pagerts 1.5.2 → 1.5.5

package/README.md

@@ -14,6 +14,8 @@ PagerTS is a secure, modern command-line utility that transforms URLs into struc
 - ⚡ **Fast**: Efficient parsing with LinkeDOM and concurrent request handling
 - 🧪 **Well-Tested**: Comprehensive test coverage with Jest
 - 📦 **Easy to Use**: Simple CLI interface with sensible defaults
+- 🗂️ **Local File Support**: bare `pagerts` parses local file paths and `file:///...` inputs
+- 🧭 **Request Header Override**: Optional `--user-agent` flag for sites that behave differently by client
 
 ## Installation
 
@@ -21,13 +23,13 @@ PagerTS is a secure, modern command-line utility that transforms URLs into struc
 
 ```bash
 npm install -g pagerts
-pagerts <url>
+pagerts ./page.html
 ```
 
 ### Using npx (No Installation Required)
 
 ```bash
-npx pagerts <url>
+npx pagerts ./page.html
 ```
 
 ### From Source
@@ -44,22 +46,40 @@ npm link
 
 ### Basic Usage
 
-Extract resources from a remote URL:
+Extract resources from a local HTML file path:
 
 ```bash
-pagerts https://example.com
+pagerts ./page.html
 ```
 
-Extract from multiple URLs:
+Extract resources from a local file URL:
 
 ```bash
-pagerts https://example.com https://example.org
+pagerts file:///path/to/file.html
 ```
 
-Extract from a local HTML file:
+Fetch resources from a remote URL:
 
 ```bash
-pagerts file:///path/to/file.html
+pagerts fetch https://website.com
+```
+
+Override the HTTP user-agent for remote fetches:
+
+```bash
+pagerts fetch --user-agent "Mozilla/5.0 (X11; Linux x86_64; rv:139.0) Gecko/20100101 Firefox/139.0" https://example.com
+```
+
+Allow fetching from localhost/private-network targets (opt-in):
+
+```bash
+pagerts fetch --allow-private-hosts http://127.0.0.1:3000
+```
+
+Fetch from multiple remote URLs:
+
+```bash
+pagerts fetch https://example.com https://example.org
 ```
 
 ### Output Format
@@ -98,10 +118,14 @@ PagerTS takes security seriously. See [SECURITY.md](./SECURITY.md) for:
 
 ### Built-in Security Features
 
-- ✅ URL validation (only allows `http://`, `https://`, `file://`)
+- ✅ URL validation for remote fetches (only allows `http://` and `https://`)
+- ✅ Private/loopback hosts are blocked by default for remote fetches (SSRF mitigation)
+- ✅ Local filesystem parsing through plain paths and `file://` inputs on the root command
 - ✅ Input sanitization to prevent XSS attacks
 - ✅ Rate limiting (50 requests/minute by default)
 - ✅ Request timeouts to prevent hanging
+- ✅ HTTP status and content-type checks for remote responses
+- ✅ Maximum remote HTML response size enforcement (2 MiB)
 - ✅ Maximum URL length enforcement
 - ✅ Suspicious pattern detection
 - ✅ Safe HTML parsing (no script execution)
@@ -226,6 +250,13 @@ This project is licensed under the MIT License - see the [LICENSE](./LICENSE) fi
 
 ## Changelog
 
+### v1.5.3
+
+- Added `--user-agent` support to the `fetch` command so callers can override the HTTP User-Agent header for remote requests.
+- Made the root `pagerts` command parse local file paths and `file:///` inputs directly, while keeping `fetch` remote-only.
+- Improved CLI/runtime compatibility for locally resolved entrypoints and packaged builds.
+- Updated focused tests to cover the new file-protocol validation and user-agent override behavior.
+
 ### v0.3.0 -> v1.4.3 summary
 
 Key changes in this range:

package/bin/main.js

@@ -12,6 +12,7 @@ var AbstractExtractor = class {
   constructor(name2) {
     this.name = name2;
   }
+  name;
 };
 
 // src/extractors/PageExtractor.ts
@@ -64,6 +65,7 @@ var ResourceExtractor = class extends AbstractExtractor {
     super("page-extractor");
     this.tags = tags;
   }
+  tags;
   async extract(value) {
     const { document } = value.window;
     return this.tags.flatMap(
@@ -79,12 +81,16 @@ var ResourceExtractor = class extends AbstractExtractor {
 
 // src/page/PageFetcher.ts
 import { parseHTML } from "linkedom";
+var MAX_HTML_BYTES = 2 * 1024 * 1024;
+var ALLOWED_CONTENT_TYPES = ["text/html", "application/xhtml+xml"];
 var PageFetcher = class {
   timeout;
   maxRetries;
-  constructor(timeout = 1e4, maxRetries = 2) {
+  userAgent;
+  constructor(timeout = 1e4, maxRetries = 2, userAgent) {
     this.timeout = timeout;
     this.maxRetries = maxRetries;
+    this.userAgent = userAgent;
   }
   buildDOMResult(html, url) {
     const { document } = parseHTML(html);
@@ -106,13 +112,33 @@ var PageFetcher = class {
           controller.abort(new Error("Request timeout"));
         }, this.timeout);
       }
-      const content = await fetch(url, { signal: controller.signal }).then(async (response) => {
-        const buffer = await response.arrayBuffer();
-        const contentType = response.headers.get("content-type") ?? "";
-        const charsetMatch = /charset=([^\s;]+)/i.exec(contentType);
-        const html = this.decodeHtml(buffer, charsetMatch?.[1] ?? "utf-8");
-        return this.buildDOMResult(html, url);
-      });
+      const headers = this.userAgent ? { "user-agent": this.userAgent } : void 0;
+      const content = await fetch(url, { headers, signal: controller.signal }).then(
+        async (response) => {
+          if (!response.ok) {
+            throw new Error(`HTTP ${response.status} ${response.statusText}`.trim());
+          }
+          const contentType = (response.headers.get("content-type") ?? "").toLowerCase();
+          const isAllowedContentType = ALLOWED_CONTENT_TYPES.some(
+            (allowedType) => contentType.includes(allowedType)
+          );
+          if (!isAllowedContentType) {
+            throw new Error(`Unsupported content type: ${contentType || "unknown"}`);
+          }
+          const contentLengthHeader = response.headers.get("content-length");
+          const contentLength = contentLengthHeader ? Number(contentLengthHeader) : Number.NaN;
+          if (Number.isFinite(contentLength) && contentLength > MAX_HTML_BYTES) {
+            throw new Error(`Response exceeds max allowed size (${MAX_HTML_BYTES} bytes)`);
+          }
+          const buffer = await response.arrayBuffer();
+          if (buffer.byteLength > MAX_HTML_BYTES) {
+            throw new Error(`Response exceeds max allowed size (${MAX_HTML_BYTES} bytes)`);
+          }
+          const charsetMatch = /charset=([^\s;]+)/i.exec(contentType);
+          const html = this.decodeHtml(buffer, charsetMatch?.[1] ?? "utf-8");
+          return this.buildDOMResult(html, url);
+        }
+      );
       return { url, content };
     } catch (error) {
       const abortTimeout = error instanceof Error && error.name === "AbortError";
@@ -183,6 +209,7 @@ var JSONStylePrinter = class extends AbstractResourcePrinter {
 };
 
