CentOS7之Scrapy爬虫部署

天才小飞猫

scrapyd

安装:

sudo pip install scrapyd

配置:

#文件~/.scrapyd.conf
#内容如下:
[scrapyd]
eggs_dir    = /home/sirius/scrapyd/eggs
logs_dir    = /home/sirius/scrapyd/logs
items_dir   = /home/sirius/scrapyd/items
jobs_to_keep = 5
dbs_dir     = /home/sirius/scrapyd/dbs
max_proc    = 0
max_proc_per_cpu = 4
finished_to_keep = 50
poll_interval = 5
bind_address = 0.0.0.0
http_port   = 6800
debug       = off
runner      = scrapyd.runner
application = scrapyd.app.application
launcher    = scrapyd.launcher.Launcher
webroot     = scrapyd.website.Root

[services]
schedule.json     = scrapyd.webservice.Schedule
cancel.json       = scrapyd.webservice.Cancel
addversion.json   = scrapyd.webservice.AddVersion
listprojects.json = scrapyd.webservice.ListProjects
listversions.json = scrapyd.webservice.ListVersions
listspiders.json  = scrapyd.webservice.ListSpiders
delproject.json   = scrapyd.webservice.DeleteProject
delversion.json   = scrapyd.webservice.DeleteVersion
listjobs.json     = scrapyd.webservice.ListJobs
#daemonstatus.json = scrapyd.webservice.DaemonStatus

supervisor

守护进程,用这个的原因实在是因为scrapyd太脆弱了,一看不住就挂了

安装:

sudo pip install supervisor

配置:

sudo mkdir -p /etc/supervisor/

#导入默认配置
sudo su - root -c "echo_supervisord_conf > /etc/supervisor/supervisord.conf"

#链接管理
[inet_http_server]         ; inet (TCP) server disabled by default
port=127.0.0.1:9001        ; (ip_address:port specifier, *:port for all iface)
;username=user              ; (default is no username (open server))
;password=123               ; (default is no password (open server))  

[supervisorctl]
;serverurl=unix:///tmp/supervisor.sock ; use a unix:// URL  for a unix socket
serverurl=http://127.0.0.1:9001 ; use an http:// url to specify an inet socket
;username=chris              ; should be same as http_username if set
;password=123                ; should be same as http_password if set
;prompt=mysupervisor         ; cmd line prompt (default "supervisor")
;history_file=~/.sc_history  ; use readline history if available

#设置管理进程
[program:scrapyd]
command=scrapyd
autostart=true
autorestart=unexpected

启动

`创建文件/usr/lib/systemd/system/supervisord.service内容如下:

[Unit]                                                              
Description=supervisord - Supervisor process control system for UNIX
Documentation=http://supervisord.org                                
After=network.target                                                

[Service]                                                           
Type=forking                                                        
ExecStart=/usr/bin/supervisord -c /etc/supervisor/supervisord.conf             
ExecReload=/usr/bin/supervisorctl reload                            
ExecStop=/usr/bin/supervisorctl shutdown                            
User=<user>

[Install]                                                           
WantedBy=multi-user.target

#启动
sudo systemctl enable supervisord
sudo systemctl start supervisord

#查看
supervisorctl

#如一切正常
|>$ scrapyd   RUNNING   pid 8059, uptime 0:02:02
#常用命令
status #查看状态
reload #重新载入
restart scrapyd #重启任务
update #可以更新 supervisor 配置
tail -f scrapyd stderr #检查日志

爬虫部署:

部署:

cd <项目目录>
scrapyd-deploy

API控制:

curl http://localhost:6800/schedule.json -d project=myproject -d spider=somespider
阅读 7.4k

320 声望
16 粉丝
0 条评论
320 声望
16 粉丝
文章目录
宣传栏