Merge pull request #546 from lockfale/phase-1/ci-and-dead-links

Phase 1: CI/CD pipeline, dead link cleanup, and URL normalization
This commit is contained in:
s0lray
2026-03-21 23:01:52 -04:00
committed by GitHub
9 changed files with 10061 additions and 6784 deletions
+90
View File
@@ -0,0 +1,90 @@
name: CI
on:
push:
branches: [master]
pull_request:
branches: [master]
schedule:
# Run link check weekly on Sunday at 02:00 UTC
- cron: '0 2 * * 0'
jobs:
json-lint:
name: JSON Lint
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Validate arf.json is well-formed
run: python3 -m json.tool public/arf.json > /dev/null
smoke-test:
name: Smoke Test
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Check index.html local asset references exist
run: |
check_asset() {
local path="public/$1"
if [ ! -f "$path" ]; then
echo "MISSING: $path"
exit 1
else
echo "OK: $path"
fi
}
check_asset "css/arf.css"
check_asset "js/d3.v3.min.js"
check_asset "js/arf.js"
check_asset "arf.json"
link-check:
name: Link Check
runs-on: ubuntu-latest
# Only run on schedule and direct pushes to master, not on every PR
# (avoids hammering external sites during code review)
if: github.event_name == 'schedule' || (github.event_name == 'push' && github.ref == 'refs/heads/master')
steps:
- uses: actions/checkout@v4
- name: Extract URLs from arf.json
run: |
python3 -c "
import json, re, sys
with open('public/arf.json') as f:
data = json.load(f)
def extract_urls(node):
urls = []
url = node.get('url', '')
if url and url.startswith('http'):
urls.append(url)
for child in node.get('children', []):
urls.extend(extract_urls(child))
return urls
urls = extract_urls(data)
print(f'Found {len(urls)} URLs', file=sys.stderr)
with open('urls.txt', 'w') as f:
f.write('\n'.join(urls))
"
- name: Run lychee link checker
uses: lycheeverse/lychee-action@v2
with:
args: |
--verbose
--no-progress
--timeout 20
--max-retries 2
--retry-wait-time 5
--exclude-mail
--accept 200,201,204,206,301,302,307,308,403,429
urls.txt
fail: true
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+6
View File
@@ -1,7 +1,13 @@
# agent / org files #
######################
agents/
# vendor packages #
######################
public/js/vendor
node_modules
bower_components
.bowerrc
# OS generated files #
######################
-13
View File
@@ -1,13 +0,0 @@
{
"name": "ARF",
"main": "index.html",
"homepage": "https://github.com/lockfale/ARF",
"authors": [
"Justin Nordine (s0lray)"
],
"description": "Advanced Reconnaissance Framework",
"license": "",
"dependencies": {
"d3": "3.5.16"
}
}
+836 -8
View File
@@ -10,7 +10,7 @@
"hasInstallScript": true,
"devDependencies": {
"copyfiles": "^1.0.0",
"d3": "^3.5.16"
"d3": "^7.9.0"
}
},
"node_modules/balanced-match": {
@@ -29,6 +29,16 @@
"concat-map": "0.0.1"
}
},
"node_modules/commander": {
"version": "7.2.0",
"resolved": "https://registry.npmjs.org/commander/-/commander-7.2.0.tgz",
"integrity": "sha512-QrWXB+ZQSVPmIWIhtEO9H+gwHaMGYiF5ChvoJ+K9ZGHG/sVsa6yiesAD1GC/x46sET00Xlwo1u49RVVVzvcSkw==",
"dev": true,
"license": "MIT",
"engines": {
"node": ">= 10"
}
},
"node_modules/concat-map": {
"version": "0.0.1",
"resolved": "https://registry.npmjs.org/concat-map/-/concat-map-0.0.1.tgz",
@@ -60,10 +70,447 @@
"dev": true
},
"node_modules/d3": {
"version": "3.5.17",
"resolved": "https://registry.npmjs.org/d3/-/d3-3.5.17.tgz",
"integrity": "sha512-yFk/2idb8OHPKkbAL8QaOaqENNoMhIaSHZerk3oQsECwkObkCpJyjYwCe+OHiq6UEdhe1m8ZGARRRO3ljFjlKg==",
"dev": true
"version": "7.9.0",
"resolved": "https://registry.npmjs.org/d3/-/d3-7.9.0.tgz",
"integrity": "sha512-e1U46jVP+w7Iut8Jt8ri1YsPOvFpg46k+K8TpCb0P+zjCkjkPnV7WzfDJzMHy1LnA+wj5pLT1wjO901gLXeEhA==",
"dev": true,
"license": "ISC",
"dependencies": {
"d3-array": "3",
"d3-axis": "3",
"d3-brush": "3",
"d3-chord": "3",
"d3-color": "3",
"d3-contour": "4",
"d3-delaunay": "6",
"d3-dispatch": "3",
"d3-drag": "3",
"d3-dsv": "3",
"d3-ease": "3",
"d3-fetch": "3",
"d3-force": "3",
"d3-format": "3",
"d3-geo": "3",
"d3-hierarchy": "3",
"d3-interpolate": "3",
"d3-path": "3",
"d3-polygon": "3",
"d3-quadtree": "3",
"d3-random": "3",
"d3-scale": "4",
"d3-scale-chromatic": "3",
"d3-selection": "3",
"d3-shape": "3",
"d3-time": "3",
"d3-time-format": "4",
"d3-timer": "3",
"d3-transition": "3",
"d3-zoom": "3"
},
"engines": {
"node": ">=12"
}
},
"node_modules/d3-array": {
