大数据 爬虫Python AI Sql

Crawlab:在 Ubuntu 18.04 上使用 docke

2020-04-15  本文已影响0人  dex0423

1. Crawlab 简介:

2. 安装 docker

sudo dpkg --configure -a
sudo apt-get install apt-transport-https ca-certificates curl software-properties-common
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo apt-key add -
sudo add-apt-repository "deb [arch=amd64] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"
sudo apt-get install docker-ce
vim /etc/docker/daemon.json

输入如下内容以修改镜像源:

{
"registry-mirrors": ["https://registry.docker-cn.com"]
}

sudo curl -L "https://github.com/docker/compose/releases/download/1.23.1/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose
sudo chmod +x /usr/local/bin/docker-compose
docker-compose --version  # 查看 docker-compose 版本
# 启动docker
sudo service docker start

# 停止docker
sudo service docker stop

# 重启docker
sudo service docker restart

# 列出镜像
docker image ls

# 拉取镜像
docker image pull library/hello-world

# 删除镜像
docker image rm 镜像id/镜像ID

# 创建容器
docker run [选项参数] 镜像名 [命令]

# 停止一个已经在运行的容器
docker container stop 容器名或容器id

# 启动一个已经停止的容器
docker container start 容器名或容器id

# kill掉一个已经在运行的容器
docker container kill 容器名或容器id

# 删除容器
docker container rm 容器名或容器id

3. 下载 Crawlab 镜像:

docker pull tikazyq/crawlab:latest
sudo docker pull registry.cn-hangzhou.aliyuncs.com/crawlab-team/crawlab:latest

4. docker-compose 启动 Crawlab

version: '3.3'
services:
  master: 
    image: tikazyq/crawlab:latest
    container_name: master
    environment:
      # CRAWLAB_API_ADDRESS: "https://<your_api_ip>:<your_api_port>"  # backend API address 后端 API 地址. 适用于 https 或者源码部署
      CRAWLAB_SERVER_MASTER: "Y"  # whether to be master node 是否为主节点,主节点为 Y,工作节点为 N
      CRAWLAB_MONGO_HOST: "mongo"  # MongoDB host address MongoDB 的地址,在 docker compose 网络中,直接引用服务名称
      # CRAWLAB_MONGO_PORT: "27017"  # MongoDB port MongoDB 的端口
      # CRAWLAB_MONGO_DB: "crawlab_test"  # MongoDB database MongoDB 的数据库
      # CRAWLAB_MONGO_USERNAME: "username"  # MongoDB username MongoDB 的用户名
      # CRAWLAB_MONGO_PASSWORD: "password"  # MongoDB password MongoDB 的密码
      # CRAWLAB_MONGO_AUTHSOURCE: "admin"  # MongoDB auth source MongoDB 的验证源
      CRAWLAB_REDIS_ADDRESS: "redis"  # Redis host address Redis 的地址,在 docker compose 网络中,直接引用服务名称
      # CRAWLAB_REDIS_PORT: "6379"  # Redis port Redis 的端口
      # CRAWLAB_REDIS_DATABASE: "1"  # Redis database Redis 的数据库
      # CRAWLAB_REDIS_PASSWORD: "password"  # Redis password Redis 的密码
      # CRAWLAB_LOG_LEVEL: "info"  # log level 日志级别. 默认为 info
      # CRAWLAB_LOG_ISDELETEPERIODICALLY: "N"  # whether to periodically delete log files 是否周期性删除日志文件. 默认不删除
      # CRAWLAB_LOG_DELETEFREQUENCY: "@hourly"  # frequency of deleting log files 删除日志文件的频率. 默认为每小时
      # CRAWLAB_SERVER_REGISTER_TYPE: "mac"  # node register type 节点注册方式. 默认为 mac 地址,也可设置为 ip(防止 mac 地址冲突)
      # CRAWLAB_SERVER_REGISTER_IP: "127.0.0.1"  # node register ip 节点注册IP. 节点唯一识别号,只有当 CRAWLAB_SERVER_REGISTER_TYPE 为 "ip" 时才生效
      # CRAWLAB_TASK_WORKERS: 8  # number of task executors 任务执行器个数(并行执行任务数)
      # CRAWLAB_RPC_WORKERS: 16  # number of RPC workers RPC 工作协程个数
      # CRAWLAB_SERVER_LANG_NODE: "Y"  # whether to pre-install Node.js 预安装 Node.js 语言环境
      # CRAWLAB_SERVER_LANG_JAVA: "Y"  # whether to pre-install Java 预安装 Java 语言环境
      # CRAWLAB_SETTING_ALLOWREGISTER: "N"  # whether to allow user registration 是否允许用户注册
      # CRAWLAB_SETTING_ENABLETUTORIAL: "N"  # whether to enable tutorial 是否启用教程
      # CRAWLAB_NOTIFICATION_MAIL_SERVER: smtp.exmaple.com  # STMP server address STMP 服务器地址
      # CRAWLAB_NOTIFICATION_MAIL_PORT: 465  # STMP server port STMP 服务器端口
      # CRAWLAB_NOTIFICATION_MAIL_SENDEREMAIL: admin@exmaple.com  # sender email 发送者邮箱
      # CRAWLAB_NOTIFICATION_MAIL_SENDERIDENTITY: admin@exmaple.com  # sender ID 发送者 ID
      # CRAWLAB_NOTIFICATION_MAIL_SMTP_USER: username  # SMTP username SMTP 用户名
      # CRAWLAB_NOTIFICATION_MAIL_SMTP_PASSWORD: password  # SMTP password SMTP 密码
    ports:    
      - "8080:8080" # frontend port mapping 前端端口映射
    depends_on:
      - mongo
      - redis
    # volumes:
    #   - "/var/crawlab/log:/var/logs/crawlab" # log persistent 日志持久化
  worker:
    image: tikazyq/crawlab:latest
    container_name: worker
    environment:
      CRAWLAB_SERVER_MASTER: "N"
      CRAWLAB_MONGO_HOST: "mongo"
      CRAWLAB_REDIS_ADDRESS: "redis"
    depends_on:
      - mongo
      - redis
    # environment:
    #   MONGO_INITDB_ROOT_USERNAME: username
    #   MONGO_INITDB_ROOT_PASSWORD: password
    # volumes:
    #   - "/var/crawlab/log:/var/logs/crawlab" # log persistent 日志持久化
  mongo:
    image: mongo:latest
    restart: always
    # volumes:
    #   - "/opt/crawlab/mongo/data/db:/data/db"  # make data persistent 持久化
    # ports:
    #   - "27017:27017"  # expose port to host machine 暴露接口到宿主机
  redis:
    image: redis:latest
    restart: always
    # command: redis-server --requirepass "password" # set redis password 设置 Redis 密码
    # volumes:
    #   - "/opt/crawlab/redis/data:/data"  # make data persistent 持久化
    # ports:
    #   - "6379:6379"  # expose port to host machine 暴露接口到宿主机
    # splash:  # use Splash to run spiders on dynamic pages
    #   image: scrapinghub/splash
    #   container_name: splash
    #   ports:
    #     - "8050:8050"
service docker start
su   # 按提示输入密码
docker-compose up -d
上一篇 下一篇

猜你喜欢

热点阅读