This commit is contained in:
Alexander Yakovlev 2023-04-21 23:49:05 +06:00
commit e89bee489f
5 changed files with 441 additions and 0 deletions

3
.env.example Normal file
View file

@ -0,0 +1,3 @@
DIRECTUS_EMAIL=""
DIRECTUS_PASSWORD=""
DIRECTUS_HOST="https://directus.anquet.com"

2
.gitignore vendored Normal file
View file

@ -0,0 +1,2 @@
.env
node_modules

13
package.json Normal file
View file

@ -0,0 +1,13 @@
{
"type": "module",
"dependencies": {
"@directus/sdk": "^10.3.3",
"cheerio": "1.0.0-rc.12",
"dotenv": "^16.0.3",
"he": "^1.2.0",
"ioredis": "^5.3.2",
"node-fetch": "^3.3.1",
"slug": "^8.2.2",
"turndown": "^7.1.2"
}
}

331
pnpm-lock.yaml Normal file
View file

@ -0,0 +1,331 @@
lockfileVersion: '6.0'
dependencies:
'@directus/sdk':
specifier: ^10.3.3
version: 10.3.3
cheerio:
specifier: 1.0.0-rc.12
version: 1.0.0-rc.12
dotenv:
specifier: ^16.0.3
version: 16.0.3
he:
specifier: ^1.2.0
version: 1.2.0
ioredis:
specifier: ^5.3.2
version: 5.3.2
node-fetch:
specifier: ^3.3.1
version: 3.3.1
slug:
specifier: ^8.2.2
version: 8.2.2
turndown:
specifier: ^7.1.2
version: 7.1.2
packages:
/@directus/sdk@10.3.3:
resolution: {integrity: sha512-58gw+QjkuIr0lJFRx5HwSp1ewAf7rjfV++eJqAmC13p7vif9wfJEcWcJwqXstYdvtJVUg+nB4O/CE0OBEtp5HQ==}
dependencies:
axios: 0.27.2
transitivePeerDependencies:
- debug
dev: false
/@ioredis/commands@1.2.0:
resolution: {integrity: sha512-Sx1pU8EM64o2BrqNpEO1CNLtKQwyhuXuqyfH7oGKCk+1a33d2r5saW8zNwm3j6BTExtjrv2BxTgzzkMwts6vGg==}
dev: false
/asynckit@0.4.0:
resolution: {integrity: sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q==}
dev: false
/axios@0.27.2:
resolution: {integrity: sha512-t+yRIyySRTp/wua5xEr+z1q60QmLq8ABsS5O9Me1AsE5dfKqgnCFzwiCZZ/cGNd1lq4/7akDWMxdhVlucjmnOQ==}
dependencies:
follow-redirects: 1.15.2
form-data: 4.0.0
transitivePeerDependencies:
- debug
dev: false
/boolbase@1.0.0:
resolution: {integrity: sha512-JZOSA7Mo9sNGB8+UjSgzdLtokWAky1zbztM3WRLCbZ70/3cTANmQmOdR7y2g+J0e2WXywy1yS468tY+IruqEww==}
dev: false
/cheerio-select@2.1.0:
resolution: {integrity: sha512-9v9kG0LvzrlcungtnJtpGNxY+fzECQKhK4EGJX2vByejiMX84MFNQw4UxPJl3bFbTMw+Dfs37XaIkCwTZfLh4g==}
dependencies:
boolbase: 1.0.0
css-select: 5.1.0
css-what: 6.1.0
domelementtype: 2.3.0
domhandler: 5.0.3
domutils: 3.0.1
dev: false
/cheerio@1.0.0-rc.12:
resolution: {integrity: sha512-VqR8m68vM46BNnuZ5NtnGBKIE/DfN0cRIzg9n40EIq9NOv90ayxLBXA8fXC5gquFRGJSTRqBq25Jt2ECLR431Q==}
engines: {node: '>= 6'}
dependencies:
cheerio-select: 2.1.0
dom-serializer: 2.0.0
domhandler: 5.0.3
domutils: 3.0.1
htmlparser2: 8.0.2
parse5: 7.1.2
