From f444425e358979c745da31f58a72948ef003c96a Mon Sep 17 00:00:00 2001 From: "Carlos (Almeira)" Date: Sun, 21 Jun 2026 14:13:02 -0500 Subject: [PATCH] feat: Add similarity checking and support for April, May, June in Multivision scraper --- package-lock.json | 403 ++++++++++++++++++++++++++++++++++++++++-- package.json | 7 +- scrape-multivision.js | 72 +++++--- 3 files changed, 440 insertions(+), 42 deletions(-) diff --git a/package-lock.json b/package-lock.json index f53ab95..8148803 100644 --- a/package-lock.json +++ b/package-lock.json @@ -22,15 +22,18 @@ "@types/dompurify": "^3.0.5", "@types/video.js": "^7.3.58", "appwrite": "^22.4.1", - "axios": "^1.13.6", + "axios": "^1.18.0", + "cheerio": "^1.2.0", "clsx": "^2.1.1", "dompurify": "^3.3.3", + "dotenv": "^17.4.2", "isomorphic-dompurify": "^2.20.0", "lucide-react": "^0.577.0", "next": "16.1.6", - "node-appwrite": "^22.0.0", + "node-appwrite": "^22.1.3", "react": "19.2.3", "react-dom": "19.2.3", + "string-similarity": "^4.0.4", "tailwind-merge": "^3.5.0", "video.js": "^8.23.7", "zod": "^4.3.6", @@ -3408,14 +3411,40 @@ } }, "node_modules/axios": { - "version": "1.13.6", - "resolved": "https://registry.npmjs.org/axios/-/axios-1.13.6.tgz", - "integrity": "sha512-ChTCHMouEe2kn713WHbQGcuYrr6fXTBiu460OTwWrWob16g1bXn4vtz07Ope7ewMozJAnEquLk5lWQWtBig9DQ==", + "version": "1.18.0", + "resolved": "https://registry.npmjs.org/axios/-/axios-1.18.0.tgz", + "integrity": "sha512-E32NzpYKp++W7XRe52rHiXV2ehxmh3wbdgO7MHeFM+vqxLBYHzt0ElkiImtOBxtOmyp0yoC8C6uESVV84Y2/hw==", "license": "MIT", "dependencies": { - "follow-redirects": "^1.15.11", + "follow-redirects": "^1.16.0", "form-data": "^4.0.5", - "proxy-from-env": "^1.1.0" + "https-proxy-agent": "^5.0.1", + "proxy-from-env": "^2.1.0" + } + }, + "node_modules/axios/node_modules/agent-base": { + "version": "6.0.2", + "resolved": "https://registry.npmjs.org/agent-base/-/agent-base-6.0.2.tgz", + "integrity": "sha512-RZNwNclF7+MS/8bDg70amg32dyeZGZxiDuQmZxKLAlQjr3jGyLx+4Kkk58UO7D2QdgFIQCovuSuZESne6RG6XQ==", + "license": "MIT", + "dependencies": { + "debug": "4" + }, + "engines": { + "node": ">= 6.0.0" + } + }, + "node_modules/axios/node_modules/https-proxy-agent": { + "version": "5.0.1", + "resolved": "https://registry.npmjs.org/https-proxy-agent/-/https-proxy-agent-5.0.1.tgz", + "integrity": "sha512-dFcAjpTQFgoLMzC2VwU+C/CbS7uRL0lWmxDITmqm7C+7F0Odmj6s9l6alZc6AELXhrnggM2CeWSXHGOdX2YtwA==", + "license": "MIT", + "dependencies": { + "agent-base": "6", + "debug": "4" + }, + "engines": { + "node": ">= 6" } }, "node_modules/axobject-query": { @@ -3465,6 +3494,12 @@ "node": "*" } }, + "node_modules/boolbase": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/boolbase/-/boolbase-1.0.0.tgz", + "integrity": "sha512-JZOSA7Mo9sNGB8+UjSgzdLtokWAky1zbztM3WRLCbZ70/3cTANmQmOdR7y2g+J0e2WXywy1yS468tY+IruqEww==", + "license": "ISC" + }, "node_modules/brace-expansion": { "version": "1.1.12", "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz", @@ -3619,6 +3654,81 @@ "url": "https://github.com/chalk/chalk?sponsor=1" } }, + "node_modules/cheerio": { + "version": "1.2.0", + "resolved": "https://registry.npmjs.org/cheerio/-/cheerio-1.2.0.tgz", + "integrity": "sha512-WDrybc/gKFpTYQutKIK6UvfcuxijIZfMfXaYm8NMsPQxSYvf+13fXUJ4rztGGbJcBQ/GF55gvrZ0Bc0bj/mqvg==", + "license": "MIT", + "dependencies": { + "cheerio-select": "^2.1.0", + "dom-serializer": "^2.0.0", + "domhandler": "^5.0.3", + "domutils": "^3.2.2", + "encoding-sniffer": "^0.2.1", + "htmlparser2": "^10.1.0", + "parse5": "^7.3.0", + "parse5-htmlparser2-tree-adapter": "^7.1.0", + "parse5-parser-stream": "^7.1.2", + "undici": "^7.19.0", + "whatwg-mimetype": "^4.0.0" + }, + "engines": { + "node": ">=20.18.1" + }, + "funding": { + "url": "https://github.com/cheeriojs/cheerio?sponsor=1" + } + }, + "node_modules/cheerio-select": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/cheerio-select/-/cheerio-select-2.1.0.tgz", + "integrity": "sha512-9v9kG0LvzrlcungtnJtpGNxY+fzECQKhK4EGJX2vByejiMX84MFNQw4UxPJl3bFbTMw+Dfs37XaIkCwTZfLh4g==", + "license": "BSD-2-Clause", + "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" + }, + "funding": { + "url": "https://github.com/sponsors/fb55" + } + }, + "node_modules/cheerio/node_modules/entities": { + "version": "6.0.1", + "resolved": "https://registry.npmjs.org/entities/-/entities-6.0.1.tgz", + "integrity": "sha512-aN97NXWF6AWBTahfVOIrB/NShkzi5H7F9r1s9mD3cDj4Ko5f2qhhVoYMibXF7GlLveb/D2ioWay8lxI97Ven3g==", + "license": "BSD-2-Clause", + "engines": { + "node": ">=0.12" + }, + "funding": { + "url": "https://github.com/fb55/entities?sponsor=1" + } + }, + "node_modules/cheerio/node_modules/parse5": { + "version": "7.3.0", + "resolved": "https://registry.npmjs.org/parse5/-/parse5-7.3.0.tgz", + "integrity": "sha512-IInvU7fabl34qmi9gY8XOVxhYyMyuH2xUNpb2q8/Y+7552KlejkRvqvD19nMoUW/uQGGbqNpA6Tufu5FL5BZgw==", + "license": "MIT", + "dependencies": { + "entities": "^6.0.0" + }, + "funding": { + "url": "https://github.com/inikulin/parse5?sponsor=1" + } + }, + "node_modules/cheerio/node_modules/whatwg-mimetype": { + "version": "4.0.0", + "resolved": "https://registry.npmjs.org/whatwg-mimetype/-/whatwg-mimetype-4.0.0.tgz", + "integrity": "sha512-QaKxh0eNIi2mE9p2vEdzfagOKHCcj1pJ56EEHGQOVxp8r9/iszLUUV7v89x9O1p/T+NlTM5W7jW6+cz4Fq1YVg==", + "license": "MIT", + "engines": { + "node": ">=18" + } + }, "node_modules/client-only": { "version": "0.0.1", "resolved": "https://registry.npmjs.org/client-only/-/client-only-0.0.1.tgz", @@ -3701,6 +3811,22 @@ "node": ">= 8" } }, + "node_modules/css-select": { + "version": "5.2.2", + "resolved": "https://registry.npmjs.org/css-select/-/css-select-5.2.2.tgz", + "integrity": "sha512-TizTzUddG/xYLA3NXodFM0fSbNizXjOKhqiQQwvhlspadZokn1KDy0NZFS0wuEubIYAV5/c1/lAr0TaaFXEXzw==", + "license": "BSD-2-Clause", + "dependencies": { + "boolbase": "^1.0.0", + "css-what": "^6.1.0", + "domhandler": "^5.0.2", + "domutils": "^3.0.1", + "nth-check": "^2.0.1" + }, + "funding": { + "url": "https://github.com/sponsors/fb55" + } + }, "node_modules/css-tree": { "version": "3.2.1", "resolved": "https://registry.npmjs.org/css-tree/-/css-tree-3.2.1.tgz", @@ -3714,6 +3840,18 @@ "node": "^10 || ^12.20.0 || ^14.13.0 || >=15.0.0" } }, + "node_modules/css-what": { + "version": "6.2.2", + "resolved": "https://registry.npmjs.org/css-what/-/css-what-6.2.2.tgz", + "integrity": "sha512-u/O3vwbptzhMs3L1fQE82ZSLHQQfto5gyZzwteVIEyeaY5Fc7R4dapF/BvRoSYFeqfBk4m0V1Vafq5Pjv25wvA==", + "license": "BSD-2-Clause", + "engines": { + "node": ">= 6" + }, + "funding": { + "url": "https://github.com/sponsors/fb55" + } + }, "node_modules/cssstyle": { "version": "6.2.0", "resolved": "https://registry.npmjs.org/cssstyle/-/cssstyle-6.2.0.tgz", @@ -3916,11 +4054,52 @@ "node": ">=0.10.0" } }, + "node_modules/dom-serializer": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/dom-serializer/-/dom-serializer-2.0.0.tgz", + "integrity": "sha512-wIkAryiqt/nV5EQKqQpo3SToSOV9J0DnbJqwK7Wv/Trc92zIAYZ4FlMu+JPFW1DfGFt81ZTCGgDEabffXeLyJg==", + "license": "MIT", + "dependencies": { + "domelementtype": "^2.3.0", + "domhandler": "^5.0.2", + "entities": "^4.2.0" + }, + "funding": { + "url": "https://github.com/cheeriojs/dom-serializer?sponsor=1" + } + }, "node_modules/dom-walk": { "version": "0.1.2", "resolved": "https://registry.npmjs.org/dom-walk/-/dom-walk-0.1.2.tgz", "integrity": "sha512-6QvTW9mrGeIegrFXdtQi9pk7O/nSK6lSdXW2eqUspN5LWD7UTji2Fqw5V2YLjBpHEoU9Xl/eUWNpDeZvoyOv2w==" }, + "node_modules/domelementtype": { + "version": "2.3.0", + "resolved": "https://registry.npmjs.org/domelementtype/-/domelementtype-2.3.0.tgz", + "integrity": "sha512-OLETBj6w0OsagBwdXnPdN0cnMfF9opN69co+7ZrbfPGrdpPVNBUj02spi6B1N7wChLQiPn4CSH/zJvXw56gmHw==", + "funding": [ + { + "type": "github", + "url": "https://github.com/sponsors/fb55" + } + ], + "license": "BSD-2-Clause" + }, + "node_modules/domhandler": { + "version": "5.0.3", + "resolved": "https://registry.npmjs.org/domhandler/-/domhandler-5.0.3.tgz", + "integrity": "sha512-cgwlv/1iFQiFnU96XXgROh8xTeetsnJiDsTc7TYCLFd9+/WNkIqPTxiM/8pSd8VIrhXGTf1Ny1q1hquVqDJB5w==", + "license": "BSD-2-Clause", + "dependencies": { + "domelementtype": "^2.3.0" + }, + "engines": { + "node": ">= 4" + }, + "funding": { + "url": "https://github.com/fb55/domhandler?sponsor=1" + } + }, "node_modules/dompurify": { "version": "3.3.3", "resolved": "https://registry.npmjs.org/dompurify/-/dompurify-3.3.3.tgz", @@ -3930,6 +4109,32 @@ "@types/trusted-types": "^2.0.7" } }, + "node_modules/domutils": { + "version": "3.2.2", + "resolved": "https://registry.npmjs.org/domutils/-/domutils-3.2.2.tgz", + "integrity": "sha512-6kZKyUajlDuqlHKVX1w7gyslj9MPIXzIFiz/rGu35uC1wMi+kMhQwGhl4lt9unC9Vb9INnY9Z3/ZA3+FhASLaw==", + "license": "BSD-2-Clause", + "dependencies": { + "dom-serializer": "^2.0.0", + "domelementtype": "^2.3.0", + "domhandler": "^5.0.3" + }, + "funding": { + "url": "https://github.com/fb55/domutils?sponsor=1" + } + }, + "node_modules/dotenv": { + "version": "17.4.2", + "resolved": "https://registry.npmjs.org/dotenv/-/dotenv-17.4.2.tgz", + "integrity": "sha512-nI4U3TottKAcAD9LLud4Cb7b2QztQMUEfHbvhTH09bqXTxnSie8WnjPALV/WMCrJZ6UV/qHJ6L03OqO3LcdYZw==", + "license": "BSD-2-Clause", + "engines": { + "node": ">=12" + }, + "funding": { + "url": "https://dotenvx.com" + } + }, "node_modules/dunder-proto": { "version": "1.0.1", "resolved": "https://registry.npmjs.org/dunder-proto/-/dunder-proto-1.0.1.tgz", @@ -3958,6 +4163,19 @@ "dev": true, "license": "MIT" }, + "node_modules/encoding-sniffer": { + "version": "0.2.1", + "resolved": "https://registry.npmjs.org/encoding-sniffer/-/encoding-sniffer-0.2.1.tgz", + "integrity": "sha512-5gvq20T6vfpekVtqrYQsSCFZ1wEg5+wW0/QaZMWkFr6BqD3NfKs0rLCx4rrVlSWJeZb5NBJgVLswK/w2MWU+Gw==", + "license": "MIT", + "dependencies": { + "iconv-lite": "^0.6.3", + "whatwg-encoding": "^3.1.1" + }, + "funding": { + "url": "https://github.com/fb55/encoding-sniffer?sponsor=1" + } + }, "node_modules/enhanced-resolve": { "version": "5.20.1", "resolved": "https://registry.npmjs.org/enhanced-resolve/-/enhanced-resolve-5.20.1.tgz", @@ -4745,9 +4963,9 @@ "license": "ISC" }, "node_modules/follow-redirects": { - "version": "1.15.11", - "resolved": "https://registry.npmjs.org/follow-redirects/-/follow-redirects-1.15.11.tgz", - "integrity": "sha512-deG2P0JfjrTxl50XGCDyfI97ZGVCxIpfKYmfyrQ54n5FO/0gfIES8C/Psl6kWVDolizcaaxZJnTS0QSMxvnsBQ==", + "version": "1.16.0", + "resolved": "https://registry.npmjs.org/follow-redirects/-/follow-redirects-1.16.0.tgz", + "integrity": "sha512-y5rN/uOsadFT/JfYwhxRS5R7Qce+g3zG97+JrtFZlC9klX/W5hD7iiLzScI4nZqUS7DNUdhPgw4xI8W2LuXlUw==", "funding": [ { "type": "individual", @@ -5130,6 +5348,37 @@ "node": "^20.19.0 || ^22.12.0 || >=24.0.0" } }, + "node_modules/htmlparser2": { + "version": "10.1.0", + "resolved": "https://registry.npmjs.org/htmlparser2/-/htmlparser2-10.1.0.tgz", + "integrity": "sha512-VTZkM9GWRAtEpveh7MSF6SjjrpNVNNVJfFup7xTY3UpFtm67foy9HDVXneLtFVt4pMz5kZtgNcvCniNFb1hlEQ==", + "funding": [ + "https://github.com/fb55/htmlparser2?sponsor=1", + { + "type": "github", + "url": "https://github.com/sponsors/fb55" + } + ], + "license": "MIT", + "dependencies": { + "domelementtype": "^2.3.0", + "domhandler": "^5.0.3", + "domutils": "^3.2.2", + "entities": "^7.0.1" + } + }, + "node_modules/htmlparser2/node_modules/entities": { + "version": "7.0.1", + "resolved": "https://registry.npmjs.org/entities/-/entities-7.0.1.tgz", + "integrity": "sha512-TWrgLOFUQTH994YUyl1yT4uyavY5nNB5muff+RtWaqNVCAK408b5ZnnbNAUEWLTCpum9w6arT70i1XdQ4UeOPA==", + "license": "BSD-2-Clause", + "engines": { + "node": ">=0.12" + }, + "funding": { + "url": "https://github.com/fb55/entities?sponsor=1" + } + }, "node_modules/http-proxy-agent": { "version": "7.0.2", "resolved": "https://registry.npmjs.org/http-proxy-agent/-/http-proxy-agent-7.0.2.tgz", @@ -5156,6 +5405,18 @@ "node": ">= 14" } }, + "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==", + "license": "MIT", + "dependencies": { + "safer-buffer": ">= 2.1.2 < 3.0.0" + }, + "engines": { + "node": ">=0.10.0" + } + }, "node_modules/ignore": { "version": "5.3.2", "resolved": "https://registry.npmjs.org/ignore/-/ignore-5.3.2.tgz", @@ -6535,6 +6796,18 @@ "dev": true, "license": "MIT" }, + "node_modules/nth-check": { + "version": "2.1.1", + "resolved": "https://registry.npmjs.org/nth-check/-/nth-check-2.1.1.tgz", + "integrity": "sha512-lqjrjmaOoAnWfMmBPL+XNnynZh2+swxiX3WUE0s4yEHI6m+AwrK2UZOimIRl3X/4QctVqS8AiZjFqyOGrMXb/w==", + "license": "BSD-2-Clause", + "dependencies": { + "boolbase": "^1.0.0" + }, + "funding": { + "url": "https://github.com/fb55/nth-check?sponsor=1" + } + }, "node_modules/object-assign": { "version": "4.1.1", "resolved": "https://registry.npmjs.org/object-assign/-/object-assign-4.1.1.tgz", @@ -6757,6 +7030,79 @@ "url": "https://github.com/inikulin/parse5?sponsor=1" } }, + "node_modules/parse5-htmlparser2-tree-adapter": { + "version": "7.1.0", + "resolved": "https://registry.npmjs.org/parse5-htmlparser2-tree-adapter/-/parse5-htmlparser2-tree-adapter-7.1.0.tgz", + "integrity": "sha512-ruw5xyKs6lrpo9x9rCZqZZnIUntICjQAd0Wsmp396Ul9lN/h+ifgVV1x1gZHi8euej6wTfpqX8j+BFQxF0NS/g==", + "license": "MIT", + "dependencies": { + "domhandler": "^5.0.3", + "parse5": "^7.0.0" + }, + "funding": { + "url": "https://github.com/inikulin/parse5?sponsor=1" + } + }, + "node_modules/parse5-htmlparser2-tree-adapter/node_modules/entities": { + "version": "6.0.1", + "resolved": "https://registry.npmjs.org/entities/-/entities-6.0.1.tgz", + "integrity": "sha512-aN97NXWF6AWBTahfVOIrB/NShkzi5H7F9r1s9mD3cDj4Ko5f2qhhVoYMibXF7GlLveb/D2ioWay8lxI97Ven3g==", + "license": "BSD-2-Clause", + "engines": { + "node": ">=0.12" + }, + "funding": { + "url": "https://github.com/fb55/entities?sponsor=1" + } + }, + "node_modules/parse5-htmlparser2-tree-adapter/node_modules/parse5": { + "version": "7.3.0", + "resolved": "https://registry.npmjs.org/parse5/-/parse5-7.3.0.tgz", + "integrity": "sha512-IInvU7fabl34qmi9gY8XOVxhYyMyuH2xUNpb2q8/Y+7552KlejkRvqvD19nMoUW/uQGGbqNpA6Tufu5FL5BZgw==", + "license": "MIT", + "dependencies": { + "entities": "^6.0.0" + }, + "funding": { + "url": "https://github.com/inikulin/parse5?sponsor=1" + } + }, + "node_modules/parse5-parser-stream": { + "version": "7.1.2", + "resolved": "https://registry.npmjs.org/parse5-parser-stream/-/parse5-parser-stream-7.1.2.tgz", + "integrity": "sha512-JyeQc9iwFLn5TbvvqACIF/VXG6abODeB3Fwmv/TGdLk2LfbWkaySGY72at4+Ty7EkPZj854u4CrICqNk2qIbow==", + "license": "MIT", + "dependencies": { + "parse5": "^7.0.0" + }, + "funding": { + "url": "https://github.com/inikulin/parse5?sponsor=1" + } + }, + "node_modules/parse5-parser-stream/node_modules/entities": { + "version": "6.0.1", + "resolved": "https://registry.npmjs.org/entities/-/entities-6.0.1.tgz", + "integrity": "sha512-aN97NXWF6AWBTahfVOIrB/NShkzi5H7F9r1s9mD3cDj4Ko5f2qhhVoYMibXF7GlLveb/D2ioWay8lxI97Ven3g==", + "license": "BSD-2-Clause", + "engines": { + "node": ">=0.12" + }, + "funding": { + "url": "https://github.com/fb55/entities?sponsor=1" + } + }, + "node_modules/parse5-parser-stream/node_modules/parse5": { + "version": "7.3.0", + "resolved": "https://registry.npmjs.org/parse5/-/parse5-7.3.0.tgz", + "integrity": "sha512-IInvU7fabl34qmi9gY8XOVxhYyMyuH2xUNpb2q8/Y+7552KlejkRvqvD19nMoUW/uQGGbqNpA6Tufu5FL5BZgw==", + "license": "MIT", + "dependencies": { + "entities": "^6.0.0" + }, + "funding": { + "url": "https://github.com/inikulin/parse5?sponsor=1" + } + }, "node_modules/parse5/node_modules/entities": { "version": "6.0.1", "resolved": "https://registry.npmjs.org/entities/-/entities-6.0.1.tgz", @@ -7100,10 +7446,13 @@ } }, "node_modules/proxy-from-env": { - "version": "1.1.0", - "resolved": "https://registry.npmjs.org/proxy-from-env/-/proxy-from-env-1.1.0.tgz", - "integrity": "sha512-D+zkORCbA9f1tdWRK0RaCR3GPv50cMxcrz4X8k5LTSUD1Dkw47mKJEZQNunItRTkWwgtaUSo1RVFRIG9ZXiFYg==", - "license": "MIT" + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/proxy-from-env/-/proxy-from-env-2.1.0.tgz", + "integrity": "sha512-cJ+oHTW1VAEa8cJslgmUZrc+sjRKgAKl3Zyse6+PV38hZe/V6Z14TbCuXcan9F9ghlz4QrFr2c92TNF82UkYHA==", + "license": "MIT", + "engines": { + "node": ">=10" + } }, "node_modules/punycode": { "version": "2.3.1", @@ -7362,6 +7711,12 @@ "url": "https://github.com/sponsors/ljharb" } }, + "node_modules/safer-buffer": { + "version": "2.1.2", + "resolved": "https://registry.npmjs.org/safer-buffer/-/safer-buffer-2.1.2.tgz", + "integrity": "sha512-YZo3K82SD7Riyi0E1EQPojLz7kpepnSQI9IyPbHHg1XXXevb5dJI7tpyN2ADxGcQbHG7vcyRHk0cbwqcQriUtg==", + "license": "MIT" + }, "node_modules/saxes": { "version": "6.0.0", "resolved": "https://registry.npmjs.org/saxes/-/saxes-6.0.0.tgz", @@ -7626,6 +7981,13 @@ "node": ">= 0.4" } }, + "node_modules/string-similarity": { + "version": "4.0.4", + "resolved": "https://registry.npmjs.org/string-similarity/-/string-similarity-4.0.4.tgz", + "integrity": "sha512-/q/8Q4Bl4ZKAPjj8WerIBJWALKkaPRfrvhfF8k/B23i4nzrlRj2/go1m90In7nG/3XDSbOo0+pu6RvCTM9RGMQ==", + "deprecated": "Package no longer supported. Contact Support at https://www.npmjs.com/support for more info.", + "license": "ISC" + }, "node_modules/string.prototype.includes": { "version": "2.0.1", "resolved": "https://registry.npmjs.org/string.prototype.includes/-/string.prototype.includes-2.0.1.tgz", @@ -8329,6 +8691,19 @@ "node": ">=20" } }, + "node_modules/whatwg-encoding": { + "version": "3.1.1", + "resolved": "https://registry.npmjs.org/whatwg-encoding/-/whatwg-encoding-3.1.1.tgz", + "integrity": "sha512-6qN4hJdMwfYBtE3YBTTHhoeuUrDBPZmbQaxWAqSALV/MeEnR5z1xd8UKud2RAkFoPkmB+hli1TZSnyi84xz1vQ==", + "deprecated": "Use @exodus/bytes instead for a more spec-conformant and faster implementation", + "license": "MIT", + "dependencies": { + "iconv-lite": "0.6.3" + }, + "engines": { + "node": ">=18" + } + }, "node_modules/whatwg-mimetype": { "version": "5.0.0", "resolved": "https://registry.npmjs.org/whatwg-mimetype/-/whatwg-mimetype-5.0.0.tgz", diff --git a/package.json b/package.json index 21698e4..27a8324 100644 --- a/package.json +++ b/package.json @@ -24,15 +24,18 @@ "@types/dompurify": "^3.0.5", "@types/video.js": "^7.3.58", "appwrite": "^22.4.1", - "axios": "^1.13.6", + "axios": "^1.18.0", + "cheerio": "^1.2.0", "clsx": "^2.1.1", "dompurify": "^3.3.3", + "dotenv": "^17.4.2", "isomorphic-dompurify": "^2.20.0", "lucide-react": "^0.577.0", "next": "16.1.6", - "node-appwrite": "^22.0.0", + "node-appwrite": "^22.1.3", "react": "19.2.3", "react-dom": "19.2.3", + "string-similarity": "^4.0.4", "tailwind-merge": "^3.5.0", "video.js": "^8.23.7", "zod": "^4.3.6", diff --git a/scrape-multivision.js b/scrape-multivision.js index b2c6b3b..1afc1bb 100644 --- a/scrape-multivision.js +++ b/scrape-multivision.js @@ -1,6 +1,7 @@ const axios = require('axios'); const fs = require('fs'); const cheerio = require('cheerio'); +const stringSimilarity = require('string-similarity'); const { Client, Databases, Storage, ID, Query } = require('node-appwrite'); require('dotenv').config({ path: '.env.local' }); @@ -19,16 +20,6 @@ const BUCKET_ID = process.env.NEXT_PUBLIC_APPWRITE_MEDIA_BUCKET_ID; const excludedNodes = ['962', '963', '895', '894', '893', '964']; -async function deleteOldScrapes(postsCollectionId) { - console.log('Deleting poorly scraped posts...'); - const res = await databases.listDocuments(DB_ID, postsCollectionId, [Query.limit(100)]); - const toDelete = res.documents.filter(p => p.slug && p.slug.startsWith('multivision-')); - for (const d of toDelete) { - await databases.deleteDocument(DB_ID, postsCollectionId, d.$id); - console.log('Deleted:', d.slug); - } -} - async function scrapeNode(url) { try { const res = await axios.get(url); @@ -39,20 +30,19 @@ async function scrapeNode(url) { // Extract date let dateObj = null; const timeText = $('span').filter((i, el) => $(el).text().match(/\d{2}\/\d{2}\/\d{4} - \d{2}:\d{2}/)).first().text(); - // e.g. "Mar, 31/03/2026 - 10:16" if (timeText) { const match = timeText.match(/(\d{2})\/(\d{2})\/(\d{4}) - (\d{2}:\d{2})/); if (match) { - // DD/MM/YYYY dateObj = new Date(`${match[3]}-${match[2]}-${match[1]}T${match[4]}:00.000Z`); } } - if (!dateObj) return null; // Skip if no date found + if (!dateObj) return null; - // We only want March 2026 - if (dateObj.getMonth() !== 2 || dateObj.getFullYear() !== 2026) { - return { skipped: true, reason: 'Not in March 2026' }; + // We only want April (3), May (4), June (5) 2026 + const validMonths = [3, 4, 5]; + if (!validMonths.includes(dateObj.getMonth()) || dateObj.getFullYear() !== 2026) { + return { skipped: true, reason: 'Not in April, May, or June 2026' }; } // Extract image @@ -61,7 +51,7 @@ async function scrapeNode(url) { const src = $(el).attr('src'); if (src && (src.includes('public/imagenes') || src.includes('styles/')) && !src.includes('logo')) { image = src.startsWith('http') ? src : 'https://www.multivisiondecolombia.com' + src; - return false; // break + return false; } }); @@ -71,11 +61,9 @@ async function scrapeNode(url) { if (bodyField.length > 0) { contentHtml = bodyField.html(); } else { - // fallback contentHtml = $('article').html() || ''; } - // Clean content: Keep only p, ul, li, strong, em, b, i const $content = cheerio.load(contentHtml || ''); $content('*').each((i, el) => { if (!