背景
公司制品库迁移，要将npm库从原制品库nexus迁移到artifactory中。涉及到近千的依赖包，手动太过费时。因此通过python脚本进行批量操作
思路
梳理思路，单个包的迁移步骤如下：下载包->修改包（package.json）中仓库地址->执行npm publish命令。
与单个包相比，批量操作还需要能拿到包的所有下载地址，在推送之前需要登录npm并设置全局repository地址。
获取包的下载地址
仓库包组件不多，但版本多。因此我选择直接在浏览器中console通过js脚本获取url，如果组件较多建议写脚本获取。
// 将数据以文件形式存储
(function (console) {
console.save = function (data, filename) {
if (!data) {
console.error('Console.save: No data')
return;
}
if (!filename) filename = 'console.json'
if (typeof data === "object") {
data = JSON.stringify(data, undefined, 4)
}
var blob = new Blob([data], { type: 'text/json' }),
e = document.createEvent('MouseEvents'),
a = document.createElement('a')
a.download = filename
a.href = window.URL.createObjectURL(blob)
a.dataset.downloadurl = ['text/json', a.download, a.href].join(':')
e.initMouseEvent('click', true, false, window, 0, 0, 0, 0, 0, false, false, false, false, 0, null)
a.dispatchEvent(e)
}
})(console)
//获取a标签中url
function getHref(a){
var urlArr = new Array();
var hrefArr = document.getElementsByTagName('a'); //获取这个页面的所有A标签
for( var i=0; i<hrefArr.length; i++ ){
hrefURL = hrefArr[i].href;
urlArr[i] = hrefURL;
}
console.save(urlArr,a);
}
//执行获取脚本
getHref("XXXX.txt");
获取到的url文件（XXXX.txt）如下：
[
"http://xxxx.com/service/rest/repository/browse/npm/xxxx/",
"http://xxxx.com/repository/npm/xxxx/xxxx.tgz"
]
python 脚本
目录
tmp_package
tmp_tar_package
tmp_utar_package
urls
auto.py
replace_file.py
tmp_package、tmp_tar_package、tmp_utar_package目录为空目录，urls中存放上一部中获取的url文件；
代码
- replace_file.py
def replace_content(file,old_content,new_content):
content=read_file(file)
content=content.replace(old_content,new_content)
rewrite_file(file,content)
#读文件
def read_file(file):
with open(file,encoding='UTF-8') as f:
read_all = f.read()
f.close()
return read_all
#写内容到文件
def rewrite_file(file,data):
with open(file,'w',encoding='UTF-8') as f:
f.write(data)
f.close()
- auto.py，运行脚本前需要登录有权限的npm账号
import wget
import os
import shutil
import tarfile
import replace_file
import urllib.parse
path='tmp_package/'
utar_path='tmp_utar_package/'
tar_path='tmp_tar_package/'
def tzgName(url):
#根据url获取压缩包名称
arr=url.split('-/')
return arr[1]
def readPackageUrls(f):
#从文件中读取地址
urls = []
f = 'urls/'+f
file=open(f)
data_lists=file.readlines()
for i in data_lists:
if i.rfind('.tgz') != -1:
urls.append(i.replace('"','').replace(',\n',''))
return urls
def dowanloadPackages(urls):
#下载文件
for u in urls:
u=u.strip()
u=urllib.parse.unquote(u)
name = path + tzgName(u)
print(u)
print(name)
t=wget.download(u,name)
return 'download success! size: '
def utar():
#文件解压
for f in os.listdir(path):
dest_dir=f.replace('.tgz','')
dest_dir=utar_path+dest_dir
f=path+f
try:
tar=tarfile.open(f)
names=tar.getnames()
for name in names:
tar.extract(name,dest_dir)
tar.close()
except Exception as e:
print(e)
def ptar():
#这个没用
for f in os.listdir(utar_path):
tar = tar_path+f+'.tgz'
f=utar_path+f+'/package/'
try:
with tarfile.open(tar,'w:gz') as tar:
tar.add(f,arcname=os.path.basename(f))
except Exception as e:
print(e)
def repalce():
#这一步把需要替换的文件中字符串替换掉，主要是仓库地址
old_path='http://xxxx.com/repository/npm/'
old_path1='http://xxxx.cn/repository/npm/'
new_path='https://xxxx.com/artifactory/api/npm/npm-releases/'
for f in os.listdir(utar_path):
package_path= utar_path + f + '/package/package.json'
replace_file.replace_content(package_path,old_path,new_path)
replace_file.replace_content(package_path,old_path1,new_path)
def dealPackage():
utar()
repalce()
# ptar()
return 'deal package success!'
def pushPackage():
for i in os.listdir(utar_path):
p = utar_path+i+'/package/'
shell= 'cd ' + p + ' & npm publish & cd ../../../'
print(shell)
os.system(shell)
return 'publish package success!'
def cleanTmp():
shutil.rmtree(path)
shutil.rmtree(utar_path)
shutil.rmtree(tar_path)
os.makedirs(path)
os.makedirs(utar_path)
os.makedirs(tar_path)
cleanTmp()
sum = 0
for f in os.listdir('urls'):
us = readPackageUrls(f)
cleanTmp()
dowan=dowanloadPackages(us)
deal=dealPackage()
push=pushPackage()
print('处理文件：%s，共:%d条数据'%(f,len(us)))
sum+=len(us)
print('共处理文件：%d 条数据'%(sum))