parse5-htmlparser2-tree-adapter: 7.0.0
dev: false
/cluster-key-slot@1.1.2:
resolution: {integrity: sha512-RMr0FhtfXemyinomL4hrWcYJxmX6deFdCxpJzhDttxgO1+bcCnkk+9drydLVDmAMG7NE6aN/fl4F7ucU/90gAA==}
engines: {node: '>=0.10.0'}
dev: false
/combined-stream@1.0.8:
resolution: {integrity: sha512-FQN4MRfuJeHf7cBbBMJFXhKSDq+2kAArBlmRBvcvFE5BB1HZKXtSFASDhdlz9zOYwxh8lDdnvmMOe/+5cdoEdg==}
engines: {node: '>= 0.8'}
dependencies:
delayed-stream: 1.0.0
dev: false
/css-select@5.1.0:
resolution: {integrity: sha512-nwoRF1rvRRnnCqqY7updORDsuqKzqYJ28+oSMaJMMgOauh3fvwHqMS7EZpIPqK8GL+g9mKxF1vP/ZjSeNjEVHg==}
dependencies:
boolbase: 1.0.0
css-what: 6.1.0
domhandler: 5.0.3
domutils: 3.0.1
nth-check: 2.1.1
dev: false
/css-what@6.1.0:
resolution: {integrity: sha512-HTUrgRJ7r4dsZKU6GjmpfRK1O76h97Z8MfS1G0FozR+oF2kG6Vfe8JE6zwrkbxigziPHinCJ+gCPjA9EaBDtRw==}
engines: {node: '>= 6'}
dev: false
/data-uri-to-buffer@4.0.1:
resolution: {integrity: sha512-0R9ikRb668HB7QDxT1vkpuUBtqc53YyAwMwGeUFKRojY/NWKvdZ+9UYtRfGmhqNbRkTSVpMbmyhXipFFv2cb/A==}
engines: {node: '>= 12'}
dev: false
/debug@4.3.4:
resolution: {integrity: sha512-PRWFHuSU3eDtQJPvnNY7Jcket1j0t5OuOsFzPPzsekD52Zl8qUfFIPEiswXqIvHWGVHOgX+7G/vCNNhehwxfkQ==}
engines: {node: '>=6.0'}
peerDependencies:
supports-color: '*'
peerDependenciesMeta:
supports-color:
optional: true
dependencies:
ms: 2.1.2
dev: false
/delayed-stream@1.0.0:
resolution: {integrity: sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==}
engines: {node: '>=0.4.0'}
dev: false
/denque@2.1.0:
resolution: {integrity: sha512-HVQE3AAb/pxF8fQAoiqpvg9i3evqug3hoiwakOyZAwJm+6vZehbkYXZ0l4JxS+I3QxM97v5aaRNhj8v5oBhekw==}
engines: {node: '>=0.10'}
dev: false
/dom-serializer@2.0.0:
resolution: {integrity: sha512-wIkAryiqt/nV5EQKqQpo3SToSOV9J0DnbJqwK7Wv/Trc92zIAYZ4FlMu+JPFW1DfGFt81ZTCGgDEabffXeLyJg==}
dependencies:
domelementtype: 2.3.0
domhandler: 5.0.3
entities: 4.5.0
dev: false
/domelementtype@2.3.0:
resolution: {integrity: sha512-OLETBj6w0OsagBwdXnPdN0cnMfF9opN69co+7ZrbfPGrdpPVNBUj02spi6B1N7wChLQiPn4CSH/zJvXw56gmHw==}
dev: false
/domhandler@5.0.3:
resolution: {integrity: sha512-cgwlv/1iFQiFnU96XXgROh8xTeetsnJiDsTc7TYCLFd9+/WNkIqPTxiM/8pSd8VIrhXGTf1Ny1q1hquVqDJB5w==}
engines: {node: '>= 4'}
dependencies:
domelementtype: 2.3.0
dev: false
/domino@2.1.6:
resolution: {integrity: sha512-3VdM/SXBZX2omc9JF9nOPCtDaYQ67BGp5CoLpIQlO2KCAPETs8TcDHacF26jXadGbvUteZzRTeos2fhID5+ucQ==}
dev: false
/domutils@3.0.1:
resolution: {integrity: sha512-z08c1l761iKhDFtfXO04C7kTdPBLi41zwOZl00WS8b5eiaebNpY00HKbztwBq+e3vyqWNwWF3mP9YLUeqIrF+Q==}
dependencies:
dom-serializer: 2.0.0