"version": "3.2.4",
"resolved": "https://registry.npmjs.org/d3-array/-/d3-array-3.2.4.tgz",
"integrity": "sha512-tdQAmyA18i4J7wprpYq8ClcxZy3SC31QMeByyCFyRt7BVHdREQZ5lpzoe5mFEYZUWe+oq8HBvk9JjpibyEV4Jg==",
"dev": true,
"license": "ISC",
"dependencies": {
"internmap": "1 - 2"
},
"engines": {
"node": ">=12"
}
},
"node_modules/d3-axis": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/d3-axis/-/d3-axis-3.0.0.tgz",
"integrity": "sha512-IH5tgjV4jE/GhHkRV0HiVYPDtvfjHQlQfJHs0usq7M30XcSBvOotpmH1IgkcXsO/5gEQZD43B//fc7SRT5S+xw==",
"dev": true,
"license": "ISC",
"engines": {
"node": ">=12"
}
},
"node_modules/d3-brush": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/d3-brush/-/d3-brush-3.0.0.tgz",
"integrity": "sha512-ALnjWlVYkXsVIGlOsuWH1+3udkYFI48Ljihfnh8FZPF2QS9o+PzGLBslO0PjzVoHLZ2KCVgAM8NVkXPJB2aNnQ==",
"dev": true,
"license": "ISC",
"dependencies": {
"d3-dispatch": "1 - 3",
"d3-drag": "2 - 3",
"d3-interpolate": "1 - 3",
"d3-selection": "3",
"d3-transition": "3"
},
"engines": {
"node": ">=12"
}
},
"node_modules/d3-chord": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-chord/-/d3-chord-3.0.1.tgz",
"integrity": "sha512-VE5S6TNa+j8msksl7HwjxMHDM2yNK3XCkusIlpX5kwauBfXuyLAtNg9jCp/iHH61tgI4sb6R/EIMWCqEIdjT/g==",
"dev": true,
"license": "ISC",
"dependencies": {
"d3-path": "1 - 3"
},
"engines": {
"node": ">=12"
}
},
"node_modules/d3-color": {
"version": "3.1.0",
"resolved": "https://registry.npmjs.org/d3-color/-/d3-color-3.1.0.tgz",
"integrity": "sha512-zg/chbXyeBtMQ1LbD/WSoW2DpC3I0mpmPdW+ynRTj/x2DAWYrIY7qeZIHidozwV24m4iavr15lNwIwLxRmOxhA==",
"dev": true,
"license": "ISC",
"engines": {
"node": ">=12"
}
},
"node_modules/d3-contour": {
"version": "4.0.2",
"resolved": "https://registry.npmjs.org/d3-contour/-/d3-contour-4.0.2.tgz",
"integrity": "sha512-4EzFTRIikzs47RGmdxbeUvLWtGedDUNkTcmzoeyg4sP/dvCexO47AaQL7VKy/gul85TOxw+IBgA8US2xwbToNA==",
"dev": true,
"license": "ISC",
"dependencies": {
"d3-array": "^3.2.0"
},
"engines": {
"node": ">=12"
}
},
"node_modules/d3-delaunay": {
"version": "6.0.4",
"resolved": "https://registry.npmjs.org/d3-delaunay/-/d3-delaunay-6.0.4.tgz",
"integrity": "sha512-mdjtIZ1XLAM8bm/hx3WwjfHt6Sggek7qH043O8KEjDXN40xi3vx/6pYSVTwLjEgiXQTbvaouWKynLBiUZ6SK6A==",
"dev": true,
"license": "ISC",
"dependencies": {
"delaunator": "5"
},
"engines": {
"node": ">=12"
}
},
"node_modules/d3-dispatch": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-dispatch/-/d3-dispatch-3.0.1.tgz",
"integrity": "sha512-rzUyPU/S7rwUflMyLc1ETDeBj0NRuHKKAcvukozwhshr6g6c5d8zh4c2gQjY2bZ0dXeGLWc1PF174P2tVvKhfg==",
"dev": true,
"license": "ISC",
"engines": {
"node": ">=12"
}
},
"node_modules/d3-drag": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/d3-drag/-/d3-drag-3.0.0.tgz",
"integrity": "sha512-pWbUJLdETVA8lQNJecMxoXfH6x+mO2UQo8rSmZ+QqxcbyA3hfeprFgIT//HW2nlHChWeIIMwS2Fq+gEARkhTkg==",
"dev": true,
"license": "ISC",
"dependencies": {
"d3-dispatch": "1 - 3",
"d3-selection": "3"
},
"engines": {
"node": ">=12"
}
},
"node_modules/d3-dsv": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-dsv/-/d3-dsv-3.0.1.tgz",
"integrity": "sha512-UG6OvdI5afDIFP9w4G0mNq50dSOsXHJaRE8arAS5o9ApWnIElp8GZw1Dun8vP8OyHOZ/QJUKUJwxiiCCnUwm+Q==",
"dev": true,
"license": "ISC",
"dependencies": {
"commander": "7",
"iconv-lite": "0.6",
"rw": "1"
},
"bin": {
"csv2json": "bin/dsv2json.js",
"csv2tsv": "bin/dsv2dsv.js",
"dsv2dsv": "bin/dsv2dsv.js",
"dsv2json": "bin/dsv2json.js",
"json2csv": "bin/json2dsv.js",
"json2dsv": "bin/json2dsv.js",
"json2tsv": "bin/json2dsv.js",
"tsv2csv": "bin/dsv2dsv.js",
"tsv2json": "bin/dsv2json.js"
},
"engines": {
"node": ">=12"
}
},
"node_modules/d3-ease": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-ease/-/d3-ease-3.0.1.tgz",
"integrity": "sha512-wR/XK3D3XcLIZwpbvQwQ5fK+8Ykds1ip7A2Txe0yxncXSdq1L9skcG7blcedkOX+ZcgxGAmLX1FrRGbADwzi0w==",
"dev": true,
"license": "BSD-3-Clause",
"engines": {
"node": ">=12"
}
},
"node_modules/d3-fetch": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-fetch/-/d3-fetch-3.0.1.tgz",
"integrity": "sha512-kpkQIM20n3oLVBKGg6oHrUchHM3xODkTzjMoj7aWQFq5QEM+R6E4WkzT5+tojDY7yjez8KgCBRoj4aEr99Fdqw==",
"dev": true,
"license": "ISC",
"dependencies": {
"d3-dsv": "1 - 3"
},
"engines": {
"node": ">=12"
}
},
"node_modules/d3-force": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/d3-force/-/d3-force-3.0.0.tgz",
