Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file added blueprints/crawlab-master/crawlab.jpeg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
41 changes: 41 additions & 0 deletions blueprints/crawlab-master/docker-compose.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,41 @@
version: "3.8"
services:
crawlab-master:
image: crawlabteam/crawlab:latest
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Unpinned image tag is a security risk

Using crawlabteam/crawlab:latest means any upstream change can silently alter the deployed version, including potentially breaking changes or supply chain attacks. The contribution guide explicitly requires images to be pinned to a specific version (e.g., crawlabteam/crawlab:0.6.0). The version field in meta.json must also match.

(Replace 0.6.0 with the actual latest stable release tag.)

Context Used: AGENTS.md (source)

restart: unless-stopped
environment:
- CRAWLAB_NODE_MASTER=Y
- CRAWLAB_MONGO_HOST=mongo
- CRAWLAB_MONGO_PORT=27017
- CRAWLAB_MONGO_DB=crawlab
- CRAWLAB_MONGO_USERNAME=${MONGO_USERNAME}
- CRAWLAB_MONGO_PASSWORD=${MONGO_PASSWORD}
- CRAWLAB_MONGO_AUTHSOURCE=admin
volumes:
- crawlab-master-data:/root/.crawlab
- crawlab-app-data:/data
- crawlab-logs:/var/log/crawlab
expose:
- "8080"
- "9666"
depends_on:
- mongo
deploy:
resources:
limits:
cpus: "${CPU_LIMIT:-0.8}" # 0.8 will limit to 80% of CPU if one core. If 2 cores, you need to put 0.8*2=1.6

mongo:
image: mongo:4.2
restart: unless-stopped
environment:
- MONGO_INITDB_ROOT_USERNAME=${MONGO_USERNAME}
- MONGO_INITDB_ROOT_PASSWORD=${MONGO_PASSWORD}
volumes:
- mongo-data:/data/db

volumes:
crawlab-master-data:
crawlab-app-data:
crawlab-logs:
mongo-data:
12 changes: 12 additions & 0 deletions blueprints/crawlab-master/template.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
[variables]
MONGO_USERNAME = "crawlab"
MONGO_PASSWORD = "${password:24}"
CPU_LIMIT = "0.8"

[config]
env = ["MONGO_USERNAME=${MONGO_USERNAME}", "MONGO_PASSWORD=${MONGO_PASSWORD}", "CPU_LIMIT=${CPU_LIMIT}"]

[[config.domains]]
serviceName = "crawlab-master"
port = 8080
host = "${domain}"
Binary file added blueprints/crawlab-worker/crawlab.jpeg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
20 changes: 20 additions & 0 deletions blueprints/crawlab-worker/docker-compose.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
version: "3.8"
services:
crawlab-worker:
image: crawlabteam/crawlab:latest
restart: unless-stopped
environment:
- CRAWLAB_NODE_MASTER=N
- CRAWLAB_GRPC_ADDRESS=${MASTER_GRPC_ADDRESS}
- CRAWLAB_FS_FILER_URL=${MASTER_FILER_URL}
volumes:
- crawlab-worker-data:/root/.crawlab
- crawlab-worker-app:/data
deploy:
resources:
limits:
cpus: "${CPU_LIMIT:-0.8}" # 0.8 will limit to 80% of CPU if one core. If 2 cores, you need to put 0.8*2=1.6

volumes:
crawlab-worker-data:
crawlab-worker-app:
7 changes: 7 additions & 0 deletions blueprints/crawlab-worker/template.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
[variables]
MASTER_GRPC_ADDRESS = "<master_node_ip>:9666"
MASTER_FILER_URL = "http://<master_node_ip>:8080/api/filer"
CPU_LIMIT = "0.8"

[config]
env = ["MASTER_GRPC_ADDRESS=${MASTER_GRPC_ADDRESS}", "MASTER_FILER_URL=${MASTER_FILER_URL}", "CPU_LIMIT=${CPU_LIMIT}"]
54 changes: 36 additions & 18 deletions meta.json
Original file line number Diff line number Diff line change
Expand Up @@ -1645,6 +1645,42 @@
"API"
]
},
{
"id": "crawlab-master",
"name": "Crawlab (Master)",
"version": "latest",
"description": "Crawlab is a distributed web crawler admin platform supporting multiple programming languages and frameworks. This template deploys the master node with MongoDB.",
"logo": "crawlab.jpeg",
"links": {
"github": "https://github.com/crawlab-team/crawlab",
"website": "https://crawlab.cn",
"docs": "https://docs.crawlab.cn"
},
"tags": [
"crawler",
"scraping",
"distributed",
"self-hosted"
]
},
{
"id": "crawlab-worker",
"name": "Crawlab (Worker)",
"version": "latest",
"description": "Crawlab worker node for distributed web crawling. Connects to an existing Crawlab master node via gRPC.",
"logo": "crawlab.jpeg",
"links": {
"github": "https://github.com/crawlab-team/crawlab",
"website": "https://crawlab.cn",
"docs": "https://docs.crawlab.cn"
},
"tags": [
"crawler",
"scraping",
"distributed",
"self-hosted"
]
},
{
"id": "crowdsec",
"name": "Crowdsec",
Expand Down Expand Up @@ -5952,24 +5988,6 @@
"media"
]
},
{
"id": "strapi",
"name": "Strapi",
"version": "v5.33.0",
"description": "Open-source headless CMS to build powerful APIs with built-in content management.",
"logo": "strapi.svg",
"links": {
"github": "https://github.com/strapi/strapi",
"discord": "https://discord.com/invite/strapi",
"docs": "https://docs.strapi.io",
"website": "https://strapi.io"
},
"tags": [
"headless",
"cms",
"content-management"
]
},
{
"id": "supabase",
"name": "SupaBase",
Expand Down
Loading