domelementtype: 2.3.0
domhandler: 5.0.3
dev: false
/dotenv@16.0.3:
resolution: {integrity: sha512-7GO6HghkA5fYG9TYnNxi14/7K9f5occMlp3zXAuSxn7CKCxt9xbNWG7yF8hTCSUchlfWSe3uLmlPfigevRItzQ==}
engines: {node: '>=12'}
dev: false
/entities@4.5.0:
resolution: {integrity: sha512-V0hjH4dGPh9Ao5p0MoRY6BVqtwCjhz6vI5LT8AJ55H+4g9/4vbHx1I54fS0XuclLhDHArPQCiMjDxjaL8fPxhw==}
engines: {node: '>=0.12'}
dev: false
/fetch-blob@3.2.0:
resolution: {integrity: sha512-7yAQpD2UMJzLi1Dqv7qFYnPbaPx7ZfFK6PiIxQ4PfkGPyNyl2Ugx+a/umUonmKqjhM4DnfbMvdX6otXq83soQQ==}
engines: {node: ^12.20 || >= 14.13}
dependencies:
node-domexception: 1.0.0
web-streams-polyfill: 3.2.1
dev: false
/follow-redirects@1.15.2:
resolution: {integrity: sha512-VQLG33o04KaQ8uYi2tVNbdrWp1QWxNNea+nmIB4EVM28v0hmP17z7aG1+wAkNzVq4KeXTq3221ye5qTJP91JwA==}
engines: {node: '>=4.0'}
peerDependencies:
debug: '*'
peerDependenciesMeta:
debug:
optional: true
dev: false
/form-data@4.0.0:
resolution: {integrity: sha512-ETEklSGi5t0QMZuiXoA/Q6vcnxcLQP5vdugSpuAyi6SVGi2clPPp+xgEhuMaHC+zGgn31Kd235W35f7Hykkaww==}
engines: {node: '>= 6'}
dependencies:
asynckit: 0.4.0
combined-stream: 1.0.8
mime-types: 2.1.35
dev: false
/formdata-polyfill@4.0.10:
resolution: {integrity: sha512-buewHzMvYL29jdeQTVILecSaZKnt/RJWjoZCF5OW60Z67/GmSLBkOFM7qh1PI3zFNtJbaZL5eQu1vLfazOwj4g==}
engines: {node: '>=12.20.0'}
dependencies:
fetch-blob: 3.2.0
dev: false
/he@1.2.0:
resolution: {integrity: sha512-F/1DnUGPopORZi0ni+CvrCgHQ5FyEAHRLSApuYWMmrbSwoN2Mn/7k+Gl38gJnR7yyDZk6WLXwiGod1JOWNDKGw==}
hasBin: true
dev: false
/htmlparser2@8.0.2:
resolution: {integrity: sha512-GYdjWKDkbRLkZ5geuHs5NY1puJ+PXwP7+fHPRz06Eirsb9ugf6d8kkXav6ADhcODhFFPMIXyxkxSuMf3D6NCFA==}
dependencies:
domelementtype: 2.3.0
domhandler: 5.0.3
domutils: 3.0.1
entities: 4.5.0
dev: false
/ioredis@5.3.2:
resolution: {integrity: sha512-1DKMMzlIHM02eBBVOFQ1+AolGjs6+xEcM4PDL7NqOS6szq7H9jSaEkIUH6/a5Hl241LzW6JLSiAbNvTQjUupUA==}
engines: {node: '>=12.22.0'}
dependencies:
'@ioredis/commands': 1.2.0
cluster-key-slot: 1.1.2
debug: 4.3.4
denque: 2.1.0
lodash.defaults: 4.2.0
lodash.isarguments: 3.1.0
redis-errors: 1.2.0
redis-parser: 3.0.0
standard-as-callback: 2.1.0
transitivePeerDependencies:
- supports-color
dev: false
/lodash.defaults@4.2.0:
resolution: {integrity: sha512-qjxPLHd3r5DnsdGacqOMU6pb/avJzdh9tFX2ymgoZE27BmjXrNy/y4LoaiTeAb+O3gL8AfpJGtqfX/ae2leYYQ==}
dev: false
/lodash.isarguments@3.1.0:
resolution: {integrity: sha512-chi4NHZlZqZD18a0imDHnZPrDeBbTtVN7GXMwuGdRH9qotxAjYs3aVLKc7zNOG9eddR5Ksd8rvFEBc9SsggPpg==}
dev: false
/mime-db@1.52.0:
