shipped two. webclaw-server lived in
the closed-source hosted-platform repo, which couldn't be opened. This
adds a minimal axum REST API in the OSS repo so self-hosting actually
works without pretending to ship the cloud platform.
Crate at crates/webclaw-server/. Stateless, no database, no job queue,
single binary. Endpoints: GET /health, POST /v1/{scrape, crawl, map,
batch, extract, summarize, diff, brand}. JSON shapes mirror
api.webclaw.io for the endpoints OSS can support, so swapping between
self-hosted and hosted is a base-URL change.
Auth: optional bearer token via WEBCLAW_API_KEY / --api-key. Comparison
is constant-time (subtle::ConstantTimeEq). Open mode (no key) is
allowed and binds 127.0.0.1 by default; the Docker image flips
WEBCLAW_HOST=0.0.0.0 so the container is reachable out of the box.
Hard caps to keep naive callers from OOMing the process: crawl capped
at 500 pages synchronously, batch capped at 100 URLs / 20 concurrent.
For unbounded crawls or anti-bot bypass the docs point users at the
hosted API.
Dockerfile + Dockerfile.ci updated to copy webclaw-server into
/usr/local/bin and EXPOSE 3000. Workspace version bumped to 0.4.0
(new public binary).
2026-04-22 12:25:11 +02:00
|
|
|
let previous = req.previous.into_extraction();
|
|
|
|
|
let result = diff(&previous, ¤t);
|
|
|
|
|
|
|
|
|
|
Ok(Json(json!({
|
|
|
|
|
"url": req.url,
|
|
|
|
|
"status": result.status,
|
|
|
|
|
"diff": result.text_diff,
|
|
|
|
|
"metadata_changes": result.metadata_changes,
|
|
|
|
|
"links_added": result.links_added,
|
|
|
|
|
"links_removed": result.links_removed,
|
|
|
|
|
"word_count_delta": result.word_count_delta,
|
|
|
|
|
})))
|
|
|
|
|
}
|