docker 构建scrapyd

docker 构建scrapyd

Dockerfile

`

FROM selenium/standalone-chrome:85.0-chromedriver-85.0-20200907
USER root

RUN apt-get update && \
  apt-get install -y xvfb && \
  apt-get install -y python3-distutils && \
  curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py && \
  python3 get-pip.py
ENV TimeZone=Asia/Shanghai   
RUN ln -snf /usr/share/zoneinfo/$TimeZone /etc/localtime && echo $TimeZone > /etc/timezone
WORKDIR /app
COPY requirements.txt .
COPY ./scrapyd.conf /etc/scrapyd/
EXPOSE 6800
RUN python3 -m pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple/
COPY . .
CMD scrapyd

`

requirements.txt

`

attrs
Automat
backports.zoneinfo
certifi
cffi
charset-normalizer
colorama
constantly
cryptography
cssselect
dateparser
Deprecated
Distance
environs
Faker
filelock
gerapy-auto-extractor
gne
hyperlink
idna
incremental
itemadapter
itemloaders
jmespath
joblib
loguru
lxml
marshmallow
numpy
packaging
parsel
Protego
pyasn1
pyasn1-modules
pycparser
PyDispatcher
pymongo
pyOpenSSL
pyparsing
python-dateutil
python-dotenv
pytz
pytz-deprecation-shim
PyYAML
queuelib
redis
regex
requests
requests-file
scikit-learn
scipy
Scrapy
scrapy-redis
service-identity
six
threadpoolctl
tldextract
Twisted
typing_extensions
tzdata
tzlocal
urllib3
w3lib
win32-setctime
wrapt
zope.interface
requests
selenium
aiohttp
beautifulsoup4
pyquery
pymysql
redis
pymongo
flask
django
scrapy
scrapyd
scrapyd-client
scrapy-redis
scrapy-splash

`

scrapyd.conf

`

[scrapyd]
eggs_dir    = eggs
logs_dir    = logs
items_dir   =
jobs_to_keep = 5
dbs_dir     = 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

`

创建scrapyd文件夹，将三个文件放进去，然后编译就可以了