resolution: {integrity: sha512-sPU4uV7dYlvtWJxwwxHD0PuihVNiE7TyAbQ5SWxDCB9mUYvOgroQOwYQQOKPJ8CIbE+1ETVlOoK1UC2nU3gYvg==}
engines: {node: '>= 0.6'}
dev: false
/mime-types@2.1.35:
resolution: {integrity: sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw==}
engines: {node: '>= 0.6'}
dependencies:
mime-db: 1.52.0
dev: false
/ms@2.1.2:
resolution: {integrity: sha512-sGkPx+VjMtmA6MX27oA4FBFELFCZZ4S4XqeGOXCv68tT+jb3vk/RyaKWP0PTKyWtmLSM0b+adUTEvbs1PEaH2w==}
dev: false
/node-domexception@1.0.0:
resolution: {integrity: sha512-/jKZoMpw0F8GRwl4/eLROPA3cfcXtLApP0QzLmUT/HuPCZWyB7IY9ZrMeKw2O/nFIqPQB3PVM9aYm0F312AXDQ==}
engines: {node: '>=10.5.0'}
dev: false
/node-fetch@3.3.1:
resolution: {integrity: sha512-cRVc/kyto/7E5shrWca1Wsea4y6tL9iYJE5FBCius3JQfb/4P4I295PfhgbJQBLTx6lATE4z+wK0rPM4VS2uow==}
engines: {node: ^12.20.0 || ^14.13.1 || >=16.0.0}
dependencies:
data-uri-to-buffer: 4.0.1
fetch-blob: 3.2.0
formdata-polyfill: 4.0.10
dev: false
/nth-check@2.1.1:
resolution: {integrity: sha512-lqjrjmaOoAnWfMmBPL+XNnynZh2+swxiX3WUE0s4yEHI6m+AwrK2UZOimIRl3X/4QctVqS8AiZjFqyOGrMXb/w==}
dependencies:
boolbase: 1.0.0
dev: false
/parse5-htmlparser2-tree-adapter@7.0.0:
resolution: {integrity: sha512-B77tOZrqqfUfnVcOrUvfdLbz4pu4RopLD/4vmu3HUPswwTA8OH0EMW9BlWR2B0RCoiZRAHEUu7IxeP1Pd1UU+g==}
dependencies:
domhandler: 5.0.3
parse5: 7.1.2
dev: false
/parse5@7.1.2:
resolution: {integrity: sha512-Czj1WaSVpaoj0wbhMzLmWD69anp2WH7FXMB9n1Sy8/ZFF9jolSQVMu1Ij5WIyGmcBmhk7EOndpO4mIpihVqAXw==}
dependencies:
entities: 4.5.0
dev: false
/redis-errors@1.2.0:
resolution: {integrity: sha512-1qny3OExCf0UvUV/5wpYKf2YwPcOqXzkwKKSmKHiE6ZMQs5heeE/c8eXK+PNllPvmjgAbfnsbpkGZWy8cBpn9w==}
engines: {node: '>=4'}
dev: false
/redis-parser@3.0.0:
resolution: {integrity: sha512-DJnGAeenTdpMEH6uAJRK/uiyEIH9WVsUmoLwzudwGJUwZPp80PDBWPHXSAGNPwNvIXAbe7MSUB1zQFugFml66A==}
engines: {node: '>=4'}
dependencies:
redis-errors: 1.2.0
dev: false
/slug@8.2.2:
resolution: {integrity: sha512-5ByW6qXqPeG0Tmlkh24JhdXhvQsbaJSjVr3GgGxUV0BSskZKKBZZfFWxezap8+fh1vxBN9GVbqI1V6nqAFxlBg==}
hasBin: true
dev: false
/standard-as-callback@2.1.0:
resolution: {integrity: sha512-qoRRSyROncaz1z0mvYqIE4lCd9p2R90i6GxW3uZv5ucSu8tU7B5HXUP1gG8pVZsYNVaXjk8ClXHPttLyxAL48A==}
dev: false
/turndown@7.1.2:
resolution: {integrity: sha512-ntI9R7fcUKjqBP6QU8rBK2Ehyt8LAzt3UBT9JR9tgo6GtuKvyUzpayWmeMKJw1DPdXzktvtIT8m2mVXz+bL/Qg==}
dependencies:
domino: 2.1.6
dev: false
/web-streams-polyfill@3.2.1:
resolution: {integrity: sha512-e0MO3wdXWKrLbL0DgGnUV7WHVuw9OUvL4hjgnPkIeEvESk74gAITi5G606JtZPp39cd8HA9VQzCIvA49LpPN5Q==}
engines: {node: '>= 8'}
dev: false

