BlueXIII

Technical note

Scrapyd学习笔记

阅读
Python

参考文档

scrapyd

安装

pip install scrapyd

vi /etc/scrapyd/scrapyd.conf
[scrapyd]
eggs_dir    = /data/scrapyd/eggs
logs_dir    = /data/scrapyd/logs
items_dir   = /data/scrapyd/items
jobs_to_keep = 100
dbs_dir     = /data/scrapyd/dbs
max_proc    = 0
max_proc_per_cpu = 10
finished_to_keep = 100
poll_interval = 5.0
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


nohup scrapyd>scrapyd.log 2>&1 &

open http://10.211.55.101:6800

# scrapyd服务器提前安装依赖
pip install -r requirements.txt

HTTP API

curl http://10.211.55.101:6800/daemonstatus.json
curl http://10.211.55.101:6800/addversion.json -F project=hydrabot -F version=1.0.0 -F egg=@hydrabot.egg
curl http://10.211.55.101:6800/schedule.json -d project=hydrabot -d spider=teacher -d task_id=1 -d entry_id=3070
curl http://10.211.55.101:6800/cancel.json -d project=hydrabot -d job=6487ec79947edab326d6db28a2d86S11e8247444

curl http://10.211.55.101:6800/listprojects.json
curl http://10.211.55.101:6800/listversions.json?project=hydrabot
curl http://10.211.55.101:6800/listspiders.json?project=hydrabot
curl http://10.211.55.101:6800/listjobs.json?project=hydrabot

curl http://10.211.55.101:6800/delversion.json -d project=hydrabot -d version=1.0.0
curl http://10.211.55.101:6800/delproject.json -d project=hydrabot

scrapyd-client

本机安装

pip3 install scrapyd-deploy pip3 install scrapyd-client

scrapyd-deploy -h

配置scrapy.cfg

[settings]
default = settings.default

[deploy:node5]
url = http://10.194.99.5:6800/
project = hydrabot

[deploy:node6]
url = http://10.194.99.6:6800/
project = hydrabot

[deploy:node7]
url = http://10.194.99.7:6800/
project = hydrabot

[deploy:node8]
url = http://10.194.99.8:6800/
project = hydrabot

CLI

# 部署到一个节点
scrapyd-deploy node8

# 部署到全部节点
scrapyd-deploy -a

# 列出工程
scrapyd-client -t http://10.194.99.8:6800 projects

# 查看计划任务
scrapyd-client -t http://10.194.99.8:6800  schedule -p hydrabot \istic 

# 列出爬虫
scrapyd-client -t http://10.194.99.8:6800 spiders -p hydrabot