"integrity": "sha512-zxV/SsA+U4yte8051P4ECydjD/S+qeYtnaIyAs9tgHCqfguma/aAQDjo85A9Z6EKhBirHRJHXIgJUlffT4wdLg==",
"dev": true,
"license": "ISC",
"dependencies": {
"d3-dispatch": "1 - 3",
"d3-quadtree": "1 - 3",
"d3-timer": "1 - 3"
},
"engines": {
"node": ">=12"
}
},
"node_modules/d3-format": {
"version": "3.1.2",
"resolved": "https://registry.npmjs.org/d3-format/-/d3-format-3.1.2.tgz",
"integrity": "sha512-AJDdYOdnyRDV5b6ArilzCPPwc1ejkHcoyFarqlPqT7zRYjhavcT3uSrqcMvsgh2CgoPbK3RCwyHaVyxYcP2Arg==",
"dev": true,
"license": "ISC",
"engines": {
"node": ">=12"
}
},
"node_modules/d3-geo": {
"version": "3.1.1",
"resolved": "https://registry.npmjs.org/d3-geo/-/d3-geo-3.1.1.tgz",
"integrity": "sha512-637ln3gXKXOwhalDzinUgY83KzNWZRKbYubaG+fGVuc/dxO64RRljtCTnf5ecMyE1RIdtqpkVcq0IbtU2S8j2Q==",
"dev": true,
"license": "ISC",
"dependencies": {
"d3-array": "2.5.0 - 3"
},
"engines": {
"node": ">=12"
}
},
"node_modules/d3-hierarchy": {
"version": "3.1.2",
"resolved": "https://registry.npmjs.org/d3-hierarchy/-/d3-hierarchy-3.1.2.tgz",
"integrity": "sha512-FX/9frcub54beBdugHjDCdikxThEqjnR93Qt7PvQTOHxyiNCAlvMrHhclk3cD5VeAaq9fxmfRp+CnWw9rEMBuA==",
"dev": true,
"license": "ISC",
"engines": {
"node": ">=12"
}
},
"node_modules/d3-interpolate": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-interpolate/-/d3-interpolate-3.0.1.tgz",
"integrity": "sha512-3bYs1rOD33uo8aqJfKP3JWPAibgw8Zm2+L9vBKEHJ2Rg+viTR7o5Mmv5mZcieN+FRYaAOWX5SJATX6k1PWz72g==",
"dev": true,
"license": "ISC",
"dependencies": {
"d3-color": "1 - 3"
},
"engines": {
"node": ">=12"
}
},
"node_modules/d3-path": {
"version": "3.1.0",
"resolved": "https://registry.npmjs.org/d3-path/-/d3-path-3.1.0.tgz",
"integrity": "sha512-p3KP5HCf/bvjBSSKuXid6Zqijx7wIfNW+J/maPs+iwR35at5JCbLUT0LzF1cnjbCHWhqzQTIN2Jpe8pRebIEFQ==",
"dev": true,
"license": "ISC",
"engines": {
"node": ">=12"
}
},
"node_modules/d3-polygon": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-polygon/-/d3-polygon-3.0.1.tgz",
"integrity": "sha512-3vbA7vXYwfe1SYhED++fPUQlWSYTTGmFmQiany/gdbiWgU/iEyQzyymwL9SkJjFFuCS4902BSzewVGsHHmHtXg==",
"dev": true,
"license": "ISC",
"engines": {
"node": ">=12"
}
},
"node_modules/d3-quadtree": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-quadtree/-/d3-quadtree-3.0.1.tgz",
"integrity": "sha512-04xDrxQTDTCFwP5H6hRhsRcb9xxv2RzkcsygFzmkSIOJy3PeRJP7sNk3VRIbKXcog561P9oU0/rVH6vDROAgUw==",
"dev": true,
"license": "ISC",
"engines": {
"node": ">=12"
}
},
"node_modules/d3-random": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-random/-/d3-random-3.0.1.tgz",
"integrity": "sha512-FXMe9GfxTxqd5D6jFsQ+DJ8BJS4E/fT5mqqdjovykEB2oFbTMDVdg1MGFxfQW+FBOGoB++k8swBrgwSHT1cUXQ==",
"dev": true,
"license": "ISC",
"engines": {
"node": ">=12"
}
},
"node_modules/d3-scale": {
"version": "4.0.2",
"resolved": "https://registry.npmjs.org/d3-scale/-/d3-scale-4.0.2.tgz",
"integrity": "sha512-GZW464g1SH7ag3Y7hXjf8RoUuAFIqklOAq3MRl4OaWabTFJY9PN/E1YklhXLh+OQ3fM9yS2nOkCoS+WLZ6kvxQ==",
"dev": true,
"license": "ISC",
"dependencies": {
"d3-array": "2.10.0 - 3",
"d3-format": "1 - 3",
"d3-interpolate": "1.2.0 - 3",
"d3-time": "2.1.1 - 3",
"d3-time-format": "2 - 4"
},
"engines": {
"node": ">=12"
}
},
"node_modules/d3-scale-chromatic": {
"version": "3.1.0",
"resolved": "https://registry.npmjs.org/d3-scale-chromatic/-/d3-scale-chromatic-3.1.0.tgz",
"integrity": "sha512-A3s5PWiZ9YCXFye1o246KoscMWqf8BsD9eRiJ3He7C9OBaxKhAd5TFCdEx/7VbKtxxTsu//1mMJFrEt572cEyQ==",
"dev": true,
"license": "ISC",
"dependencies": {
"d3-color": "1 - 3",
"d3-interpolate": "1 - 3"
},
"engines": {
"node": ">=12"
}
},
"node_modules/d3-selection": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/d3-selection/-/d3-selection-3.0.0.tgz",
"integrity": "sha512-fmTRWbNMmsmWq6xJV8D19U/gw/bwrHfNXxrIN+HfZgnzqTHp9jOmKMhsTUjXOJnZOdZY9Q28y4yebKzqDKlxlQ==",
"dev": true,
"license": "ISC",
"peer": true,
"engines": {
"node": ">=12"
}
},
"node_modules/d3-shape": {
"version": "3.2.0",
"resolved": "https://registry.npmjs.org/d3-shape/-/d3-shape-3.2.0.tgz",
"integrity": "sha512-SaLBuwGm3MOViRq2ABk3eLoxwZELpH6zhl3FbAoJ7Vm1gofKx6El1Ib5z23NUEhF9AsGl7y+dzLe5Cw2AArGTA==",
"dev": true,
"license": "ISC",
"dependencies": {
"d3-path": "^3.1.0"
},
"engines": {
"node": ">=12"
}
},
"node_modules/d3-time": {
"version": "3.1.0",
"resolved": "https://registry.npmjs.org/d3-time/-/d3-time-3.1.0.tgz",