92
update.js Normal file
View file

@ -0,0 +1,92 @@
import { Directus } from '@directus/sdk';
import TurndownService from 'turndown';
import fs from 'fs';
import he from 'he';
import * as cheerio from 'cheerio';
import slug from 'slug';
import Redis from 'ioredis';
import * as dotenv from 'dotenv' // see https://github.com/motdotla/dotenv#how-do-i-use-dotenv-with-import
dotenv.config()
const directus = new Directus(process.env.DIRECTUS_HOST);
const turndownService = new TurndownService()
const htmlString = fs.readFileSync('Solutions.xml').toString();
const $ = cheerio.load(htmlString);
const redis = new Redis();
async function start() {
await directus.auth.login({ process.env.DIRECTUS_EMAIL, process.env.DIRECTUS_PASSWORD })
.catch(() => {
console.error('Invalid credentials');
});
$('solution-article').each(async function(i, element) {
let parentTitle = $("name", $(this).parent().parent()).html();
let title = he.decode($(this).children("title").html());
let description = he.decode($(this).children("description").html());
let images = $(description).children("img");
const title_slug = slug(parentTitle)+"/"+slug(title)
let original_id = parseInt(he.decode($(this).children("id").html()));
await redis.hset("pageurls", original_id, title_slug);
console.log('Parsing images');
images.each(async function(e, image) {
let imageUrl = $(image).attr('src');
let uploaded = redis.hget("images", imageUrl);
if (!uploaded) {
let file = directus.files.import({
url: imageUrl,
});
await redis.hset("images", imageUrl, 'https://directus.anquet.com/assets/' + file.id + '-' + file.width + '-' + file.height);
}
});
description = turndownService.turndown(description);
console.log('Saving page '+title);
await redis.hset("pages", original_id, JSON.stringify({
title: title,
content: description,
status: 'published',
original_id: original_id,
url: slug(title),
}))
return Promise.resolve();
});
const articles = directus.items('omn2omn3');
const translations = directus.items('omn2omn3_translations');
const pages = await redis.hgetall("pages");
const images = await redis.hgetall("images");
Object.keys(pages).forEach(async function (original_id) {
const page = JSON.parse(pages[original_id])
const reg = new RegExp(/https:\/\/support.anquet.com\/support\/solutions\/articles\/(\d+)-?/gm);
for (const match of page.content.matchAll(reg)) {
const title_slug = await redis.hget("pageurls", match[1]);
if (title_slug) {
const reg2 = new RegExp("/\(https:\/\/support.anquet.com\/support\/solutions\/articles\/"+match[1]+"-?.*\)/gm");
page.content.replace(reg2, '('+title_slug+')');
}
}
Object.keys(images).forEach(async function (image_url) {
page.content.replace(image_url, images[image_url])
});
const content = await translations.createOne({
languages_code: 'en-GB',
markdown: page.content,
});
await articles.createOne({
title: page.title,
translations: [content.id],
status: 'published',
original_id: original_id,
url: page.url,
}).then(function() {
console.log("Added "+page.title);
});
return Promise.resolve();
})
}
start();