 // src/security.ts
+import { isIP } from "node:net";
 var ALLOWED_PROTOCOLS = ["http:", "https:"];
 var MAX_URL_LENGTH = 2048;
 var SUSPICIOUS_PATTERNS = [
@@ -193,7 +220,26 @@ var SUSPICIOUS_PATTERNS = [
   /on\w+=/i
   // Event handlers like onclick=
 ];
-function validateUrl(url) {
+function isPrivateHostname(hostname) {
+  const normalized = hostname.toLowerCase();
+  if (normalized === "localhost" || normalized.endsWith(".localhost")) {
+    return true;
+  }
+  const ipType = isIP(normalized);
+  if (ipType === 0) {
+    return false;
+  }
+  if (ipType === 4) {
+    const octets = normalized.split(".").map(Number);
+    if (octets.length !== 4 || octets.some((octet) => Number.isNaN(octet))) {
+      return false;
+    }
+    const [a, b] = octets;
+    return a === 10 || a === 127 || a === 169 && b === 254 || a === 172 && b >= 16 && b <= 31 || a === 192 && b === 168 || a === 0;
+  }
+  return normalized === "::1" || normalized === "::" || normalized.startsWith("fc") || normalized.startsWith("fd") || normalized.startsWith("fe8") || normalized.startsWith("fe9") || normalized.startsWith("fea") || normalized.startsWith("feb");
+}
+function validateUrl(url, options = {}) {
   if (!url || !url.trim()) {
     return {
       isValid: false,
@@ -230,21 +276,28 @@ function validateUrl(url) {
       error: `Protocol ${parsedUrl.protocol} is not allowed. Allowed protocols: ${ALLOWED_PROTOCOLS.join(", ")}`
     };
   }
-  const hostname = parsedUrl.hostname.toLowerCase();
-  const isLocalhost = hostname === "localhost" || hostname === "127.0.0.1" || hostname === "::1" || hostname.startsWith("192.168.") || hostname.startsWith("10.") || /^172\.(1[6-9]|2\d|3[01])\./.test(hostname);
-  if (isLocalhost) {
-    console.warn(`Warning: Accessing local network resource: ${trimmedUrl}`);
+  if (parsedUrl.username || parsedUrl.password) {
+    return {
+      isValid: false,
+      error: "URLs with embedded credentials are not allowed"
+    };
+  }
+  if (!options.allowPrivateHosts && isPrivateHostname(parsedUrl.hostname)) {
+    return {
+      isValid: false,
+      error: "Private or loopback hostnames are blocked by default. Use --allow-private-hosts if you trust the target."
+    };
   }
   return {
     isValid: true,
     sanitizedUrl: parsedUrl.toString()
   };
 }
-function validateUrls(urls) {
+function validateUrls(urls, options = {}) {
   const validUrls = [];
   const errors = [];
   for (const url of urls) {
-    const result = validateUrl(url);
+    const result = validateUrl(url, options);
     if (result.isValid && result.sanitizedUrl) {
       validUrls.push(result.sanitizedUrl);
     } else {
@@ -277,6 +330,37 @@ async function buildPageMetadata(responses) {
   }
   return pageMetadatas;
 }
+function normalizeLocalPath(value) {
+  if (value.startsWith("file://")) {
+    return fileURLToPath(value);
+  }
+  return value;
+}
+async function runFileCommand(paths, options) {
+  if (options.failsafe && paths.length > MAX_FILES_FAILSAFE) {
+    console.error(
+      `
+\u274C ${paths.length} files specified exceeds the safety limit of ${MAX_FILES_FAILSAFE}.`
+    );
+    console.error(`   Pass --no-failsafe to bypass this check and process all files.`);
+    process.exit(1);
+  }
+  if (!options.failsafe && paths.length > MAX_FILES_FAILSAFE) {
+    console.error(
+      `
+\u26A0\uFE0F  Failsafe bypassed: processing ${paths.length} files (limit is ${MAX_FILES_FAILSAFE}).`
+    );
+  }
+  console.error(`
+\u2705 Processing ${paths.length} file(s)...`);
+  const fileFetcher = new FileFetcher();
+  const normalizedPaths = paths.map((pathValue) => normalizeLocalPath(pathValue));
+  const responses = await fileFetcher.fetchAll(normalizedPaths);
+  const pageMetadatas = await buildPageMetadata(
+    responses.map(({ path, content, error }) => ({ path, content, error }))
+  );
+  await printer.print(...pageMetadatas);
+}
 function isCliEntrypoint() {
   const invokedPath = process.argv[1];
   if (!invokedPath) {
@@ -290,85 +374,86 @@ function isCliEntrypoint() {
 }
 async function runCli(argv = process.argv) {
   program.name(name).version(version, "-v, --version").description(description);
-  program.command("fetch", { isDefault: true }).description("fetch and extract resources from remote URL(s)").addArgument(urlArg).addOption(
+  program.addArgument(fileArg).addOption(
+    new Option("--no-failsafe", `bypass the ${MAX_FILES_FAILSAFE}-file limit safety check`)
+  ).action(async (paths, options) => {
+    try {
+      await runFileCommand(paths, options);
+    } catch (error) {
+      console.error("\n\u274C An error occurred:", error instanceof Error ? error.message : error);
+      process.exit(1);
+    }
+  });
+  program.command("fetch").description("fetch and extract resources from remote URL(s)").addArgument(urlArg).addOption(
     new Option(
       "--watch",
       "keep running: SIGWINCH re-fetches after resize, Ctrl-D releases in-flight requests, Ctrl-C exits"
     )
-  ).action(async (urls, options) => {
-    try {
-      const { validUrls, errors } = validateUrls(urls);
-      if (errors.length > 0) {
-        console.error("\n\u274C URL Validation Errors:");
-        errors.forEach(({ url: invalidUrl, error }) => {
-          console.error(`  - ${invalidUrl}: ${error}`);
+  ).addOption(new Option("-A, --user-agent <value>", "override the HTTP User-Agent header")).addOption(
+    new Option(
+      "--allow-private-hosts",
+      "allow localhost/private-network targets (disabled by default for SSRF safety)"
+    )
+  ).action(
+    async (urls, options) => {
+      try {
+        const { validUrls, errors } = validateUrls(urls, {
+          allowPrivateHosts: options.allowPrivateHosts
         });
-      }
-      if (validUrls.length === 0) {
-        console.error("\n\u274C No valid URLs to process. Exiting.");
-        process.exit(1);
-      }
-      console.error(`
+        if (errors.length > 0) {
+          console.error("\n\u274C URL Validation Errors:");
+          errors.forEach(({ url: invalidUrl, error }) => {
+            console.error(`  - ${invalidUrl}: ${error}`);
+          });
+        }
+        if (validUrls.length === 0) {
+          console.error("\n\u274C No valid URLs to process. Exiting.");
+          process.exit(1);
+        }
+        console.error(`
 \u2705 Processing ${validUrls.length} valid URL(s)...`);
-      const pageFetcher = new PageFetcher(options.watch ? 0 : 1e4, 2);
-      const execute = async () => {
-        const responses = await pageFetcher.fetchAll(validUrls);
-        const pageMetadatas = await buildPageMetadata(responses);
-        await printer.print(...pageMetadatas);
-      };
-      if (options.watch) {
-        process.stdin.resume();
-        process.on("SIGINT", () => process.exit(0));
-        let activeExecution = null;
-        process.stdin.on("end", () => {
-          activeExecution = null;
-        });
-        let winchTimer = null;
-        process.on("SIGWINCH", () => {
-          if (winchTimer !== null) clearTimeout(winchTimer);
-          winchTimer = setTimeout(() => {
-            winchTimer = null;
-            activeExecution = execute().catch((err) => {
-              console.error("\n\u274C An error occurred:", err instanceof Error ? err.message : err);
-            });
-          }, 150);
-        });
-        activeExecution = execute();
-        await activeExecution;
-      } else {
-        await execute();
+        const pageFetcher = new PageFetcher(options.watch ? 0 : 1e4, 2, options.userAgent);
+        const execute = async () => {
+          const responses = await pageFetcher.fetchAll(validUrls);
+          const pageMetadatas = await buildPageMetadata(responses);
+          await printer.print(...pageMetadatas);
+        };
+        if (options.watch) {
+          process.stdin.resume();
+          process.on("SIGINT", () => process.exit(0));
+          let activeExecution = null;
+          process.stdin.on("end", () => {
+            activeExecution = null;
+          });
+          let winchTimer = null;
+          process.on("SIGWINCH", () => {
+            if (winchTimer !== null) clearTimeout(winchTimer);
+            winchTimer = setTimeout(() => {
+              winchTimer = null;
+              activeExecution = execute().catch((err) => {
+                console.error(
+                  "\n\u274C An error occurred:",
+                  err instanceof Error ? err.message : err
+                );
+              });
+            }, 150);
+          });
+          activeExecution = execute();
+          await activeExecution;
+        } else {
+          await execute();
+        }
+      } catch (error) {
+        console.error("\n\u274C An error occurred:", error instanceof Error ? error.message : error);
+        process.exit(1);
       }
-    } catch (error) {
-      console.error("\n\u274C An error occurred:", error instanceof Error ? error.message : error);
-      process.exit(1);
     }
-  });
+  );
   program.command("file").description("extract resources from local file(s) via direct filesystem access").addArgument(fileArg).addOption(
     new Option("--no-failsafe", `bypass the ${MAX_FILES_FAILSAFE}-file limit safety check`)
   ).action(async (paths, options) => {
     try {
-      if (options.failsafe && paths.length > MAX_FILES_FAILSAFE) {
-        console.error(
-          `
-\u274C ${paths.length} files specified exceeds the safety limit of ${MAX_FILES_FAILSAFE}.`
-        );
-        console.error(`   Pass --no-failsafe to bypass this check and process all files.`);
-        process.exit(1);
-      }
-      if (!options.failsafe && paths.length > MAX_FILES_FAILSAFE) {
-        console.error(
-          `
-\u26A0\uFE0F  Failsafe bypassed: processing ${paths.length} files (limit is ${MAX_FILES_FAILSAFE}).`
-        );
-      }
-      console.error(`
-\u2705 Processing ${paths.length} file(s)...`);
-      const fileFetcher = new FileFetcher();
-      const responses = await fileFetcher.fetchAll(paths);
-      const pageMetadatas = await buildPageMetadata(
-        responses.map(({ path, content, error }) => ({ path, content, error }))
-      );
-      await printer.print(...pageMetadatas);
+      await runFileCommand(paths, options);
     } catch (error) {
       console.error("\n\u274C An error occurred:", error instanceof Error ? error.message : error);
       process.exit(1);