"integrity": "sha512-VqKjzBLejbSMT4IgbmVgDjpkYrNWUYJnbCGo874u7MMKIWsILRX+OpX/gTk8MqjpT1A/c6HY2dCA77ZN0lkQ2Q==",
"dev": true,
"license": "ISC",
"dependencies": {
"d3-array": "2 - 3"
},
"engines": {
"node": ">=12"
}
},
"node_modules/d3-time-format": {
"version": "4.1.0",
"resolved": "https://registry.npmjs.org/d3-time-format/-/d3-time-format-4.1.0.tgz",
"integrity": "sha512-dJxPBlzC7NugB2PDLwo9Q8JiTR3M3e4/XANkreKSUxF8vvXKqm1Yfq4Q5dl8budlunRVlUUaDUgFt7eA8D6NLg==",
"dev": true,
"license": "ISC",
"dependencies": {
"d3-time": "1 - 3"
},
"engines": {
"node": ">=12"
}
},
"node_modules/d3-timer": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-timer/-/d3-timer-3.0.1.tgz",
"integrity": "sha512-ndfJ/JxxMd3nw31uyKoY2naivF+r29V+Lc0svZxe1JvvIRmi8hUsrMvdOwgS1o6uBHmiz91geQ0ylPP0aj1VUA==",
"dev": true,
"license": "ISC",
"engines": {
"node": ">=12"
}
},
"node_modules/d3-transition": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-transition/-/d3-transition-3.0.1.tgz",
"integrity": "sha512-ApKvfjsSR6tg06xrL434C0WydLr7JewBB3V+/39RMHsaXTOG0zmt/OAXeng5M5LBm0ojmxJrpomQVZ1aPvBL4w==",
"dev": true,
"license": "ISC",
"dependencies": {
"d3-color": "1 - 3",
"d3-dispatch": "1 - 3",
"d3-ease": "1 - 3",
"d3-interpolate": "1 - 3",
"d3-timer": "1 - 3"
},
"engines": {
"node": ">=12"
},
"peerDependencies": {
"d3-selection": "2 - 3"
}
},
"node_modules/d3-zoom": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/d3-zoom/-/d3-zoom-3.0.0.tgz",
"integrity": "sha512-b8AmV3kfQaqWAuacbPuNbL6vahnOJflOhexLzMMNLga62+/nh0JzvJ0aO/5a5MVgUFGS7Hu1P9P03o3fJkDCyw==",
"dev": true,
"license": "ISC",
"dependencies": {
"d3-dispatch": "1 - 3",
"d3-drag": "2 - 3",
"d3-interpolate": "1 - 3",
"d3-selection": "2 - 3",
"d3-transition": "2 - 3"
},
"engines": {
"node": ">=12"
}
},
"node_modules/delaunator": {
"version": "5.0.1",
"resolved": "https://registry.npmjs.org/delaunator/-/delaunator-5.0.1.tgz",
"integrity": "sha512-8nvh+XBe96aCESrGOqMp/84b13H9cdKbG5P2ejQCh4d4sK9RL4371qou9drQjMhvnPmhWl5hnmqbEE0fXr9Xnw==",
"dev": true,
"license": "ISC",
"dependencies": {
"robust-predicates": "^3.0.2"
}
},
"node_modules/fs.realpath": {
"version": "1.0.0",
@@ -92,6 +539,19 @@
"url": "https://github.com/sponsors/isaacs"
}
},
"node_modules/iconv-lite": {
"version": "0.6.3",
"resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.6.3.tgz",
"integrity": "sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw==",
"dev": true,
"license": "MIT",
"dependencies": {
"safer-buffer": ">= 2.1.2 < 3.0.0"
},
"engines": {
"node": ">=0.10.0"
}
},
"node_modules/inflight": {
"version": "1.0.6",
"resolved": "https://registry.npmjs.org/inflight/-/inflight-1.0.6.tgz",
@@ -109,6 +569,16 @@
"integrity": "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ==",
"dev": true
},
"node_modules/internmap": {
"version": "2.0.3",
"resolved": "https://registry.npmjs.org/internmap/-/internmap-2.0.3.tgz",
"integrity": "sha512-5Hh7Y1wQbvY5ooGgPbDaL5iYLAPzMTUrjMulskHLH6wnv/A+1q5rgEaiuqEjB+oxGXIVZs1FF+R/KPN3ZSQYYg==",
"dev": true,
"license": "ISC",
"engines": {
"node": ">=12"
}
},
"node_modules/isarray": {
"version": "0.0.1",
"resolved": "https://registry.npmjs.org/isarray/-/isarray-0.0.1.tgz",
@@ -203,12 +673,33 @@
"string_decoder": "~0.10.x"
}
},
"node_modules/robust-predicates": {
"version": "3.0.2",
"resolved": "https://registry.npmjs.org/robust-predicates/-/robust-predicates-3.0.2.tgz",
"integrity": "sha512-IXgzBWvWQwE6PrDI05OvmXUIruQTcoMDzRsOd5CDvHCVLcLHMTSYvOK5Cm46kWqlV3yAbuSpBZdJ5oP5OUoStg==",
"dev": true,
"license": "Unlicense"
},
"node_modules/rw": {
"version": "1.3.3",
"resolved": "https://registry.npmjs.org/rw/-/rw-1.3.3.tgz",
"integrity": "sha512-PdhdWy89SiZogBLaw42zdeqtRJ//zFd2PgQavcICDUgJT5oW10QCRKbJ6bg4r0/UY2M6BWd5tkxuGFRvCkgfHQ==",
"dev": true,
"license": "BSD-3-Clause"
},
"node_modules/safe-buffer": {
"version": "5.1.2",
"resolved": "https://registry.npmjs.org/safe-buffer/-/safe-buffer-5.1.2.tgz",
"integrity": "sha512-Gd2UZBJDkXlY7GbJxfsE8/nvKkUEU1G38c1siN6QP6a9PT9MmHB8GnpscSmMJSoF8LOIrt8ud/wPtojys4G6+g==",
"dev": true
},
"node_modules/safer-buffer": {
"version": "2.1.2",
"resolved": "https://registry.npmjs.org/safer-buffer/-/safer-buffer-2.1.2.tgz",
"integrity": "sha512-YZo3K82SD7Riyi0E1EQPojLz7kpepnSQI9IyPbHHg1XXXevb5dJI7tpyN2ADxGcQbHG7vcyRHk0cbwqcQriUtg==",
"dev": true,
"license": "MIT"