['p', 'ul', 'li', 'strong', 'em', 'b', 'i'].includes(el.tagName.toLowerCase())) { @@ -107,13 +95,25 @@ async function run() { const typeRes = await databases.listDocuments(DB_ID, pubTypesCollectionId, [Query.equal('codigo', 'NOTICIA')]); const typeId = typeRes.documents.length > 0 ? typeRes.documents[0].$id : null; - await deleteOldScrapes(postsCollectionId); + console.log('Fetching existing titles from Appwrite to prevent duplicates...'); + let allExistingTitles = []; + let cursor = null; + while (true) { + const queries = [Query.limit(100), Query.select(['titulo'])]; + if (cursor) queries.push(Query.cursorAfter(cursor)); + const existingRes = await databases.listDocuments(DB_ID, postsCollectionId, queries); + + existingRes.documents.forEach(d => allExistingTitles.push(d.titulo)); + + if (existingRes.documents.length < 100) break; + cursor = existingRes.documents[existingRes.documents.length - 1].$id; + } + console.log(`Found ${allExistingTitles.length} existing posts.`); - console.log('Fetching news list from Multivision...'); + console.log('Fetching news list from Multivision (Pages 0-15)...'); const allNodes = new Set(); - // Loop through some pages (0 to 5) - for (let page = 0; page <= 5; page++) { + for (let page = 0; page <= 15; page++) { try { const listUrl = `https://www.multivisiondecolombia.com/noticias?page=${page}`; const res = await axios.get(listUrl); @@ -149,9 +149,27 @@ async function run() { continue; } + // Check similarity + let isDuplicate = false; + let highestSimilarity = 0; + let mostSimilarTitle = ''; + + for (const exTitle of allExistingTitles) { + if (!exTitle) continue; + const sim = stringSimilarity.compareTwoStrings(data.title.toLowerCase(), exTitle.toLowerCase()); + if (sim > highestSimilarity) { + highestSimilarity = sim; + mostSimilarTitle = exTitle; + } + } + + if (highestSimilarity > 0.60) { + console.log(`Skipped due to similarity (${(highestSimilarity*100).toFixed(1)}%) with: "${mostSimilarTitle}"`); + continue; + } + console.log('Extracted Title:', data.title); console.log('Extracted Date:', data.date); - console.log('Extracted Image:', data.image); let mediaId = null; if (data.image) { @@ -178,7 +196,7 @@ async function run() { const doc = { titulo: data.title.substring(0, 100), - slug: `multivision-marzo-${Date.now()}-${count}`, + slug: `multivision-amj-${Date.now()}-${count}`, tipo_publicacion_id: typeId, estado: 'Publicado', fecha_publicacion: data.date, @@ -188,9 +206,11 @@ async function run() { const res = await databases.createDocument(DB_ID, postsCollectionId, ID.unique(), doc); console.log('Published! ID:', res.$id); + // Add to existing to prevent duplicates within this run + allExistingTitles.push(data.title); count++; } - console.log(`\nAll done! Successfully published ${count} news articles from March.`); + console.log(`\nAll done! Successfully published ${count} unique news articles from April, May, and June.`); } catch(e) { console.error(e); }