package/bin/main.js.map

@@ -1,7 +1,7 @@
 {
   "version": 3,
   "sources": ["../src/main.ts", "../src/extractors/AbstractExtractor.ts", "../src/extractors/PageExtractor.ts", "../src/resource.ts", "../src/extractors/ResourceExtractor.ts", "../src/page/PageFetcher.ts", "../src/page/FileFetcher.ts", "../src/printers/AbstractResourcePrinter.ts", "../src/printers/JSONStylePrinter.ts", "../src/security.ts"],
-  "sourcesContent": ["#!/usr/bin/env node\nimport { Command, createArgument, Option } from 'commander';\nimport { createRequire } from 'node:module';\nimport { resolve } from 'node:path';\nimport { fileURLToPath } from 'node:url';\nimport { realpathSync } from 'node:fs';\n\nimport { PageExtractor, ResourceExtractor } from './extractors/index.js';\nimport { FileFetcher, MAX_FILES_FAILSAFE, PageFetcher, type PageMetadata } from './page/index.js';\nimport { JSONStylePrinter } from './printers/index.js';\nimport { validateUrls } from './security.js';\n\nconst require = createRequire(import.meta.url);\nconst pkg = require('../package.json') as {\n  description: string;\n  name: string;\n  version: string;\n};\n\nconst { description, name, version } = pkg;\n\nconst program = new Command();\n\nconst urlArg = createArgument('<url...>', 'remote https://URL to extract from');\nconst fileArg = createArgument('<paths...>', 'local file paths to extract from');\n\n// Shared extractor instances.\nconst pageExtractor = new PageExtractor();\nconst resourceExtractor = new ResourceExtractor(['a', 'meta', 'link', 'embed', 'script']);\nconst printer = new JSONStylePrinter();\n\nasync function buildPageMetadata(\n  responses: Array<{\n    url?: string;\n    path?: string;\n    content?: import('./page/index.js').DOMResult;\n    error?: string;\n  }>\n): Promise<PageMetadata[]> {\n  const pageMetadatas: PageMetadata[] = [];\n\n  for (const { content, url: responseUrl, path, error } of responses) {\n    const resolvedUrl = responseUrl ?? path ?? '';\n    const resources =\n      error !== undefined || !content ? [] : await resourceExtractor.extract(content);\n    const descriptor =\n      error !== undefined || !content\n        ? { url: resolvedUrl, error: error ?? 'Unknown error', resources }\n        : await pageExtractor.extract(content);\n    pageMetadatas.push({ ...descriptor, resources });\n  }\n\n  return pageMetadatas;\n}\n\nfunction isCliEntrypoint(): boolean {\n  const invokedPath = process.argv[1];\n  if (!invokedPath) {\n    return false;\n  }\n\n  try {\n    return realpathSync(fileURLToPath(import.meta.url)) === realpathSync(resolve(invokedPath));\n  } catch {\n    return false;\n  }\n}\n\nexport async function runCli(argv: string[] = process.argv): Promise<void> {\n  program.name(name).version(version, '-v, --version').description(description);\n\n  // \u2500\u2500 fetch subcommand (default remote URL mode) \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\n  program\n    .command('fetch', { isDefault: true })\n    .description('fetch and extract resources from remote URL(s)')\n    .addArgument(urlArg)\n    .addOption(\n      new Option(\n        '--watch',\n        'keep running: SIGWINCH re-fetches after resize, Ctrl-D releases in-flight requests, Ctrl-C exits'\n      )\n    )\n    .action(async (urls: string[], options: { watch: boolean }) => {\n      try {\n        const { validUrls, errors } = validateUrls(urls);\n\n        if (errors.length > 0) {\n          console.error('\\n\u274C URL Validation Errors:');\n          errors.forEach(({ url: invalidUrl, error }) => {\n            console.error(`  - ${invalidUrl}: ${error}`);\n          });\n        }\n\n        if (validUrls.length === 0) {\n          console.error('\\n\u274C No valid URLs to process. Exiting.');\n          process.exit(1);\n        }\n\n        console.error(`\\n\u2705 Processing ${validUrls.length} valid URL(s)...`);\n\n        const pageFetcher = new PageFetcher(options.watch ? 0 : 10000, 2);\n\n        const execute = async (): Promise<void> => {\n          const responses = await pageFetcher.fetchAll(validUrls);\n          const pageMetadatas = await buildPageMetadata(responses);\n          await printer.print(...pageMetadatas);\n        };\n\n        if (options.watch) {\n          process.stdin.resume();\n          process.on('SIGINT', () => process.exit(0));\n\n          let activeExecution: Promise<void> | null = null;\n          process.stdin.on('end', () => {\n            activeExecution = null;\n          });\n\n          let winchTimer: ReturnType<typeof setTimeout> | null = null;\n          process.on('SIGWINCH', () => {\n            if (winchTimer !== null) clearTimeout(winchTimer);\n            winchTimer = setTimeout(() => {\n              winchTimer = null;\n              activeExecution = execute().catch((err: unknown) => {\n                console.error('\\n\u274C An error occurred:', err instanceof Error ? err.message : err);\n              });\n            }, 150);\n          });\n\n          activeExecution = execute();\n          await activeExecution;\n        } else {\n          await execute();\n        }\n      } catch (error) {\n        console.error('\\n\u274C An error occurred:', error instanceof Error ? error.message : error);\n        process.exit(1);\n      }\n    });\n\n  // \u2500\u2500 file subcommand (local filesystem access) \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\n  program\n    .command('file')\n    .description('extract resources from local file(s) via direct filesystem access')\n    .addArgument(fileArg)\n    .addOption(\n      new Option('--no-failsafe', `bypass the ${MAX_FILES_FAILSAFE}-file limit safety check`)\n    )\n    .action(async (paths: string[], options: { failsafe: boolean }) => {\n      try {\n        if (options.failsafe && paths.length > MAX_FILES_FAILSAFE) {\n          console.error(\n            `\\n\u274C ${paths.length} files specified exceeds the safety limit of ${MAX_FILES_FAILSAFE}.`\n          );\n          console.error(`   Pass --no-failsafe to bypass this check and process all files.`);\n          process.exit(1);\n        }\n\n        if (!options.failsafe && paths.length > MAX_FILES_FAILSAFE) {\n          console.error(\n            `\\n\u26A0\uFE0F  Failsafe bypassed: processing ${paths.length} files (limit is ${MAX_FILES_FAILSAFE}).`\n          );\n        }\n\n        console.error(`\\n\u2705 Processing ${paths.length} file(s)...`);\n\n        const fileFetcher = new FileFetcher();\n        const responses = await fileFetcher.fetchAll(paths);\n        const pageMetadatas = await buildPageMetadata(\n          responses.map(({ path, content, error }) => ({ path, content, error }))\n        );\n\n        await printer.print(...pageMetadatas);\n      } catch (error) {\n        console.error('\\n\u274C An error occurred:', error instanceof Error ? error.message : error);\n        process.exit(1);\n      }\n    });\n\n  await program.parseAsync(argv);\n}\n\nif (isCliEntrypoint()) {\n  runCli().catch((error: unknown) => {\n    console.error('\\n\u274C An error occurred:', error instanceof Error ? error.message : error);\n    process.exit(1);\n  });\n}\n", "export abstract class AbstractExtractor<V, R> {\n  constructor(readonly name: string) {}\n  abstract extract(value: V): Promise<R>;\n}\n", "import type { Page } from '../page/index.js';\nimport type { DOMResult } from '../page/index.js';\nimport { AbstractExtractor } from './AbstractExtractor.js';\n\nexport class PageExtractor extends AbstractExtractor<DOMResult, Page> {\n  constructor() {\n    super('page-extractor');\n  }\n\n  async extract(value: DOMResult): Promise<Page> {\n    const {\n      window: { document },\n      url,\n    } = value;\n    return { title: document.title, url };\n  }\n}\n", "/**\n * @license MIT\n * We are interested in visualising a page as a collection of tags.\n *\n * We wish to work with tags that can be compactly previewed on a webpage.\n * Here we must declare all of the element types that can be used to represent\n * a resource that can be hyperlinked off a webpage.\n */\ntype Tags = HTMLElementTagNameMap;\n\nexport const RESOURCE_DISPLAYABLE_KEYS = [\n  'id',\n  'innerText',\n  'textContent',\n  'class',\n  'ariaLabel',\n  'ariaDescription',\n  'alt',\n] as const;\n\nexport type DisplayableKey = (typeof RESOURCE_DISPLAYABLE_KEYS)[number];\n\nexport const RESOURCE_LINK_KEYS = ['href', 'data-src', 'target', 'action', 'src', 'url'] as const;\n\nexport type LinkKey = (typeof RESOURCE_LINK_KEYS)[number];\n\nexport type AttributeKey = DisplayableKey | LinkKey;\n\nexport type ResourceKey = { key: AttributeKey; value: string };\nexport type ResourceLink = { key: LinkKey; value: string };\n\nexport type ExternalResource = {\n  text: ResourceKey;\n  link: ResourceLink;\n};\n\nexport type Tag = keyof Tags;\n\nexport type Resource = HTMLElement & {\n  [K in AttributeKey]?: string | null;\n};\n\nexport type ResourceByName<T extends keyof Tags> = Tags[T];\n\n// --- adapters ---\n\nconst readAttr = (element: Resource, key: AttributeKey): string | undefined => {\n  const v = element.getAttribute(key);\n  return v != null && v.trim() !== '' ? v : undefined;\n};\n\nexport function findResourceText(element: Resource): ResourceKey | undefined {\n  for (const key of RESOURCE_DISPLAYABLE_KEYS) {\n    const value = readAttr(element, key);\n    if (value !