},
"node_modules/string_decoder": {
"version": "0.10.31",
"resolved": "https://registry.npmjs.org/string_decoder/-/string_decoder-0.10.31.tgz",
@@ -294,6 +785,12 @@
"concat-map": "0.0.1"
}
},
"commander": {
"version": "7.2.0",
"resolved": "https://registry.npmjs.org/commander/-/commander-7.2.0.tgz",
"integrity": "sha512-QrWXB+ZQSVPmIWIhtEO9H+gwHaMGYiF5ChvoJ+K9ZGHG/sVsa6yiesAD1GC/x46sET00Xlwo1u49RVVVzvcSkw==",
"dev": true
},
"concat-map": {
"version": "0.0.1",
"resolved": "https://registry.npmjs.org/concat-map/-/concat-map-0.0.1.tgz",
@@ -321,11 +818,309 @@
"dev": true
},
"d3": {
"version": "3.5.17",
"resolved": "https://registry.npmjs.org/d3/-/d3-3.5.17.tgz",
"integrity": "sha512-yFk/2idb8OHPKkbAL8QaOaqENNoMhIaSHZerk3oQsECwkObkCpJyjYwCe+OHiq6UEdhe1m8ZGARRRO3ljFjlKg==",
"version": "7.9.0",
"resolved": "https://registry.npmjs.org/d3/-/d3-7.9.0.tgz",
"integrity": "sha512-e1U46jVP+w7Iut8Jt8ri1YsPOvFpg46k+K8TpCb0P+zjCkjkPnV7WzfDJzMHy1LnA+wj5pLT1wjO901gLXeEhA==",
"dev": true,
"requires": {
"d3-array": "3",
"d3-axis": "3",
"d3-brush": "3",
"d3-chord": "3",
"d3-color": "3",
"d3-contour": "4",
"d3-delaunay": "6",
"d3-dispatch": "3",
"d3-drag": "3",
"d3-dsv": "3",
"d3-ease": "3",
"d3-fetch": "3",
"d3-force": "3",
"d3-format": "3",
"d3-geo": "3",
"d3-hierarchy": "3",
"d3-interpolate": "3",
"d3-path": "3",
"d3-polygon": "3",
"d3-quadtree": "3",
"d3-random": "3",
"d3-scale": "4",
"d3-scale-chromatic": "3",
"d3-selection": "3",
"d3-shape": "3",
"d3-time": "3",
"d3-time-format": "4",
"d3-timer": "3",
"d3-transition": "3",
"d3-zoom": "3"
}
},
"d3-array": {
"version": "3.2.4",
"resolved": "https://registry.npmjs.org/d3-array/-/d3-array-3.2.4.tgz",
"integrity": "sha512-tdQAmyA18i4J7wprpYq8ClcxZy3SC31QMeByyCFyRt7BVHdREQZ5lpzoe5mFEYZUWe+oq8HBvk9JjpibyEV4Jg==",
"dev": true,
"requires": {
"internmap": "1 - 2"
}
},
"d3-axis": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/d3-axis/-/d3-axis-3.0.0.tgz",
"integrity": "sha512-IH5tgjV4jE/GhHkRV0HiVYPDtvfjHQlQfJHs0usq7M30XcSBvOotpmH1IgkcXsO/5gEQZD43B//fc7SRT5S+xw==",
"dev": true
},
"d3-brush": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/d3-brush/-/d3-brush-3.0.0.tgz",
"integrity": "sha512-ALnjWlVYkXsVIGlOsuWH1+3udkYFI48Ljihfnh8FZPF2QS9o+PzGLBslO0PjzVoHLZ2KCVgAM8NVkXPJB2aNnQ==",
"dev": true,
"requires": {
"d3-dispatch": "1 - 3",
"d3-drag": "2 - 3",
"d3-interpolate": "1 - 3",
"d3-selection": "3",
"d3-transition": "3"
}
},
"d3-chord": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-chord/-/d3-chord-3.0.1.tgz",
"integrity": "sha512-VE5S6TNa+j8msksl7HwjxMHDM2yNK3XCkusIlpX5kwauBfXuyLAtNg9jCp/iHH61tgI4sb6R/EIMWCqEIdjT/g==",
"dev": true,
"requires": {
"d3-path": "1 - 3"
}
},
"d3-color": {
"version": "3.1.0",
"resolved": "https://registry.npmjs.org/d3-color/-/d3-color-3.1.0.tgz",
"integrity": "sha512-zg/chbXyeBtMQ1LbD/WSoW2DpC3I0mpmPdW+ynRTj/x2DAWYrIY7qeZIHidozwV24m4iavr15lNwIwLxRmOxhA==",
"dev": true
},
"d3-contour": {
"version": "4.0.2",
"resolved": "https://registry.npmjs.org/d3-contour/-/d3-contour-4.0.2.tgz",
"integrity": "sha512-4EzFTRIikzs47RGmdxbeUvLWtGedDUNkTcmzoeyg4sP/dvCexO47AaQL7VKy/gul85TOxw+IBgA8US2xwbToNA==",
"dev": true,
"requires": {
"d3-array": "^3.2.0"
}
},
"d3-delaunay": {
"version": "6.0.4",
"resolved": "https://registry.npmjs.org/d3-delaunay/-/d3-delaunay-6.0.4.tgz",
"integrity": "sha512-mdjtIZ1XLAM8bm/hx3WwjfHt6Sggek7qH043O8KEjDXN40xi3vx/6pYSVTwLjEgiXQTbvaouWKynLBiUZ6SK6A==",
"dev": true,
"requires": {
"delaunator": "5"
}
},
"d3-dispatch": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-dispatch/-/d3-dispatch-3.0.1.tgz",
"integrity": "sha512-rzUyPU/S7rwUflMyLc1ETDeBj0NRuHKKAcvukozwhshr6g6c5d8zh4c2gQjY2bZ0dXeGLWc1PF174P2tVvKhfg==",
"dev": true
},
"d3-drag": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/d3-drag/-/d3-drag-3.0.0.tgz",
"integrity": "sha512-pWbUJLdETVA8lQNJecMxoXfH6x+mO2UQo8rSmZ+QqxcbyA3hfeprFgIT//HW2nlHChWeIIMwS2Fq+gEARkhTkg==",
"dev": true,
"requires": {
"d3-dispatch": "1 - 3",
"d3-selection": "3"
}
},
"d3-dsv": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-dsv/-/d3-dsv-3.0.1.tgz",
"integrity": "sha512-UG6OvdI5afDIFP9w4G0mNq50dSOsXHJaRE8arAS5o9ApWnIElp8GZw1Dun8vP8OyHOZ/QJUKUJwxiiCCnUwm+Q==",
"dev": true,
"requires": {
"commander": "7",
"iconv-lite": "0.6",
"rw": "1"
}
},
"d3-ease": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-ease/-/d3-ease-3.0.1.tgz",
