mirror of
https://github.com/webrecorder/browsertrix-crawler.git
synced 2025-10-19 06:23:16 +00:00
5afd19f43d
* non-html page load improvements: fix for #129 - don't include cookie check in eliminating direct fetch, may be too speculative - as suggested in #129, when loading non-html, only wait for dom load and don't run behaviors - don't do text extraction for non-HTML pages (will need to handle pdf separately) bump to 0.5.0-beta.8
33 lines
919 B
JSON
33 lines
919 B
JSON
{
|
|
"name": "browsertrix-crawler",
|
|
"version": "0.5.0-beta.8",
|
|
"main": "browsertrix-crawler",
|
|
"repository": "https://github.com/webrecorder/browsertrix-crawler",
|
|
"author": "Ilya Kreymer <ikreymer@gmail.com>, Webrecorder Software",
|
|
"license": "MIT",
|
|
"scripts": {
|
|
"lint": "eslint *.js util/*.js tests/*.test.js"
|
|
},
|
|
"dependencies": {
|
|
"abort-controller": "^3.0.0",
|
|
"browsertrix-behaviors": "^0.2.5",
|
|
"ioredis": "^4.27.1",
|
|
"js-yaml": "^4.1.0",
|
|
"minio": "^7.0.26",
|
|
"node-fetch": "^2.6.1",
|
|
"puppeteer-cluster": "github:ikreymer/puppeteer-cluster#async-job-queue",
|
|
"puppeteer-core": "^13.3.2",
|
|
"request": "^2.88.2",
|
|
"sitemapper": "^3.1.2",
|
|
"uuid": "8.3.2",
|
|
"warcio": "^1.5.0",
|
|
"ws": "^7.4.4",
|
|
"yargs": "^16.0.3"
|
|
},
|
|
"devDependencies": {
|
|
"eslint": "^7.20.0",
|
|
"eslint-plugin-react": "^7.22.0",
|
|
"jest": "^26.6.3",
|
|
"md5": "^2.3.0"
|
|
}
|
|
}
|