== undefined) return { key, value };\n  }\n  return undefined;\n}\n\nexport function findResourceLink(element: Resource): ResourceLink | undefined {\n  for (const key of RESOURCE_LINK_KEYS) {\n    const value = readAttr(element, key);\n    if (value !== undefined) return { key, value };\n  }\n  return undefined;\n}\n\nexport const isResourceKey = (key: string): key is AttributeKey =>\n  (RESOURCE_DISPLAYABLE_KEYS as readonly string[]).includes(key) ||\n  (RESOURCE_LINK_KEYS as readonly string[]).includes(key);\n", "import type { DOMResult } from '../page/index.js';\nimport {\n  findResourceLink,\n  findResourceText,\n  type ExternalResource,\n  type Resource,\n  type Tag,\n} from '../resource.js';\nimport { AbstractExtractor } from './AbstractExtractor.js';\n\nexport class ResourceExtractor extends AbstractExtractor<DOMResult, ExternalResource[]> {\n  constructor(private readonly tags: Tag[]) {\n    super('page-extractor');\n  }\n  async extract(value: DOMResult): Promise<ExternalResource[]> {\n    const { document } = value.window;\n    return this.tags.flatMap((tag) =>\n      Array.from(document.querySelectorAll<Resource>(tag)).flatMap((element) => {\n        const link = findResourceLink(element);\n        if (!link) return [];\n        const text = findResourceText(element) ?? { key: 'src' as const, value: link.value };\n        return [{ text, link }];\n      })\n    );\n  }\n}\n", "import { parseHTML } from 'linkedom';\n\ntype ParseHTMLResult = {\n  document: Document;\n};\n\nexport interface DOMResult {\n  window: { document: Document };\n  url: string;\n}\n\ninterface PageResponse {\n  url: string;\n  content?: DOMResult;\n  error?: string;\n}\n\nexport class PageFetcher {\n  private readonly timeout: number;\n  private readonly maxRetries: number;\n\n  constructor(timeout = 10000, maxRetries = 2) {\n    this.timeout = timeout;\n    this.maxRetries = maxRetries;\n  }\n\n  private buildDOMResult(html: string, url: string): DOMResult {\n    const { document } = parseHTML(html) as ParseHTMLResult;\n    return { window: { document }, url };\n  }\n\n  private decodeHtml(buffer: ArrayBuffer, charset: string): string {\n    try {\n      return new TextDecoder(charset).decode(new Uint8Array(buffer));\n    } catch {\n      return new TextDecoder('utf-8').decode(new Uint8Array(buffer));\n    }\n  }\n\n  private async fetchPage(url: string, retryCount = 0): Promise<PageResponse> {\n    const controller = new AbortController();\n    let timeoutId: ReturnType<typeof setTimeout> | null = null;\n\n    try {\n      if (this.timeout > 0) {\n        timeoutId = setTimeout(() => {\n          controller.abort(new Error('Request timeout'));\n        }, this.timeout);\n      }\n\n      const content = await fetch(url, { signal: controller.signal }).then(async (response) => {\n        const buffer = await response.arrayBuffer();\n        const contentType = response.headers.get('content-type') ?? '';\n        const charsetMatch = /charset=([^\\s;]+)/i.exec(contentType);\n        const html = this.decodeHtml(buffer, charsetMatch?.[1] ?? 'utf-8');\n        return this.buildDOMResult(html, url);\n      });\n\n      return { url, content };\n    } catch (error) {\n      const abortTimeout = error instanceof Error && error.name === 'AbortError';\n      const message = abortTimeout\n        ? 'Request timeout'\n        : error instanceof Error\n          ? error.message\n          : 'Unknown error';\n\n      // Retry logic for transient errors\n      if (retryCount < this.maxRetries && this.isRetryableError(message)) {\n        process.stderr.write(`Retrying ${url} (attempt ${retryCount + 1}/${this.maxRetries})...\\n`);\n        await this.delay(1000 * (retryCount + 1)); // Exponential backoff\n        return this.fetchPage(url, retryCount + 1);\n      }\n\n      return { url, error: `Failed to fetch: ${message}` };\n    } finally {\n      if (timeoutId !== null) {\n        clearTimeout(timeoutId);\n      }\n    }\n  }\n\n  private isRetryableError(message: string): boolean {\n    const retryablePatterns = [/timeout/i, /ECONNRESET/i, /ETIMEDOUT/i, /ENOTFOUND/i, /network/i];\n    return retryablePatterns.some((pattern) => pattern.test(message));\n  }\n\n  private delay(ms: number): Promise<void> {\n    return new Promise((resolve) => setTimeout(resolve, ms));\n  }\n\n  async fetchAll(urls: string[]): Promise<PageResponse[]> {\n    const responses = await Promise.all(urls.map((url) => this.fetchPage(url)));\n    return responses.filter((response) => response.content !== undefined || response.error);\n  }\n}\n", "import { readFile } from 'node:fs/promises';\nimport { parseHTML } from 'linkedom';\n\nimport type { DOMResult } from './PageFetcher.js';\n\nexport const MAX_FILES_FAILSAFE = 254;\n\ntype ParseHTMLResult = {\n  document: Document;\n};\n\nexport interface FileResponse {\n  path: string;\n  content?: DOMResult;\n  error?: string;\n}\n\nexport class FileFetcher {\n  private buildDOMResult(html: string, filePath: string): DOMResult {\n    const { document } = parseHTML(html) as ParseHTMLResult;\n    return { window: { document }, url: `file://${filePath}` };\n  }\n\n  async fetchFile(filePath: string): Promise<FileResponse> {\n    try {\n      // filePath is supplied directly by the CLI user, not derived from network input.\n      // eslint-disable-next-line security/detect-non-literal-fs-filename\n      const html = await readFile(filePath, 'utf-8');\n      return { path: filePath, content: this.buildDOMResult(html, filePath) };\n    } catch (error) {\n      return {\n        path: filePath,\n        error: error instanceof Error ? error.message : 'Unknown error',\n      };\n    }\n  }\n\n  async fetchAll(filePaths: string[]): Promise<FileResponse[]> {\n    return Promise.all(filePaths.map((p) => this.fetchFile(p)));\n  }\n}\n", "import type { PageMetadata } from '../page/index.js';\n\nexport abstract class AbstractResourcePrinter {\n  constructor() {}\n  abstract print(...pages: PageMetadata[]): void | Promise<void>;\n}\n", "import type { PageMetadata } from '../page/index.js';\nimport { AbstractResourcePrinter } from './AbstractResourcePrinter.js';\n\nexport class JSONStylePrinter extends AbstractResourcePrinter {\n  print(...pages: PageMetadata[]): void | Promise<void> {\n    const json = JSON.stringify(pages);\n    process.stdout.write(json + '\\n');\n  }\n}\n", "/**\n * Security utilities for URL validation and sanitization\n */\n\nconst ALLOWED_PROTOCOLS = ['http:', 'https:'];\nconst MAX_URL_LENGTH = 2048;\nconst SUSPICIOUS_PATTERNS = [\n  /javascript:/i,\n  /data:/i,\n  /vbscript:/i,\n  /<script/i,\n  /on\\w+=/i, // Event handlers like onclick=\n];\n\nexport interface ValidationResult {\n  isValid: boolean;\n  error?: string;\n  sanitizedUrl?: string;\n}\n\n/**\n * Validates a URL for security concerns\n * @param url - The URL to validate\n * @returns ValidationResult object with validation status\n */\nexport function validateUrl(url: string): ValidationResult {\n  // Check if URL is empty or whitespace\n  if (!url || !url.trim()) {\n    return {\n      isValid: false,\n      error: 'URL cannot be empty',\n    };\n  }\n\n  const trimmedUrl = url.trim();\n\n  // Check URL length to prevent DoS\n  if (trimmedUrl.length > MAX_URL_LENGTH) {\n    return {\n      isValid: false,\n      error: `URL exceeds maximum length of ${MAX_URL_LENGTH} characters`,\n    };\n  }\n\n  // Check for suspicious patterns\n  for (const pattern of SUSPICIOUS_PATTERNS) {\n    if (pattern.test(trimmedUrl)) {\n      return {\n        isValid: false,\n        error: 'URL contains suspicious patterns',\n      };\n    }\n  }\n\n  // Parse the URL\n  let parsedUrl: URL;\n  try {\n    parsedUrl = new URL(trimmedUrl);\n  } catch {\n    return {\n      isValid: false,\n      error: 'Invalid URL format',\n    };\n  }\n\n  // Check protocol\n  if (!ALLOWED_PROTOCOLS.includes(parsedUrl.protocol)) {\n    return {\n      isValid: false,\n      error: `Protocol ${parsedUrl.protocol} is not allowed. Allowed protocols: ${ALLOWED_PROTOCOLS.join(', ')}`,\n    };\n  }\n\n  // Check for localhost/internal IPs in production (security consideration)\n  const hostname = parsedUrl.hostname.toLowerCase();\n  const isLocalhost =\n    hostname === 'localhost' ||\n    hostname === '127.0.0.1' ||\n    hostname === '::1' ||\n    hostname.startsWith('192.168.') ||\n    hostname.startsWith('10.') ||\n    /^172\\.(1[6-9]|2\\d|3[01])\\./.test(hostname);\n\n  if (isLocalhost) {\n    // Allow but warn about localhost URLs\n    console.warn(`Warning: Accessing local network resource: ${trimmedUrl}`);\n  }\n\n  return {\n    isValid: true,\n    sanitizedUrl: parsedUrl.toString(),\n  };\n}\n\n/**\n * Validates an array of URLs\n * @param urls - Array of URLs to validate\n * @returns Object with valid URLs and errors\n */\nexport function validateUrls(urls: string[]): {\n  validUrls: string[];\n  errors: Array<{ url: string; error: string }>;\n} {\n  const validUrls: string[] = [];\n  const errors: Array<{ url: string; error: string }> = [];\n\n  for (const url of urls) {\n    const result = validateUrl(url);\n    if (result.isValid && result.sanitizedUrl) {\n      validUrls.push(result.sanitizedUrl);\n    } else {\n      errors.push({\n        url,\n        error: result.error || 'Unknown validation error',\n      });\n    }\n  }\n\n  return { validUrls, errors };\n}\n\n/**\n * Rate limiter to prevent abuse\n */\nexport class RateLimiter {\n  private requests: number[] = [];\n  private readonly maxRequests: number;\n  private readonly windowMs: number;\n\n  constructor(maxRequests = 10, windowMs = 60000) {\n    this.maxRequests = maxRequests;\n    this.windowMs = windowMs;\n  }\n\n  /**\n   * Check if a request is allowed under rate limiting\n   * @returns true if request is allowed, false otherwise\n   */\n  public isAllowed(): boolean {\n    const now = Date.now();\n\n    // Remove old requests outside the time window\n    this.requests = this.requests.filter((time) => now - time < this.windowMs);\n\n    if (this.requests.length >= this.maxRequests) {\n      return false;\n    }\n\n    this.requests.push(now);\n    return true;\n  }\n\n  /**\n   * Get remaining requests in current window\n   */\n  public getRemainingRequests(): number {\n    const now = Date.now();\n    this.requests = this.requests.filter((time) => now - time < this.windowMs);\n    return Math.max(0, this.maxRequests - this.requests.length);\n  }\n}\n\n/**\n * Sanitizes HTML content to prevent XSS attacks\n * @param text - Text to sanitize\n * @returns Sanitized text\n */\nexport function sanitizeText(text: string): string {\n  if (!text) return '';\n\n  return text\n    .replace(/</g, '&lt;')\n    .replace(/>/g, '&gt;')\n    .replace(/\"/g, '&quot;')\n    .replace(/'/g, '&#x27;')\n    .replace(/\\//g, '&#x2F;');\n}\n"],