"integrity": "sha512-wR/XK3D3XcLIZwpbvQwQ5fK+8Ykds1ip7A2Txe0yxncXSdq1L9skcG7blcedkOX+ZcgxGAmLX1FrRGbADwzi0w==",
"dev": true
},
"d3-fetch": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-fetch/-/d3-fetch-3.0.1.tgz",
"integrity": "sha512-kpkQIM20n3oLVBKGg6oHrUchHM3xODkTzjMoj7aWQFq5QEM+R6E4WkzT5+tojDY7yjez8KgCBRoj4aEr99Fdqw==",
"dev": true,
"requires": {
"d3-dsv": "1 - 3"
}
},
"d3-force": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/d3-force/-/d3-force-3.0.0.tgz",
"integrity": "sha512-zxV/SsA+U4yte8051P4ECydjD/S+qeYtnaIyAs9tgHCqfguma/aAQDjo85A9Z6EKhBirHRJHXIgJUlffT4wdLg==",
"dev": true,
"requires": {
"d3-dispatch": "1 - 3",
"d3-quadtree": "1 - 3",
"d3-timer": "1 - 3"
}
},
"d3-format": {
"version": "3.1.2",
"resolved": "https://registry.npmjs.org/d3-format/-/d3-format-3.1.2.tgz",
"integrity": "sha512-AJDdYOdnyRDV5b6ArilzCPPwc1ejkHcoyFarqlPqT7zRYjhavcT3uSrqcMvsgh2CgoPbK3RCwyHaVyxYcP2Arg==",
"dev": true
},
"d3-geo": {
"version": "3.1.1",
"resolved": "https://registry.npmjs.org/d3-geo/-/d3-geo-3.1.1.tgz",
"integrity": "sha512-637ln3gXKXOwhalDzinUgY83KzNWZRKbYubaG+fGVuc/dxO64RRljtCTnf5ecMyE1RIdtqpkVcq0IbtU2S8j2Q==",
"dev": true,
"requires": {
"d3-array": "2.5.0 - 3"
}
},
"d3-hierarchy": {
"version": "3.1.2",
"resolved": "https://registry.npmjs.org/d3-hierarchy/-/d3-hierarchy-3.1.2.tgz",
"integrity": "sha512-FX/9frcub54beBdugHjDCdikxThEqjnR93Qt7PvQTOHxyiNCAlvMrHhclk3cD5VeAaq9fxmfRp+CnWw9rEMBuA==",
"dev": true
},
"d3-interpolate": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-interpolate/-/d3-interpolate-3.0.1.tgz",
"integrity": "sha512-3bYs1rOD33uo8aqJfKP3JWPAibgw8Zm2+L9vBKEHJ2Rg+viTR7o5Mmv5mZcieN+FRYaAOWX5SJATX6k1PWz72g==",
"dev": true,
"requires": {
"d3-color": "1 - 3"
}
},
"d3-path": {
"version": "3.1.0",
"resolved": "https://registry.npmjs.org/d3-path/-/d3-path-3.1.0.tgz",
"integrity": "sha512-p3KP5HCf/bvjBSSKuXid6Zqijx7wIfNW+J/maPs+iwR35at5JCbLUT0LzF1cnjbCHWhqzQTIN2Jpe8pRebIEFQ==",
"dev": true
},
"d3-polygon": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-polygon/-/d3-polygon-3.0.1.tgz",
"integrity": "sha512-3vbA7vXYwfe1SYhED++fPUQlWSYTTGmFmQiany/gdbiWgU/iEyQzyymwL9SkJjFFuCS4902BSzewVGsHHmHtXg==",
"dev": true
},
"d3-quadtree": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-quadtree/-/d3-quadtree-3.0.1.tgz",
"integrity": "sha512-04xDrxQTDTCFwP5H6hRhsRcb9xxv2RzkcsygFzmkSIOJy3PeRJP7sNk3VRIbKXcog561P9oU0/rVH6vDROAgUw==",
"dev": true
},
"d3-random": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-random/-/d3-random-3.0.1.tgz",
"integrity": "sha512-FXMe9GfxTxqd5D6jFsQ+DJ8BJS4E/fT5mqqdjovykEB2oFbTMDVdg1MGFxfQW+FBOGoB++k8swBrgwSHT1cUXQ==",
"dev": true
},
"d3-scale": {
"version": "4.0.2",
"resolved": "https://registry.npmjs.org/d3-scale/-/d3-scale-4.0.2.tgz",
"integrity": "sha512-GZW464g1SH7ag3Y7hXjf8RoUuAFIqklOAq3MRl4OaWabTFJY9PN/E1YklhXLh+OQ3fM9yS2nOkCoS+WLZ6kvxQ==",
"dev": true,
"requires": {
"d3-array": "2.10.0 - 3",
"d3-format": "1 - 3",
"d3-interpolate": "1.2.0 - 3",
"d3-time": "2.1.1 - 3",
"d3-time-format": "2 - 4"
}
},
"d3-scale-chromatic": {
"version": "3.1.0",
"resolved": "https://registry.npmjs.org/d3-scale-chromatic/-/d3-scale-chromatic-3.1.0.tgz",
"integrity": "sha512-A3s5PWiZ9YCXFye1o246KoscMWqf8BsD9eRiJ3He7C9OBaxKhAd5TFCdEx/7VbKtxxTsu//1mMJFrEt572cEyQ==",
"dev": true,
"requires": {
"d3-color": "1 - 3",
"d3-interpolate": "1 - 3"
}
},
"d3-selection": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/d3-selection/-/d3-selection-3.0.0.tgz",
"integrity": "sha512-fmTRWbNMmsmWq6xJV8D19U/gw/bwrHfNXxrIN+HfZgnzqTHp9jOmKMhsTUjXOJnZOdZY9Q28y4yebKzqDKlxlQ==",
"dev": true,
"peer": true
},
"d3-shape": {
"version": "3.2.0",
"resolved": "https://registry.npmjs.org/d3-shape/-/d3-shape-3.2.0.tgz",
"integrity": "sha512-SaLBuwGm3MOViRq2ABk3eLoxwZELpH6zhl3FbAoJ7Vm1gofKx6El1Ib5z23NUEhF9AsGl7y+dzLe5Cw2AArGTA==",
"dev": true,
"requires": {
"d3-path": "^3.1.0"
}
},
"d3-time": {
"version": "3.1.0",
"resolved": "https://registry.npmjs.org/d3-time/-/d3-time-3.1.0.tgz",
"integrity": "sha512-VqKjzBLejbSMT4IgbmVgDjpkYrNWUYJnbCGo874u7MMKIWsILRX+OpX/gTk8MqjpT1A/c6HY2dCA77ZN0lkQ2Q==",
"dev": true,
"requires": {
"d3-array": "2 - 3"
}
},
"d3-time-format": {
"version": "4.1.0",
"resolved": "https://registry.npmjs.org/d3-time-format/-/d3-time-format-4.1.0.tgz",
