基于alpine用dockerfile創(chuàng)建的爬蟲Scrapy鏡像的實現(xiàn)

[root@DockerBrian ~]# docker pull alpine
Using default tag: latest
Trying to pull repository docker.io/library/alpine ...
latest: Pulling from docker.io/library/alpine
4fe2ade4980c: Pull complete
Digest: sha256:621c2f39f8133acb8e64023a94dbdf0d5ca81896102b9e57c0dc184cadaf5528
Status: Downloaded newer image for docker.io/alpine:latest
[root@docker43 ~]# docker images
REPOSITORY TAG IMAGE ID CREATED SIZE
docker.io/alpine latest 196d12cf6ab1 3 weeks ago 4.41 MB 

[root@DockerBrian ~]# mkdir /opt/alpineDockerfile/
[root@DockerBrian ~]# cd /opt/alpineDockerfile/
[root@DockerBrian alpineDockerfile]# mkdir scrapy && cd scrapy && touch Dockerfile
[root@DockerBrian alpineDockerfile]# cd scrapy/
[root@DockerBrian scrapy]# ll
總用量 4
-rw-r--r-- 1 root root 1394 10月 10 11:36 Dockerfile 

# 指定創(chuàng)建的基礎(chǔ)鏡像
FROM alpine
 
# 作者描述信息
MAINTAINER alpine_python3_scrapy (zhujingzhi@123.com)
 
# 替換阿里云的源
RUN echo "http://mirrors.aliyun.com/alpine/latest-stable/main/" > /etc/apk/repositories && \

  echo "http://mirrors.aliyun.com/alpine/latest-stable/community/" >> /etc/apk/repositories
 
# 同步時間
 
# 更新源、安裝openssh 并修改配置文件和生成key 并且同步時間
RUN apk update && \

  apk add --no-cache openssh-server tzdata && \

  cp /usr/share/zoneinfo/Asia/Shanghai /etc/localtime && \

  sed -i "s/#PermitRootLogin.*/PermitRootLogin yes/g" /etc/ssh/sshd_config && \

  ssh-keygen -t rsa -P "" -f /etc/ssh/ssh_host_rsa_key && \

  ssh-keygen -t ecdsa -P "" -f /etc/ssh/ssh_host_ecdsa_key && \

  ssh-keygen -t ed25519 -P "" -f /etc/ssh/ssh_host_ed25519_key && \

  echo "root:h056zHJLg85oW5xh7VtSa" | chpasswd
 
# 安裝Scrapy依賴包(必須安裝的依賴包)
RUN apk add --no-cache python3 python3-dev gcc openssl-dev openssl libressl libc-dev linux-headers libffi-dev libxml2-dev libxml2 libxslt-dev openssh-client openssh-sftp-server
 
# 安裝環(huán)境需要pip包(這里的包可以按照需求添加或者刪除)
RUN pip3 install --default-timeout=100 --no-cache-dir --upgrade pip setuptools pymysql pymongo redis scrapy-redis ipython Scrapy requests
 
# 啟動ssh腳本
RUN echo "/usr/sbin/sshd -D" >> /etc/start.sh && \

  chmod +x /etc/start.sh
 
# 開放22端口
EXPOSE 22
 
# 執(zhí)行ssh啟動命令
CMD ["/bin/sh","/etc/start.sh"] 

[root@DockerBrian scrapy]# docker build -t scrapy_redis_ssh:v1 . 

[root@DockerBrian scrapy]# docker images
REPOSITORY     TAG         IMAGE ID      CREATED       SIZE
scrapy_redis_ssh  v1         b2c95ef95fb9    4 hours ago     282 MB
docker.io/alpine  latest       196d12cf6ab1    4 weeks ago     4.41 MB 

[root@DockerBrian scrapy]# docker ps
CONTAINER ID    IMAGE        COMMAND         CREATED       STATUS       PORTS          NAMES
7fb9e69d79f5    b2c95ef95fb9    "/bin/sh /etc/star..."  3 hours ago     Up 3 hours     0.0.0.0:10086->22/tcp  scrapy10086 

[root@DockerBrian scrapy]# ssh root@127.0.0.1 -p 10086 
The authenticity of host '[127.0.0.1]:10086 ([127.0.0.1]:10086)' can't be established.
ECDSA key fingerprint is SHA256:wC46AU6SLjHyEfQWX6d6ht9MdpGKodeMOK6/cONcpxk.
ECDSA key fingerprint is MD5:6a:b7:31:3c:63:02:ca:74:5b:d9:68:42:08:be:22:fc.
Are you sure you want to continue connecting (yes/no)? yes
Warning: Permanently added '[127.0.0.1]:10086' (ECDSA) to the list of known hosts.
root@127.0.0.1's password:                                # 這里的密碼就是dockerfile中定義的 echo "root:h056zHJLg85oW5xh7VtSa" | chpasswd
Welcome to Alpine!
 
The Alpine Wiki contains a large amount of how-to guides and general
information about administrating Alpine systems.
See <http://wiki.alpinelinux.org>.
 
You can setup the system with the command: setup-alpine
 
You may change this message by editing /etc/motd.
 
7363738cc96a:~# 

7363738cc96a:~# scrapy startproject test
New Scrapy project 'test', using template directory '/usr/lib/python3.6/site-packages/scrapy/templates/project', created in:
  /root/test
 
You can start your first spider with:
  cd test
  scrapy genspider example example.com
7363738cc96a:~# cd test/
7363738cc96a:~/test# ls
scrapy.cfg test
7363738cc96a:~/test# cd test/
7363738cc96a:~/test/test# ls
__init__.py   __pycache__   items.py    middlewares.py pipelines.py  settings.py   spiders
7363738cc96a:~/test/test#