-  "mappings": ";;;AACA,SAAS,SAAS,gBAAgB,cAAc;AAChD,SAAS,qBAAqB;AAC9B,SAAS,eAAe;AACxB,SAAS,qBAAqB;AAC9B,SAAS,oBAAoB;;;ACLtB,IAAe,oBAAf,MAAuC;AAAA,EAC5C,YAAqBA,OAAc;AAAd,gBAAAA;AAAA,EAAe;AAEtC;;;ACCO,IAAM,gBAAN,cAA4B,kBAAmC;AAAA,EACpE,cAAc;AACZ,UAAM,gBAAgB;AAAA,EACxB;AAAA,EAEA,MAAM,QAAQ,OAAiC;AAC7C,UAAM;AAAA,MACJ,QAAQ,EAAE,SAAS;AAAA,MACnB;AAAA,IACF,IAAI;AACJ,WAAO,EAAE,OAAO,SAAS,OAAO,IAAI;AAAA,EACtC;AACF;;;ACNO,IAAM,4BAA4B;AAAA,EACvC;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AACF;AAIO,IAAM,qBAAqB,CAAC,QAAQ,YAAY,UAAU,UAAU,OAAO,KAAK;AAwBvF,IAAM,WAAW,CAAC,SAAmB,QAA0C;AAC7E,QAAM,IAAI,QAAQ,aAAa,GAAG;AAClC,SAAO,KAAK,QAAQ,EAAE,KAAK,MAAM,KAAK,IAAI;AAC5C;AAEO,SAAS,iBAAiB,SAA4C;AAC3E,aAAW,OAAO,2BAA2B;AAC3C,UAAM,QAAQ,SAAS,SAAS,GAAG;AACnC,QAAI,UAAU,OAAW,QAAO,EAAE,KAAK,MAAM;AAAA,EAC/C;AACA,SAAO;AACT;AAEO,SAAS,iBAAiB,SAA6C;AAC5E,aAAW,OAAO,oBAAoB;AACpC,UAAM,QAAQ,SAAS,SAAS,GAAG;AACnC,QAAI,UAAU,OAAW,QAAO,EAAE,KAAK,MAAM;AAAA,EAC/C;AACA,SAAO;AACT;;;ACvDO,IAAM,oBAAN,cAAgC,kBAAiD;AAAA,EACtF,YAA6B,MAAa;AACxC,UAAM,gBAAgB;AADK;AAAA,EAE7B;AAAA,EACA,MAAM,QAAQ,OAA+C;AAC3D,UAAM,EAAE,SAAS,IAAI,MAAM;AAC3B,WAAO,KAAK,KAAK;AAAA,MAAQ,CAAC,QACxB,MAAM,KAAK,SAAS,iBAA2B,GAAG,CAAC,EAAE,QAAQ,CAAC,YAAY;AACxE,cAAM,OAAO,iBAAiB,OAAO;AACrC,YAAI,CAAC,KAAM,QAAO,CAAC;AACnB,cAAM,OAAO,iBAAiB,OAAO,KAAK,EAAE,KAAK,OAAgB,OAAO,KAAK,MAAM;AACnF,eAAO,CAAC,EAAE,MAAM,KAAK,CAAC;AAAA,MACxB,CAAC;AAAA,IACH;AAAA,EACF;AACF;;;ACzBA,SAAS,iBAAiB;AAiBnB,IAAM,cAAN,MAAkB;AAAA,EACN;AAAA,EACA;AAAA,EAEjB,YAAY,UAAU,KAAO,aAAa,GAAG;AAC3C,SAAK,UAAU;AACf,SAAK,aAAa;AAAA,EACpB;AAAA,EAEQ,eAAe,MAAc,KAAwB;AAC3D,UAAM,EAAE,SAAS,IAAI,UAAU,IAAI;AACnC,WAAO,EAAE,QAAQ,EAAE,SAAS,GAAG,IAAI;AAAA,EACrC;AAAA,EAEQ,WAAW,QAAqB,SAAyB;AAC/D,QAAI;AACF,aAAO,IAAI,YAAY,OAAO,EAAE,OAAO,IAAI,WAAW,MAAM,CAAC;AAAA,IAC/D,QAAQ;AACN,aAAO,IAAI,YAAY,OAAO,EAAE,OAAO,IAAI,WAAW,MAAM,CAAC;AAAA,IAC/D;AAAA,EACF;AAAA,EAEA,MAAc,UAAU,KAAa,aAAa,GAA0B;AAC1E,UAAM,aAAa,IAAI,gBAAgB;AACvC,QAAI,YAAkD;AAEtD,QAAI;AACF,UAAI,KAAK,UAAU,GAAG;AACpB,oBAAY,WAAW,MAAM;AAC3B,qBAAW,MAAM,IAAI,MAAM,iBAAiB,CAAC;AAAA,QAC/C,GAAG,KAAK,OAAO;AAAA,MACjB;AAEA,YAAM,UAAU,MAAM,MAAM,KAAK,EAAE,QAAQ,WAAW,OAAO,CAAC,EAAE,KAAK,OAAO,aAAa;AACvF,cAAM,SAAS,MAAM,SAAS,YAAY;AAC1C,cAAM,cAAc,SAAS,QAAQ,IAAI,cAAc,KAAK;AAC5D,cAAM,eAAe,qBAAqB,KAAK,WAAW;AAC1D,cAAM,OAAO,KAAK,WAAW,QAAQ,eAAe,CAAC,KAAK,OAAO;AACjE,eAAO,KAAK,eAAe,MAAM,GAAG;AAAA,MACtC,CAAC;AAED,aAAO,EAAE,KAAK,QAAQ;AAAA,IACxB,SAAS,OAAO;AACd,YAAM,eAAe,iBAAiB,SAAS,MAAM,SAAS;AAC9D,YAAM,UAAU,eACZ,oBACA,iBAAiB,QACf,MAAM,UACN;AAGN,UAAI,aAAa,KAAK,cAAc,KAAK,iBAAiB,OAAO,GAAG;AAClE,gBAAQ,OAAO,MAAM,YAAY,GAAG,aAAa,aAAa,CAAC,IAAI,KAAK,UAAU;AAAA,CAAQ;AAC1F,cAAM,KAAK,MAAM,OAAQ,aAAa,EAAE;AACxC,eAAO,KAAK,UAAU,KAAK,aAAa,CAAC;AAAA,MAC3C;AAEA,aAAO,EAAE,KAAK,OAAO,oBAAoB,OAAO,GAAG;AAAA,IACrD,UAAE;AACA,UAAI,cAAc,MAAM;AACtB,qBAAa,SAAS;AAAA,MACxB;AAAA,IACF;AAAA,EACF;AAAA,EAEQ,iBAAiB,SAA0B;AACjD,UAAM,oBAAoB,CAAC,YAAY,eAAe,cAAc,cAAc,UAAU;AAC5F,WAAO,kBAAkB,KAAK,CAAC,YAAY,QAAQ,KAAK,OAAO,CAAC;AAAA,EAClE;AAAA,EAEQ,MAAM,IAA2B;AACvC,WAAO,IAAI,QAAQ,CAACC,aAAY,WAAWA,UAAS,EAAE,CAAC;AAAA,EACzD;AAAA,EAEA,MAAM,SAAS,MAAyC;AACtD,UAAM,YAAY,MAAM,QAAQ,IAAI,KAAK,IAAI,CAAC,QAAQ,KAAK,UAAU,GAAG,CAAC,CAAC;AAC1E,WAAO,UAAU,OAAO,CAAC,aAAa,SAAS,YAAY,UAAa,SAAS,KAAK;AAAA,EACxF;AACF;;;AC/FA,SAAS,gBAAgB;AACzB,SAAS,aAAAC,kBAAiB;AAInB,IAAM,qBAAqB;AAY3B,IAAM,cAAN,MAAkB;AAAA,EACf,eAAe,MAAc,UAA6B;AAChE,UAAM,EAAE,SAAS,IAAIA,WAAU,IAAI;AACnC,WAAO,EAAE,QAAQ,EAAE,SAAS,GAAG,KAAK,UAAU,QAAQ,GAAG;AAAA,EAC3D;AAAA,EAEA,MAAM,UAAU,UAAyC;AACvD,QAAI;AAGF,YAAM,OAAO,MAAM,SAAS,UAAU,OAAO;AAC7C,aAAO,EAAE,MAAM,UAAU,SAAS,KAAK,eAAe,MAAM,QAAQ,EAAE;AAAA,IACxE,SAAS,OAAO;AACd,aAAO;AAAA,QACL,MAAM;AAAA,QACN,OAAO,iBAAiB,QAAQ,MAAM,UAAU;AAAA,MAClD;AAAA,IACF;AAAA,EACF;AAAA,EAEA,MAAM,SAAS,WAA8C;AAC3D,WAAO,QAAQ,IAAI,UAAU,IAAI,CAAC,MAAM,KAAK,UAAU,CAAC,CAAC,CAAC;AAAA,EAC5D;AACF;;;ACtCO,IAAe,0BAAf,MAAuC;AAAA,EAC5C,cAAc;AAAA,EAAC;AAEjB;;;ACFO,IAAM,mBAAN,cAA+B,wBAAwB;AAAA,EAC5D,SAAS,OAA6C;AACpD,UAAM,OAAO,KAAK,UAAU,KAAK;AACjC,YAAQ,OAAO,MAAM,OAAO,IAAI;AAAA,EAClC;AACF;;;ACJA,IAAM,oBAAoB,CAAC,SAAS,QAAQ;AAC5C,IAAM,iBAAiB;AACvB,IAAM,sBAAsB;AAAA,EAC1B;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA;AACF;AAaO,SAAS,YAAY,KAA+B;AAEzD,MAAI,CAAC,OAAO,CAAC,IAAI,KAAK,GAAG;AACvB,WAAO;AAAA,MACL,SAAS;AAAA,MACT,OAAO;AAAA,IACT;AAAA,EACF;AAEA,QAAM,aAAa,IAAI,KAAK;AAG5B,MAAI,WAAW,SAAS,gBAAgB;AACtC,WAAO;AAAA,MACL,SAAS;AAAA,MACT,OAAO,iCAAiC,cAAc;AAAA,IACxD;AAAA,EACF;AAGA,aAAW,WAAW,qBAAqB;AACzC,QAAI,QAAQ,KAAK,UAAU,GAAG;AAC5B,aAAO;AAAA,QACL,SAAS;AAAA,QACT,OAAO;AAAA,MACT;AAAA,IACF;AAAA,EACF;AAGA,MAAI;AACJ,MAAI;AACF,gBAAY,IAAI,IAAI,UAAU;AAAA,EAChC,QAAQ;AACN,WAAO;AAAA,MACL,SAAS;AAAA,MACT,OAAO;AAAA,IACT;AAAA,EACF;AAGA,MAAI,CAAC,kBAAkB,SAAS,UAAU,QAAQ,GAAG;AACnD,WAAO;AAAA,MACL,SAAS;AAAA,MACT,OAAO,YAAY,UAAU,QAAQ,uCAAuC,kBAAkB,KAAK,IAAI,CAAC;AAAA,IAC1G;AAAA,EACF;AAGA,QAAM,WAAW,UAAU,SAAS,YAAY;AAChD,QAAM,cACJ,aAAa,eACb,aAAa,eACb,aAAa,SACb,SAAS,WAAW,UAAU,KAC9B,SAAS,WAAW,KAAK,KACzB,6BAA6B,KAAK,QAAQ;AAE5C,MAAI,aAAa;AAEf,YAAQ,KAAK,8CAA8C,UAAU,EAAE;AAAA,EACzE;AAEA,SAAO;AAAA,IACL,SAAS;AAAA,IACT,cAAc,UAAU,SAAS;AAAA,EACnC;AACF;AAOO,SAAS,aAAa,MAG3B;AACA,QAAM,YAAsB,CAAC;AAC7B,QAAM,SAAgD,CAAC;AAEvD,aAAW,OAAO,MAAM;AACtB,UAAM,SAAS,YAAY,GAAG;AAC9B,QAAI,OAAO,WAAW,OAAO,cAAc;AACzC,gBAAU,KAAK,OAAO,YAAY;AAAA,IACpC,OAAO;AACL,aAAO,KAAK;AAAA,QACV;AAAA,QACA,OAAO,OAAO,SAAS;AAAA,MACzB,CAAC;AAAA,IACH;AAAA,EACF;AAEA,SAAO,EAAE,WAAW,OAAO;AAC7B;;;AT3GA,IAAMC,WAAU,cAAc,YAAY,GAAG;AAC7C,IAAM,MAAMA,SAAQ,iBAAiB;AAMrC,IAAM,EAAE,aAAa,MAAM,QAAQ,IAAI;AAEvC,IAAM,UAAU,IAAI,QAAQ;AAE5B,IAAM,SAAS,eAAe,YAAY,oCAAoC;AAC9E,IAAM,UAAU,eAAe,cAAc,kCAAkC;AAG/E,IAAM,gBAAgB,IAAI,cAAc;AACxC,IAAM,oBAAoB,IAAI,kBAAkB,CAAC,KAAK,QAAQ,QAAQ,SAAS,QAAQ,CAAC;AACxF,IAAM,UAAU,IAAI,iBAAiB;AAErC,eAAe,kBACb,WAMyB;AACzB,QAAM,gBAAgC,CAAC;AAEvC,aAAW,EAAE,SAAS,KAAK,aAAa,MAAM,MAAM,KAAK,WAAW;AAClE,UAAM,cAAc,eAAe,QAAQ;AAC3C,UAAM,YACJ,UAAU,UAAa,CAAC,UAAU,CAAC,IAAI,MAAM,kBAAkB,QAAQ,OAAO;AAChF,UAAM,aACJ,UAAU,UAAa,CAAC,UACpB,EAAE,KAAK,aAAa,OAAO,SAAS,iBAAiB,UAAU,IAC/D,MAAM,cAAc,QAAQ,OAAO;AACzC,kBAAc,KAAK,EAAE,GAAG,YAAY,UAAU,CAAC;AAAA,EACjD;AAEA,SAAO;AACT;AAEA,SAAS,kBAA2B;AAClC,QAAM,cAAc,QAAQ,KAAK,CAAC;AAClC,MAAI,CAAC,aAAa;AAChB,WAAO;AAAA,EACT;AAEA,MAAI;AACF,WAAO,aAAa,cAAc,YAAY,GAAG,CAAC,MAAM,aAAa,QAAQ,WAAW,CAAC;AAAA,EAC3F,QAAQ;AACN,WAAO;AAAA,EACT;AACF;AAEA,eAAsB,OAAO,OAAiB,QAAQ,MAAqB;AACzE,UAAQ,KAAK,IAAI,EAAE,QAAQ,SAAS,eAAe,EAAE,YAAY,WAAW;AAG5E,UACG,QAAQ,SAAS,EAAE,WAAW,KAAK,CAAC,EACpC,YAAY,gDAAgD,EAC5D,YAAY,MAAM,EAClB;AAAA,IACC,IAAI;AAAA,MACF;AAAA,MACA;AAAA,IACF;AAAA,EACF,EACC,OAAO,OAAO,MAAgB,YAAgC;AAC7D,QAAI;AACF,YAAM,EAAE,WAAW,OAAO,IAAI,aAAa,IAAI;AAE/C,UAAI,OAAO,SAAS,GAAG;AACrB,gBAAQ,MAAM,iCAA4B;AAC1C,eAAO,QAAQ,CAAC,EAAE,KAAK,YAAY,MAAM,MAAM;AAC7C,kBAAQ,MAAM,OAAO,UAAU,KAAK,KAAK,EAAE;AAAA,QAC7C,CAAC;AAAA,MACH;AAEA,UAAI,UAAU,WAAW,GAAG;AAC1B,gBAAQ,MAAM,6CAAwC;AACtD,gBAAQ,KAAK,CAAC;AAAA,MAChB;AAEA,cAAQ,MAAM;AAAA,oBAAkB,UAAU,MAAM,kBAAkB;AAElE,YAAM,cAAc,IAAI,YAAY,QAAQ,QAAQ,IAAI,KAAO,CAAC;AAEhE,YAAM,UAAU,YAA2B;AACzC,cAAM,YAAY,MAAM,YAAY,SAAS,SAAS;AACtD,cAAM,gBAAgB,MAAM,kBAAkB,SAAS;AACvD,cAAM,QAAQ,MAAM,GAAG,aAAa;AAAA,MACtC;AAEA,UAAI,QAAQ,OAAO;AACjB,gBAAQ,MAAM,OAAO;AACrB,gBAAQ,GAAG,UAAU,MAAM,QAAQ,KAAK,CAAC,CAAC;AAE1C,YAAI,kBAAwC;AAC5C,gBAAQ,MAAM,GAAG,OAAO,MAAM;AAC5B,4BAAkB;AAAA,QACpB,CAAC;AAED,YAAI,aAAmD;AACvD,gBAAQ,GAAG,YAAY,MAAM;AAC3B,cAAI,eAAe,KAAM,cAAa,UAAU;AAChD,uBAAa,WAAW,MAAM;AAC5B,yBAAa;AACb,8BAAkB,QAAQ,EAAE,MAAM,CAAC,QAAiB;AAClD,sBAAQ,MAAM,+BAA0B,eAAe,QAAQ,IAAI,UAAU,GAAG;AAAA,YAClF,CAAC;AAAA,UACH,GAAG,GAAG;AAAA,QACR,CAAC;AAED,0BAAkB,QAAQ;AAC1B,cAAM;AAAA,MACR,OAAO;AACL,cAAM,QAAQ;AAAA,MAChB;AAAA,IACF,SAAS,OAAO;AACd,cAAQ,MAAM,+BAA0B,iBAAiB,QAAQ,MAAM,UAAU,KAAK;AACtF,cAAQ,KAAK,CAAC;AAAA,IAChB;AAAA,EACF,CAAC;AAGH,UACG,QAAQ,MAAM,EACd,YAAY,mEAAmE,EAC/E,YAAY,OAAO,EACnB;AAAA,IACC,IAAI,OAAO,iBAAiB,cAAc,kBAAkB,0BAA0B;AAAA,EACxF,EACC,OAAO,OAAO,OAAiB,YAAmC;AACjE,QAAI;AACF,UAAI,QAAQ,YAAY,MAAM,SAAS,oBAAoB;AACzD,gBAAQ;AAAA,UACN;AAAA,SAAO,MAAM,MAAM,gDAAgD,kBAAkB;AAAA,QACvF;AACA,gBAAQ,MAAM,mEAAmE;AACjF,gBAAQ,KAAK,CAAC;AAAA,MAChB;AAEA,UAAI,CAAC,QAAQ,YAAY,MAAM,SAAS,oBAAoB;AAC1D,gBAAQ;AAAA,UACN;AAAA,8CAAuC,MAAM,MAAM,oBAAoB,kBAAkB;AAAA,QAC3F;AAAA,MACF;AAEA,cAAQ,MAAM;AAAA,oBAAkB,MAAM,MAAM,aAAa;AAEzD,YAAM,cAAc,IAAI,YAAY;AACpC,YAAM,YAAY,MAAM,YAAY,SAAS,KAAK;AAClD,YAAM,gBAAgB,MAAM;AAAA,QAC1B,UAAU,IAAI,CAAC,EAAE,MAAM,SAAS,MAAM,OAAO,EAAE,MAAM,SAAS,MAAM,EAAE;AAAA,MACxE;AAEA,YAAM,QAAQ,MAAM,GAAG,aAAa;AAAA,IACtC,SAAS,OAAO;AACd,cAAQ,MAAM,+BAA0B,iBAAiB,QAAQ,MAAM,UAAU,KAAK;AACtF,cAAQ,KAAK,CAAC;AAAA,IAChB;AAAA,EACF,CAAC;AAEH,QAAM,QAAQ,WAAW,IAAI;AAC/B;AAEA,IAAI,gBAAgB,GAAG;AACrB,SAAO,EAAE,MAAM,CAAC,UAAmB;AACjC,YAAQ,MAAM,+BAA0B,iBAAiB,QAAQ,MAAM,UAAU,KAAK;AACtF,YAAQ,KAAK,CAAC;AAAA,EAChB,CAAC;AACH;",