"integrity": "sha512-dJxPBlzC7NugB2PDLwo9Q8JiTR3M3e4/XANkreKSUxF8vvXKqm1Yfq4Q5dl8budlunRVlUUaDUgFt7eA8D6NLg==",
"dev": true,
"requires": {
"d3-time": "1 - 3"
}
},
"d3-timer": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-timer/-/d3-timer-3.0.1.tgz",
"integrity": "sha512-ndfJ/JxxMd3nw31uyKoY2naivF+r29V+Lc0svZxe1JvvIRmi8hUsrMvdOwgS1o6uBHmiz91geQ0ylPP0aj1VUA==",
"dev": true
},
"d3-transition": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/d3-transition/-/d3-transition-3.0.1.tgz",
"integrity": "sha512-ApKvfjsSR6tg06xrL434C0WydLr7JewBB3V+/39RMHsaXTOG0zmt/OAXeng5M5LBm0ojmxJrpomQVZ1aPvBL4w==",
"dev": true,
"requires": {
"d3-color": "1 - 3",
"d3-dispatch": "1 - 3",
"d3-ease": "1 - 3",
"d3-interpolate": "1 - 3",
"d3-timer": "1 - 3"
}
},
"d3-zoom": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/d3-zoom/-/d3-zoom-3.0.0.tgz",
"integrity": "sha512-b8AmV3kfQaqWAuacbPuNbL6vahnOJflOhexLzMMNLga62+/nh0JzvJ0aO/5a5MVgUFGS7Hu1P9P03o3fJkDCyw==",
"dev": true,
"requires": {
"d3-dispatch": "1 - 3",
"d3-drag": "2 - 3",
"d3-interpolate": "1 - 3",
"d3-selection": "2 - 3",
"d3-transition": "2 - 3"
}
},
"delaunator": {
"version": "5.0.1",
"resolved": "https://registry.npmjs.org/delaunator/-/delaunator-5.0.1.tgz",
"integrity": "sha512-8nvh+XBe96aCESrGOqMp/84b13H9cdKbG5P2ejQCh4d4sK9RL4371qou9drQjMhvnPmhWl5hnmqbEE0fXr9Xnw==",
"dev": true,
"requires": {
"robust-predicates": "^3.0.2"
}
},
"fs.realpath": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/fs.realpath/-/fs.realpath-1.0.0.tgz",
@@ -346,6 +1141,15 @@
"path-is-absolute": "^1.0.0"
}
},
"iconv-lite": {
"version": "0.6.3",
"resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.6.3.tgz",
"integrity": "sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw==",
"dev": true,
"requires": {
"safer-buffer": ">= 2.1.2 < 3.0.0"
}
},
"inflight": {
"version": "1.0.6",
"resolved": "https://registry.npmjs.org/inflight/-/inflight-1.0.6.tgz",
@@ -362,6 +1166,12 @@
"integrity": "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ==",
"dev": true
},
"internmap": {
"version": "2.0.3",
"resolved": "https://registry.npmjs.org/internmap/-/internmap-2.0.3.tgz",
"integrity": "sha512-5Hh7Y1wQbvY5ooGgPbDaL5iYLAPzMTUrjMulskHLH6wnv/A+1q5rgEaiuqEjB+oxGXIVZs1FF+R/KPN3ZSQYYg==",
"dev": true
},
"isarray": {
"version": "0.0.1",
"resolved": "https://registry.npmjs.org/isarray/-/isarray-0.0.1.tgz",
@@ -441,12 +1251,30 @@
"string_decoder": "~0.10.x"
}
},
"robust-predicates": {
"version": "3.0.2",
"resolved": "https://registry.npmjs.org/robust-predicates/-/robust-predicates-3.0.2.tgz",
"integrity": "sha512-IXgzBWvWQwE6PrDI05OvmXUIruQTcoMDzRsOd5CDvHCVLcLHMTSYvOK5Cm46kWqlV3yAbuSpBZdJ5oP5OUoStg==",
"dev": true
},
"rw": {
"version": "1.3.3",
"resolved": "https://registry.npmjs.org/rw/-/rw-1.3.3.tgz",
"integrity": "sha512-PdhdWy89SiZogBLaw42zdeqtRJ//zFd2PgQavcICDUgJT5oW10QCRKbJ6bg4r0/UY2M6BWd5tkxuGFRvCkgfHQ==",
"dev": true
},
"safe-buffer": {
"version": "5.1.2",
"resolved": "https://registry.npmjs.org/safe-buffer/-/safe-buffer-5.1.2.tgz",
"integrity": "sha512-Gd2UZBJDkXlY7GbJxfsE8/nvKkUEU1G38c1siN6QP6a9PT9MmHB8GnpscSmMJSoF8LOIrt8ud/wPtojys4G6+g==",
"dev": true
},
"safer-buffer": {
"version": "2.1.2",
"resolved": "https://registry.npmjs.org/safer-buffer/-/safer-buffer-2.1.2.tgz",
"integrity": "sha512-YZo3K82SD7Riyi0E1EQPojLz7kpepnSQI9IyPbHHg1XXXevb5dJI7tpyN2ADxGcQbHG7vcyRHk0cbwqcQriUtg==",
"dev": true
},
"string_decoder": {
"version": "0.10.31",
"resolved": "https://registry.npmjs.org/string_decoder/-/string_decoder-0.10.31.tgz",
+3 -3
View File
@@ -4,8 +4,8 @@
"description": "Advanced Reconnaissance Framework",
"main": "public/index.html",
"scripts": {
"postinstall": "copyfiles -f ./node_modules/d3/d3.min.js ./public/js/vendor/d3",
"start": "cd ./public; python -m SimpleHTTPServer 8000"
"postinstall": "copyfiles -f ./node_modules/d3/dist/d3.min.js ./public/js/",
"start": "cd ./public; python3 -m http.server 8000"
},
"repository": {
"type": "git",
@@ -19,6 +19,6 @@
"homepage": "https://github.com/lockfale/ARF#readme",
"devDependencies": {
"copyfiles": "^1.0.0",
"d3": "^3.5.16"
"d3": "^7.9.0"
}
}
+6126 -6760
View File
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
+177
View File
@@ -0,0 +1,177 @@
#!/usr/bin/env python3
"""
Dead link checker for arf.json.
Extracts all URLs, checks HTTP status, and reports dead/redirected/slow links.