+  "sourcesContent": ["#!/usr/bin/env node\nimport { Command, createArgument, Option } from 'commander';\nimport { createRequire } from 'node:module';\nimport { resolve } from 'node:path';\nimport { fileURLToPath } from 'node:url';\nimport { realpathSync } from 'node:fs';\n\nimport { PageExtractor, ResourceExtractor } from './extractors/index.js';\nimport { FileFetcher, MAX_FILES_FAILSAFE, PageFetcher, type PageMetadata } from './page/index.js';\nimport { JSONStylePrinter } from './printers/index.js';\nimport { validateUrls } from './security.js';\n\nconst require = createRequire(import.meta.url);\nconst pkg = require('../package.json') as {\n  description: string;\n  name: string;\n  version: string;\n};\n\nconst { description, name, version } = pkg;\n\nconst program = new Command();\n\nconst urlArg = createArgument('<url...>', 'remote https://URL to extract from');\nconst fileArg = createArgument('<paths...>', 'local file paths to extract from');\n\n// Shared extractor instances.\nconst pageExtractor = new PageExtractor();\nconst resourceExtractor = new ResourceExtractor(['a', 'meta', 'link', 'embed', 'script']);\nconst printer = new JSONStylePrinter();\n\nasync function buildPageMetadata(\n  responses: Array<{\n    url?: string;\n    path?: string;\n    content?: import('./page/index.js').DOMResult;\n    error?: string;\n  }>\n): Promise<PageMetadata[]> {\n  const pageMetadatas: PageMetadata[] = [];\n\n  for (const { content, url: responseUrl, path, error } of responses) {\n    const resolvedUrl = responseUrl ?? path ?? '';\n    const resources =\n      error !== undefined || !content ? [] : await resourceExtractor.extract(content);\n    const descriptor =\n      error !== undefined || !content\n        ? { url: resolvedUrl, error: error ?? 'Unknown error', resources }\n        : await pageExtractor.extract(content);\n    pageMetadatas.push({ ...descriptor, resources });\n  }\n\n  return pageMetadatas;\n}\n\nfunction normalizeLocalPath(value: string): string {\n  if (value.startsWith('file://')) {\n    return fileURLToPath(value);\n  }\n\n  return value;\n}\n\nasync function runFileCommand(paths: string[], options: { failsafe: boolean }): Promise<void> {\n  if (options.failsafe && paths.length > MAX_FILES_FAILSAFE) {\n    console.error(\n      `\\n\u274C ${paths.length} files specified exceeds the safety limit of ${MAX_FILES_FAILSAFE}.`\n    );\n    console.error(`   Pass --no-failsafe to bypass this check and process all files.`);\n    process.exit(1);\n  }\n\n  if (!options.failsafe && paths.length > MAX_FILES_FAILSAFE) {\n    console.error(\n      `\\n\u26A0\uFE0F  Failsafe bypassed: processing ${paths.length} files (limit is ${MAX_FILES_FAILSAFE}).`\n    );\n  }\n\n  console.error(`\\n\u2705 Processing ${paths.length} file(s)...`);\n\n  const fileFetcher = new FileFetcher();\n  const normalizedPaths = paths.map((pathValue) => normalizeLocalPath(pathValue));\n  const responses = await fileFetcher.fetchAll(normalizedPaths);\n  const pageMetadatas = await buildPageMetadata(\n    responses.map(({ path, content, error }) => ({ path, content, error }))\n  );\n\n  await printer.print(...pageMetadatas);\n}\n\nfunction isCliEntrypoint(): boolean {\n  const invokedPath = process.argv[1];\n  if (!invokedPath) {\n    return false;\n  }\n\n  try {\n    return realpathSync(fileURLToPath(import.meta.url)) === realpathSync(resolve(invokedPath));\n  } catch {\n    return false;\n  }\n}\n\nexport async function runCli(argv: string[] = process.argv): Promise<void> {\n  program.name(name).version(version, '-v, --version').description(description);\n\n  program\n    .addArgument(fileArg)\n    .addOption(\n      new Option('--no-failsafe', `bypass the ${MAX_FILES_FAILSAFE}-file limit safety check`)\n    )\n    .action(async (paths: string[], options: { failsafe: boolean }) => {\n      try {\n        await runFileCommand(paths, options);\n      } catch (error) {\n        console.error('\\n\u274C An error occurred:', error instanceof Error ? error.message : error);\n        process.exit(1);\n      }\n    });\n\n  // \u2500\u2500 fetch subcommand (remote URL mode only) \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\n  program\n    .command('fetch')\n    .description('fetch and extract resources from remote URL(s)')\n    .addArgument(urlArg)\n    .addOption(\n      new Option(\n        '--watch',\n        'keep running: SIGWINCH re-fetches after resize, Ctrl-D releases in-flight requests, Ctrl-C exits'\n      )\n    )\n    .addOption(new Option('-A, --user-agent <value>', 'override the HTTP User-Agent header'))\n    .addOption(\n      new Option(\n        '--allow-private-hosts',\n        'allow localhost/private-network targets (disabled by default for SSRF safety)'\n      )\n    )\n    .action(\n      async (\n        urls: string[],\n        options: { watch: boolean; userAgent?: string; allowPrivateHosts: boolean }\n      ) => {\n        try {\n          const { validUrls, errors } = validateUrls(urls, {\n            allowPrivateHosts: options.allowPrivateHosts,\n          });\n\n          if (errors.length > 0) {\n            console.error('\\n\u274C URL Validation Errors:');\n            errors.forEach(({ url: invalidUrl, error }) => {\n              console.error(`  - ${invalidUrl}: ${error}`);\n            });\n          }\n\n          if (validUrls.length === 0) {\n            console.error('\\n\u274C No valid URLs to process. Exiting.');\n            process.exit(1);\n          }\n\n          console.error(`\\n\u2705 Processing ${validUrls.length} valid URL(s)...`);\n\n          const pageFetcher = new PageFetcher(options.watch ? 0 : 10000, 2, options.userAgent);\n\n          const execute = async (): Promise<void> => {\n            const responses = await pageFetcher.fetchAll(validUrls);\n            const pageMetadatas = await buildPageMetadata(responses);\n            await printer.print(...pageMetadatas);\n          };\n\n          if (options.watch) {\n            process.stdin.resume();\n            process.on('SIGINT', () => process.exit(0));\n\n            let activeExecution: Promise<void> | null = null;\n            process.stdin.on('end', () => {\n              activeExecution = null;\n            });\n\n            let winchTimer: ReturnType<typeof setTimeout> | null = null;\n            process.on('SIGWINCH', () => {\n              if (winchTimer !== null) clearTimeout(winchTimer);\n              winchTimer = setTimeout(() => {\n                winchTimer = null;\n                activeExecution = execute().catch((err: unknown) => {\n                  console.error(\n                    '\\n\u274C An error occurred:',\n                    err instanceof Error ? err.message : err\n                  );\n                });\n              }, 150);\n            });\n\n            activeExecution = execute();\n            await activeExecution;\n          } else {\n            await execute();\n          }\n        } catch (error) {\n          console.error('\\n\u274C An error occurred:', error instanceof Error ? error.message : error);\n          process.exit(1);\n        }\n      }\n    );\n\n  // \u2500\u2500 file subcommand (local filesystem access) \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\n  program\n    .command('file')\n    .description('extract resources from local file(s) via direct filesystem access')\n    .addArgument(fileArg)\n    .addOption(\n      new Option('--no-failsafe', `bypass the ${MAX_FILES_FAILSAFE}-file limit safety check`)\n    )\n    .action(async (paths: string[], options: { failsafe: boolean }) => {\n      try {\n        await runFileCommand(paths, options);\n      } catch (error) {\n        console.error('\\n\u274C An error occurred:', error instanceof Error ? error.message : error);\n        process.exit(1);\n      }\n    });\n\n  await program.parseAsync(argv);\n}\n\nif (isCliEntrypoint()) {\n  runCli().catch((error: unknown) => {\n    console.error('\\n\u274C An error occurred:', error instanceof Error ? error.message : error);\n    process.exit(1);\n  });\n}\n", "export abstract class AbstractExtractor<V, R> {\n  constructor(readonly name: string) {}\n  abstract extract(value: V): Promise<R>;\n}\n", "import type { Page } from '../page/index.js';\nimport type { DOMResult } from '../page/index.js';\nimport { AbstractExtractor } from './AbstractExtractor.js';\n\nexport class PageExtractor extends AbstractExtractor<DOMResult, Page> {\n  constructor() {\n    super('page-extractor');\n  }\n\n  async extract(value: DOMResult): Promise<Page> {\n    const {\n      window: { document },\n      url,\n    } = value;\n    return { title: document.title, url };\n  }\n}\n", "/**\n * @license MIT\n * We are interested in visualising a page as a collection of tags.\n *\n * We wish to work with tags that can be compactly previewed on a webpage.\n * Here we must declare all of the element types that can be used to represent\n * a resource that can be hyperlinked off a webpage.\n */\ntype Tags = HTMLElementTagNameMap;\n\nexport const RESOURCE_DISPLAYABLE_KEYS = [\n  'id',\n  'innerText',\n  'textContent',\n  'class',\n  'ariaLabel',\n  'ariaDescription',\n  'alt',\n] as const;\n\nexport type DisplayableKey = (typeof RESOURCE_DISPLAYABLE_KEYS)[number];\n\nexport const RESOURCE_LINK_KEYS = ['href', 'data-src', 'target', 'action', 'src', 'url'] as const;\n\nexport type LinkKey = (typeof RESOURCE_LINK_KEYS)[number];\n\nexport type AttributeKey = DisplayableKey | LinkKey;\n\nexport type ResourceKey = { key: AttributeKey; value: string };\nexport type ResourceLink = { key: LinkKey; value: string };\n\nexport type ExternalResource = {\n  text: ResourceKey;\n  link: ResourceLink;\n};\n\nexport type Tag = keyof Tags;\n\nexport type Resource = HTMLElement & {\n  [K in AttributeKey]?: string | null;\n};\n\nexport type ResourceByName<T extends keyof Tags> = Tags[T];\n\n// --- adapters ---\n\nconst readAttr = (element: Resource, key: AttributeKey): string | undefined => {\n  const v = element.getAttribute(key);\n  return v != null && v.trim() !== '' ? v : undefined;\n};\n\nexport function findResourceText(element: Resource): ResourceKey | undefined {\n  for (const key of RESOURCE_DISPLAYABLE_KEYS) {\n    const value = readAttr(element, key);\n    if (value !== undefined) return { key, value };\n  }\n  return undefined;\n}\n\nexport function findResourceLink(element: Resource): ResourceLink | undefined {\n  for (const key of RESOURCE_LINK_KEYS) {\n    const value = readAttr(element, key);\n    if (value !== undefined) return { key, value };\n  }\n  return undefined;\n}\n\nexport const isResourceKey = (key: string): key is AttributeKey =>\n  (RESOURCE_DISPLAYABLE_KEYS as readonly string[]).includes(key) ||\n  (RESOURCE_LINK_KEYS as readonly string[]).includes(key);\n", "import type { DOMResult } from '../page/index.js';\nimport {\n  findResourceLink,\n  findResourceText,\n  type ExternalResource,\n  type Resource,\n  type Tag,\n} from '../resource.js';\nimport { AbstractExtractor } from './AbstractExtractor.js';\n\nexport class ResourceExtractor extends AbstractExtractor<DOMResult, ExternalResource[]> {\n  constructor(private readonly tags: Tag[]) {\n    super('page-extractor');\n  }\n  async extract(value: DOMResult): Promise<ExternalResource[]> {\n    const { document } = value.window;\n    return this.tags.flatMap((tag) =>\n      Array.from(document.querySelectorAll<Resource>(tag)).flatMap((element) => {\n        const link = findResourceLink(element);\n        if (!link) return [];\n        const text = findResourceText(element) ?? { key: 'src' as const, value: link.value };\n        return [{ text, link }];\n      })\n    );\n  }\n}\n", "import { parseHTML } from 'linkedom';\n\nconst MAX_HTML_BYTES = 2 * 1024 * 1024;\nconst ALLOWED_CONTENT_TYPES = ['text/html', 'application/xhtml+xml'];\n\ntype ParseHTMLResult = {\n  document: Document;\n};\n\nexport interface DOMResult {\n  window: { document: Document };\n  url: string;\n}\n\ninterface PageResponse {\n  url: string;\n  content?: DOMResult;\n  error?: string;\n}\n\nexport class PageFetcher {\n  private readonly timeout: number;\n  private readonly maxRetries: number;\n  private readonly userAgent?: string;\n\n  constructor(timeout = 10000, maxRetries = 2, userAgent?: string) {\n    this.timeout = timeout;\n    this.maxRetries = maxRetries;\n    this.userAgent = userAgent;\n  }\n\n  private buildDOMResult(html: string, url: string): DOMResult {\n    const { document } = parseHTML(html) as ParseHTMLResult;\n    return { window: { document }, url };\n  }\n\n  private decodeHtml(buffer: ArrayBuffer, charset: string): string {\n    try {\n      return new TextDecoder(charset).decode(new Uint8Array(buffer));\n    } catch {\n      return new TextDecoder('utf-8').decode(new Uint8Array(buffer));\n    }\n  }\n\n  private async fetchPage(url: string, retryCount = 0): Promise<PageResponse> {\n    const controller = new AbortController();\n    let timeoutId: ReturnType<typeof setTimeout> | null = null;\n\n    try {\n      if (this.timeout > 0) {\n        timeoutId = setTimeout(() => {\n          controller.abort(new Error('Request timeout'));\n        }, this.timeout);\n      }\n\n      const headers = this.userAgent ? { 'user-agent': this.userAgent } : undefined;\n      const content = await fetch(url, { headers, signal: controller.signal }).then(\n        async (response) => {\n          if (!response.ok) {\n            throw new Error(`HTTP ${response.status} ${response.statusText}`.trim());\n          }\n\n          const contentType = (response.headers.get('content-type') ?? '').toLowerCase();\n          const isAllowedContentType = ALLOWED_CONTENT_TYPES.some((allowedType) =>\n            contentType.includes(allowedType)\n          );\n          if (!isAllowedContentType) {\n            throw new Error(`Unsupported content type: ${contentType || 'unknown'}`);\n          }\n\n          const contentLengthHeader = response.headers.get('content-length');\n          const contentLength = contentLengthHeader ? Number(contentLengthHeader) : Number.NaN;\n          if (Number.isFinite(contentLength) && contentLength > MAX_HTML_BYTES) {\n            throw new Error(`Response exceeds max allowed size (${MAX_HTML_BYTES} bytes)`);\n          }\n\n          const buffer = await response.arrayBuffer();\n          if (buffer.byteLength > MAX_HTML_BYTES) {\n            throw new Error(`Response exceeds max allowed size (${MAX_HTML_BYTES} bytes)`);\n          }\n\n          const charsetMatch = /charset=([^\\s;]+)/i.exec(contentType);\n          const html = this.decodeHtml(buffer, charsetMatch?.[1] ?? 'utf-8');\n          return this.buildDOMResult(html, url);\n        }\n      );\n\n      return { url, content };\n    } catch (error) {\n      const abortTimeout = error instanceof Error && error.name === 'AbortError';\n      const message = abortTimeout\n        ? 'Request timeout'\n        : error instanceof Error\n          ? error.message\n          : 'Unknown error';\n\n      // Retry logic for transient errors\n      if (retryCount < this.maxRetries && this.isRetryableError(message)) {\n        process.stderr.write(`Retrying ${url} (attempt ${retryCount + 1}/${this.maxRetries})...\\n`);\n        await this.delay(1000 * (retryCount + 1)); // Exponential backoff\n        return this.fetchPage(url, retryCount + 1);\n      }\n\n      return { url, error: `Failed to fetch: ${message}` };\n    } finally {\n      if (timeoutId !== null) {\n        clearTimeout(timeoutId);\n      }\n    }\n  }\n\n  private isRetryableError(message: string): boolean {\n    const retryablePatterns = [/timeout/i, /ECONNRESET/i, /ETIMEDOUT/i, /ENOTFOUND/i, /network/i];\n    return retryablePatterns.some((pattern) => pattern.test(message));\n  }\n\n  private delay(ms: number): Promise<void> {\n    return new Promise((resolve) => setTimeout(resolve, ms));\n  }\n\n  async fetchAll(urls: string[]): Promise<PageResponse[]> {\n    const responses = await Promise.all(urls.map((url) => this.fetchPage(url)));\n    return responses.filter((response) => response.content !== undefined || response.error);\n  }\n}\n", "import { readFile } from 'node:fs/promises';\nimport { parseHTML } from 'linkedom';\n\nimport type { DOMResult } from './PageFetcher.js';\n\nexport const MAX_FILES_FAILSAFE = 254;\n\ntype ParseHTMLResult = {\n  document: Document;\n};\n\nexport interface FileResponse {\n  path: string;\n  content?: DOMResult;\n  error?: string;\n}\n\nexport class FileFetcher {\n  private buildDOMResult(html: string, filePath: string): DOMResult {\n    const { document } = parseHTML(html) as ParseHTMLResult;\n    return { window: { document }, url: `file://${filePath}` };\n  }\n\n  async fetchFile(filePath: string): Promise<FileResponse> {\n    try {\n      // filePath is supplied directly by the CLI user, not derived from network input.\n      // eslint-disable-next-line security/detect-non-literal-fs-filename\n      const html = await readFile(filePath, 'utf-8');\n      return { path: filePath, content: this.buildDOMResult(html, filePath) };\n    } catch (error) {\n      return {\n        path: filePath,\n        error: error instanceof Error ? error.message : 'Unknown error',\n      };\n    }\n  }\n\n  async fetchAll(filePaths: string[]): Promise<FileResponse[]> {\n    return Promise.all(filePaths.map((p) => this.fetchFile(p)));\n  }\n}\n", "import type { PageMetadata } from '../page/index.js';\n\nexport abstract class AbstractResourcePrinter {\n  constructor() {}\n  abstract print(...pages: PageMetadata[]): void | Promise<void>;\n}\n", "import type { PageMetadata } from '../page/index.js';\nimport { AbstractResourcePrinter } from './AbstractResourcePrinter.js';\n\nexport class JSONStylePrinter extends AbstractResourcePrinter {\n  print(...pages: PageMetadata[]): void | Promise<void> {\n    const json = JSON.stringify(pages);\n    process.stdout.write(json + '\\n');\n  }\n}\n", "/**\n * Security utilities for URL validation and sanitization\n */\n\nimport { isIP } from 'node:net';\n\nconst ALLOWED_PROTOCOLS = ['http:', 'https:'];\nconst MAX_URL_LENGTH = 2048;\nconst SUSPICIOUS_PATTERNS = [\n  /javascript:/i,\n  /data:/i,\n  /vbscript:/i,\n  /<script/i,\n  /on\\w+=/i, // Event handlers like onclick=\n];\n\nexport interface ValidationResult {\n  isValid: boolean;\n  error?: string;\n  sanitizedUrl?: string;\n}\n\nexport interface UrlValidationOptions {\n  allowPrivateHosts?: boolean;\n}\n\nfunction isPrivateHostname(hostname: string): boolean {\n  const normalized = hostname.toLowerCase();\n\n  if (normalized === 'localhost' || normalized.endsWith('.localhost')) {\n    return true;\n  }\n\n  const ipType = isIP(normalized);\n  if (ipType === 0) {\n    return false;\n  }\n\n  if (ipType === 4) {\n    const octets = normalized.split('.').map(Number);\n    if (octets.length !