"""
import json
import re
import sys
import time
import urllib.request
import urllib.error
import urllib.parse
from concurrent.futures import ThreadPoolExecutor, as_completed
from dataclasses import dataclass, field
from typing import Optional
import ssl
TIMEOUT = 30
MAX_WORKERS = 20
SLOW_THRESHOLD = 10 # seconds
# Skip these domains known to block bots or require auth
SKIP_DOMAINS = set()
# User agent to avoid some bot blocks
HEADERS = {
"User-Agent": "Mozilla/5.0 (compatible; OSINT-Framework-LinkChecker/1.0; +https://osintframework.com)"
}
@dataclass
class LinkResult:
url: str
status: Optional[int] = None
final_url: Optional[str] = None
elapsed: float = 0.0
error: Optional[str] = None
@property
def is_dead(self):
if self.error and "404" not in str(self.error):
return True
return self.status is not None and self.status >= 400
@property
def is_redirect(self):
return self.final_url and self.final_url != self.url
@property
def is_slow(self):
return self.elapsed >= SLOW_THRESHOLD
def check_url(url: str) -> LinkResult:
result = LinkResult(url=url)
start = time.time()
try:
# Build request with headers
req = urllib.request.Request(url, headers=HEADERS)
ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE
with urllib.request.urlopen(req, timeout=TIMEOUT, context=ctx) as resp:
result.status = resp.status
result.final_url = resp.url
except urllib.error.HTTPError as e:
result.status = e.code
result.error = str(e)
except urllib.error.URLError as e:
result.error = str(e.reason)
except Exception as e:
result.error = str(e)
finally:
result.elapsed = time.time() - start
return result
def extract_urls(json_path: str) -> list[str]:
with open(json_path) as f:
raw = f.read()
urls = re.findall(r'https?://[^\s"\'<>]+', raw)
# Clean trailing punctuation
cleaned = []
for u in urls:
u = u.rstrip(".,;:)'\"")
cleaned.append(u)
return sorted(set(cleaned))
def main():
json_path = "public/arf.json"
urls = extract_urls(json_path)
total = len(urls)
print(f"Checking {total} unique URLs (timeout={TIMEOUT}s, workers={MAX_WORKERS})...\n")
results = []
completed = 0
with ThreadPoolExecutor(max_workers=MAX_WORKERS) as executor:
future_to_url = {executor.submit(check_url, url): url for url in urls}
for future in as_completed(future_to_url):
result = future.result()
results.append(result)
completed += 1
if completed % 50 == 0:
print(f" Progress: {completed}/{total}", flush=True)
# Sort results by URL for consistent output
results.sort(key=lambda r: r.url)
dead = [r for r in results if r.is_dead]
redirected = [r for r in results if r.is_redirect and not r.is_dead]
slow = [r for r in results if r.is_slow and not r.is_dead]
ok = [r for r in results if not r.is_dead and not r.is_slow]
print("\n" + "=" * 70)
print(f"LINK AUDIT REPORT")
print("=" * 70)
print(f"Total URLs checked : {total}")
print(f"OK : {len(ok)}")
print(f"Dead (errors/404+) : {len(dead)}")
print(f"Redirected : {len(redirected)}")
print(f"Slow (>{SLOW_THRESHOLD}s) : {len(slow)}")
print()
if dead:
print("=" * 70)
print(f"DEAD LINKS ({len(dead)})")
print("=" * 70)
for r in dead:
status_str = f"HTTP {r.status}" if r.status else f"ERROR: {r.error}"
print(f" [{status_str}] {r.url}")
print()
if redirected:
print("=" * 70)
print(f"REDIRECTED LINKS ({len(redirected)})")
print("=" * 70)
for r in redirected:
print(f" [HTTP {r.status}] {r.url}")
print(f" -> {r.final_url}")
print()
if slow:
print("=" * 70)
print(f"SLOW LINKS (>{SLOW_THRESHOLD}s) ({len(slow)})")
print("=" * 70)
for r in slow:
print(f" [{r.elapsed:.1f}s] {r.url}")
print()
# Write JSON report
report = {
"summary": {
"total": total,
"ok": len(ok),
"dead": len(dead),
"redirected": len(redirected),
"slow": len(slow),
},
"dead": [{"url": r.url, "status": r.status, "error": r.error} for r in dead],
"redirected": [{"url": r.url, "status": r.status, "final_url": r.final_url} for r in redirected],
"slow": [{"url": r.url, "elapsed": round(r.elapsed, 2)} for r in slow],
}
report_path = "tools/link_audit_report.json"
with open(report_path, "w") as f:
json.dump(report, f, indent=2)
print(f"Full report written to: {report_path}")
return len(dead)
if __name__ == "__main__":
sys.exit(main())
+89
View File
@@ -0,0 +1,89 @@
#!/usr/bin/env python3
"""
Remove confirmed dead links from arf.json.
Targets: DNS failures, connection refused, HTTP 404.
Leaves alone: .onion, 403 (bot-block), 5xx (transient), timeouts.
"""
import json
import sys
REPORT_PATH = "tools/link_audit_report.json"
ARF_PATH = "public/arf.json"
def get_dead_urls(report_path: str) -> set:
with open(report_path) as f:
report = json.load(f)
dead_urls = set()
for d in report["dead"]:
url = d.get("url", "")
err = d.get("error") or ""
status = d.get("status")
# Skip .onion (Tor hidden services - expected failure from clearnet)
if ".onion" in url:
continue
# DNS failure = truly dead
if "nodename nor servname" in err:
dead_urls.add(url)
# Connection refused = truly dead
elif "Connection refused" in err:
dead_urls.add(url)
# 404 = page gone
elif status == 404:
dead_urls.add(url)
return dead_urls
def remove_nodes(tree, dead_urls: set) -> tuple:
"""Recursively remove leaf nodes whose URL is dead. Returns (cleaned_tree, removed_count)."""
removed = 0
if not isinstance(tree, dict):
return tree, 0
children = tree.get("children", [])
if not children:
# Leaf node - check URL
url = tree.get("url", "")
if url in dead_urls:
return None, 1
return tree, 0
# Non-leaf: recurse into children
new_children = []
for child in children:
cleaned, n = remove_nodes(child, dead_urls)
removed += n
if cleaned is not None:
new_children.append(cleaned)
tree = dict(tree)
tree["children"] = new_children
return tree, removed
def main():
dead_urls = get_dead_urls(REPORT_PATH)
print(f"Confirmed dead URLs to remove: {len(dead_urls)}")
with open(ARF_PATH) as f:
data = json.load(f)
cleaned, removed = remove_nodes(data, dead_urls)
print(f"Removed {removed} nodes from arf.json")
with open(ARF_PATH, "w") as f:
json.dump(cleaned, f, indent=2, separators=(",", ": "))
f.write("\n")
print(f"Wrote cleaned data to {ARF_PATH}")
return 0
if __name__ == "__main__":
sys.exit(main())