== 4 || octets.some((octet) => Number.isNaN(octet))) {\n      return false;\n    }\n\n    const [a, b] = octets;\n    return (\n      a === 10 ||\n      a === 127 ||\n      (a === 169 && b === 254) ||\n      (a === 172 && b >= 16 && b <= 31) ||\n      (a === 192 && b === 168) ||\n      a === 0\n    );\n  }\n\n  // IPv6 private/internal ranges.\n  return (\n    normalized === '::1' ||\n    normalized === '::' ||\n    normalized.startsWith('fc') ||\n    normalized.startsWith('fd') ||\n    normalized.startsWith('fe8') ||\n    normalized.startsWith('fe9') ||\n    normalized.startsWith('fea') ||\n    normalized.startsWith('feb')\n  );\n}\n\n/**\n * Validates a URL for security concerns\n * @param url - The URL to validate\n * @returns ValidationResult object with validation status\n */\nexport function validateUrl(url: string, options: UrlValidationOptions = {}): ValidationResult {\n  // Check if URL is empty or whitespace\n  if (!url || !url.trim()) {\n    return {\n      isValid: false,\n      error: 'URL cannot be empty',\n    };\n  }\n\n  const trimmedUrl = url.trim();\n\n  // Check URL length to prevent DoS\n  if (trimmedUrl.length > MAX_URL_LENGTH) {\n    return {\n      isValid: false,\n      error: `URL exceeds maximum length of ${MAX_URL_LENGTH} characters`,\n    };\n  }\n\n  // Check for suspicious patterns\n  for (const pattern of SUSPICIOUS_PATTERNS) {\n    if (pattern.test(trimmedUrl)) {\n      return {\n        isValid: false,\n        error: 'URL contains suspicious patterns',\n      };\n    }\n  }\n\n  // Parse the URL\n  let parsedUrl: URL;\n  try {\n    parsedUrl = new URL(trimmedUrl);\n  } catch {\n    return {\n      isValid: false,\n      error: 'Invalid URL format',\n    };\n  }\n\n  // Check protocol\n  if (!ALLOWED_PROTOCOLS.includes(parsedUrl.protocol)) {\n    return {\n      isValid: false,\n      error: `Protocol ${parsedUrl.protocol} is not allowed. Allowed protocols: ${ALLOWED_PROTOCOLS.join(', ')}`,\n    };\n  }\n\n  if (parsedUrl.username || parsedUrl.password) {\n    return {\n      isValid: false,\n      error: 'URLs with embedded credentials are not allowed',\n    };\n  }\n\n  if (!options.allowPrivateHosts && isPrivateHostname(parsedUrl.hostname)) {\n    return {\n      isValid: false,\n      error:\n        'Private or loopback hostnames are blocked by default. Use --allow-private-hosts if you trust the target.',\n    };\n  }\n\n  return {\n    isValid: true,\n    sanitizedUrl: parsedUrl.toString(),\n  };\n}\n\n/**\n * Validates an array of URLs\n * @param urls - Array of URLs to validate\n * @returns Object with valid URLs and errors\n */\nexport function validateUrls(\n  urls: string[],\n  options: UrlValidationOptions = {}\n): {\n  validUrls: string[];\n  errors: Array<{ url: string; error: string }>;\n} {\n  const validUrls: string[] = [];\n  const errors: Array<{ url: string; error: string }> = [];\n\n  for (const url of urls) {\n    const result = validateUrl(url, options);\n    if (result.isValid && result.sanitizedUrl) {\n      validUrls.push(result.sanitizedUrl);\n    } else {\n      errors.push({\n        url,\n        error: result.error || 'Unknown validation error',\n      });\n    }\n  }\n\n  return { validUrls, errors };\n}\n\n/**\n * Rate limiter to prevent abuse\n */\nexport class RateLimiter {\n  private requests: number[] = [];\n  private readonly maxRequests: number;\n  private readonly windowMs: number;\n\n  constructor(maxRequests = 10, windowMs = 60000) {\n    this.maxRequests = maxRequests;\n    this.windowMs = windowMs;\n  }\n\n  /**\n   * Check if a request is allowed under rate limiting\n   * @returns true if request is allowed, false otherwise\n   */\n  public isAllowed(): boolean {\n    const now = Date.now();\n\n    // Remove old requests outside the time window\n    this.requests = this.requests.filter((time) => now - time < this.windowMs);\n\n    if (this.requests.length >= this.maxRequests) {\n      return false;\n    }\n\n    this.requests.push(now);\n    return true;\n  }\n\n  /**\n   * Get remaining requests in current window\n   */\n  public getRemainingRequests(): number {\n    const now = Date.now();\n    this.requests = this.requests.filter((time) => now - time < this.windowMs);\n    return Math.max(0, this.maxRequests - this.requests.length);\n  }\n}\n\n/**\n * Sanitizes HTML content to prevent XSS attacks\n * @param text - Text to sanitize\n * @returns Sanitized text\n */\nexport function sanitizeText(text: string): string {\n  if (!text) return '';\n\n  return text\n    .replace(/</g, '&lt;')\n    .replace(/>/g, '&gt;')\n    .replace(/\"/g, '&quot;')\n    .replace(/'/g, '&#x27;')\n    .replace(/\\//g, '&#x2F;');\n}\n"],
+  "mappings": ";;;AACA,SAAS,SAAS,gBAAgB,cAAc;AAChD,SAAS,qBAAqB;AAC9B,SAAS,eAAe;AACxB,SAAS,qBAAqB;AAC9B,SAAS,oBAAoB;;;ACLtB,IAAe,oBAAf,MAAuC;AAAA,EAC5C,YAAqBA,OAAc;AAAd,gBAAAA;AAAA,EAAe;AAAA,EAAf;AAEvB;;;ACCO,IAAM,gBAAN,cAA4B,kBAAmC;AAAA,EACpE,cAAc;AACZ,UAAM,gBAAgB;AAAA,EACxB;AAAA,EAEA,MAAM,QAAQ,OAAiC;AAC7C,UAAM;AAAA,MACJ,QAAQ,EAAE,SAAS;AAAA,MACnB;AAAA,IACF,IAAI;AACJ,WAAO,EAAE,OAAO,SAAS,OAAO,IAAI;AAAA,EACtC;AACF;;;ACNO,IAAM,4BAA4B;AAAA,EACvC;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AACF;AAIO,IAAM,qBAAqB,CAAC,QAAQ,YAAY,UAAU,UAAU,OAAO,KAAK;AAwBvF,IAAM,WAAW,CAAC,SAAmB,QAA0C;AAC7E,QAAM,IAAI,QAAQ,aAAa,GAAG;AAClC,SAAO,KAAK,QAAQ,EAAE,KAAK,MAAM,KAAK,IAAI;AAC5C;AAEO,SAAS,iBAAiB,SAA4C;AAC3E,aAAW,OAAO,2BAA2B;AAC3C,UAAM,QAAQ,SAAS,SAAS,GAAG;AACnC,QAAI,UAAU,OAAW,QAAO,EAAE,KAAK,MAAM;AAAA,EAC/C;AACA,SAAO;AACT;AAEO,SAAS,iBAAiB,SAA6C;AAC5E,aAAW,OAAO,oBAAoB;AACpC,UAAM,QAAQ,SAAS,SAAS,GAAG;AACnC,QAAI,UAAU,OAAW,QAAO,EAAE,KAAK,MAAM;AAAA,EAC/C;AACA,SAAO;AACT;;;ACvDO,IAAM,oBAAN,cAAgC,kBAAiD;AAAA,EACtF,YAA6B,MAAa;AACxC,UAAM,gBAAgB;AADK;AAAA,EAE7B;AAAA,EAF6B;AAAA,EAG7B,MAAM,QAAQ,OAA+C;AAC3D,UAAM,EAAE,SAAS,IAAI,MAAM;AAC3B,WAAO,KAAK,KAAK;AAAA,MAAQ,CAAC,QACxB,MAAM,KAAK,SAAS,iBAA2B,GAAG,CAAC,EAAE,QAAQ,CAAC,YAAY;AACxE,cAAM,OAAO,iBAAiB,OAAO;AACrC,YAAI,CAAC,KAAM,QAAO,CAAC;AACnB,cAAM,OAAO,iBAAiB,OAAO,KAAK,EAAE,KAAK,OAAgB,OAAO,KAAK,MAAM;AACnF,eAAO,CAAC,EAAE,MAAM,KAAK,CAAC;AAAA,MACxB,CAAC;AAAA,IACH;AAAA,EACF;AACF;;;ACzBA,SAAS,iBAAiB;AAE1B,IAAM,iBAAiB,IAAI,OAAO;AAClC,IAAM,wBAAwB,CAAC,aAAa,uBAAuB;AAiB5D,IAAM,cAAN,MAAkB;AAAA,EACN;AAAA,EACA;AAAA,EACA;AAAA,EAEjB,YAAY,UAAU,KAAO,aAAa,GAAG,WAAoB;AAC/D,SAAK,UAAU;AACf,SAAK,aAAa;AAClB,SAAK,YAAY;AAAA,EACnB;AAAA,EAEQ,eAAe,MAAc,KAAwB;AAC3D,UAAM,EAAE,SAAS,IAAI,UAAU,IAAI;AACnC,WAAO,EAAE,QAAQ,EAAE,SAAS,GAAG,IAAI;AAAA,EACrC;AAAA,EAEQ,WAAW,QAAqB,SAAyB;AAC/D,QAAI;AACF,aAAO,IAAI,YAAY,OAAO,EAAE,OAAO,IAAI,WAAW,MAAM,CAAC;AAAA,IAC/D,QAAQ;AACN,aAAO,IAAI,YAAY,OAAO,EAAE,OAAO,IAAI,WAAW,MAAM,CAAC;AAAA,IAC/D;AAAA,EACF;AAAA,EAEA,MAAc,UAAU,KAAa,aAAa,GAA0B;AAC1E,UAAM,aAAa,IAAI,gBAAgB;AACvC,QAAI,YAAkD;AAEtD,QAAI;AACF,UAAI,KAAK,UAAU,GAAG;AACpB,oBAAY,WAAW,MAAM;AAC3B,qBAAW,MAAM,IAAI,MAAM,iBAAiB,CAAC;AAAA,QAC/C,GAAG,KAAK,OAAO;AAAA,MACjB;AAEA,YAAM,UAAU,KAAK,YAAY,EAAE,cAAc,KAAK,UAAU,IAAI;AACpE,YAAM,UAAU,MAAM,MAAM,KAAK,EAAE,SAAS,QAAQ,WAAW,OAAO,CAAC,EAAE;AAAA,QACvE,OAAO,aAAa;AAClB,cAAI,CAAC,SAAS,IAAI;AAChB,kBAAM,IAAI,MAAM,QAAQ,SAAS,MAAM,IAAI,SAAS,UAAU,GAAG,KAAK,CAAC;AAAA,UACzE;AAEA,gBAAM,eAAe,SAAS,QAAQ,IAAI,cAAc,KAAK,IAAI,YAAY;AAC7E,gBAAM,uBAAuB,sBAAsB;AAAA,YAAK,CAAC,gBACvD,YAAY,SAAS,WAAW;AAAA,UAClC;AACA,cAAI,CAAC,sBAAsB;AACzB,kBAAM,IAAI,MAAM,6BAA6B,eAAe,SAAS,EAAE;AAAA,UACzE;AAEA,gBAAM,sBAAsB,SAAS,QAAQ,IAAI,gBAAgB;AACjE,gBAAM,gBAAgB,sBAAsB,OAAO,mBAAmB,IAAI,OAAO;AACjF,cAAI,OAAO,SAAS,aAAa,KAAK,gBAAgB,gBAAgB;AACpE,kBAAM,IAAI,MAAM,sCAAsC,cAAc,SAAS;AAAA,UAC/E;AAEA,gBAAM,SAAS,MAAM,SAAS,YAAY;AAC1C,cAAI,OAAO,aAAa,gBAAgB;AACtC,kBAAM,IAAI,MAAM,sCAAsC,cAAc,SAAS;AAAA,UAC/E;AAEA,gBAAM,eAAe,qBAAqB,KAAK,WAAW;AAC1D,gBAAM,OAAO,KAAK,WAAW,QAAQ,eAAe,CAAC,KAAK,OAAO;AACjE,iBAAO,KAAK,eAAe,MAAM,GAAG;AAAA,QACtC;AAAA,MACF;AAEA,aAAO,EAAE,KAAK,QAAQ;AAAA,IACxB,SAAS,OAAO;AACd,YAAM,eAAe,iBAAiB,SAAS,MAAM,SAAS;AAC9D,YAAM,UAAU,eACZ,oBACA,iBAAiB,QACf,MAAM,UACN;AAGN,UAAI,aAAa,KAAK,cAAc,KAAK,iBAAiB,OAAO,GAAG;AAClE,gBAAQ,OAAO,MAAM,YAAY,GAAG,aAAa,aAAa,CAAC,IAAI,KAAK,UAAU;AAAA,CAAQ;AAC1F,cAAM,KAAK,MAAM,OAAQ,aAAa,EAAE;AACxC,eAAO,KAAK,UAAU,KAAK,aAAa,CAAC;AAAA,MAC3C;AAEA,aAAO,EAAE,KAAK,OAAO,oBAAoB,OAAO,GAAG;AAAA,IACrD,UAAE;AACA,UAAI,cAAc,MAAM;AACtB,qBAAa,SAAS;AAAA,MACxB;AAAA,IACF;AAAA,EACF;AAAA,EAEQ,iBAAiB,SAA0B;AACjD,UAAM,oBAAoB,CAAC,YAAY,eAAe,cAAc,cAAc,UAAU;AAC5F,WAAO,kBAAkB,KAAK,CAAC,YAAY,QAAQ,KAAK,OAAO,CAAC;AAAA,EAClE;AAAA,EAEQ,MAAM,IAA2B;AACvC,WAAO,IAAI,QAAQ,CAACC,aAAY,WAAWA,UAAS,EAAE,CAAC;AAAA,EACzD;AAAA,EAEA,MAAM,SAAS,MAAyC;AACtD,UAAM,YAAY,MAAM,QAAQ,IAAI,KAAK,IAAI,CAAC,QAAQ,KAAK,UAAU,GAAG,CAAC,CAAC;AAC1E,WAAO,UAAU,OAAO,CAAC,aAAa,SAAS,YAAY,UAAa,SAAS,KAAK;AAAA,EACxF;AACF;;;AC5HA,SAAS,gBAAgB;AACzB,SAAS,aAAAC,kBAAiB;AAInB,IAAM,qBAAqB;AAY3B,IAAM,cAAN,MAAkB;AAAA,EACf,eAAe,MAAc,UAA6B;AAChE,UAAM,EAAE,SAAS,IAAIA,WAAU,IAAI;AACnC,WAAO,EAAE,QAAQ,EAAE,SAAS,GAAG,KAAK,UAAU,QAAQ,GAAG;AAAA,EAC3D;AAAA,EAEA,MAAM,UAAU,UAAyC;AACvD,QAAI;AAGF,YAAM,OAAO,MAAM,SAAS,UAAU,OAAO;AAC7C,aAAO,EAAE,MAAM,UAAU,SAAS,KAAK,eAAe,MAAM,QAAQ,EAAE;AAAA,IACxE,SAAS,OAAO;AACd,aAAO;AAAA,QACL,MAAM;AAAA,QACN,OAAO,iBAAiB,QAAQ,MAAM,UAAU;AAAA,MAClD;AAAA,IACF;AAAA,EACF;AAAA,EAEA,MAAM,SAAS,WAA8C;AAC3D,WAAO,QAAQ,IAAI,UAAU,IAAI,CAAC,MAAM,KAAK,UAAU,CAAC,CAAC,CAAC;AAAA,EAC5D;AACF;;;ACtCO,IAAe,0BAAf,MAAuC;AAAA,EAC5C,cAAc;AAAA,EAAC;AAEjB;;;ACFO,IAAM,mBAAN,cAA+B,wBAAwB;AAAA,EAC5D,SAAS,OAA6C;AACpD,UAAM,OAAO,KAAK,UAAU,KAAK;AACjC,YAAQ,OAAO,MAAM,OAAO,IAAI;AAAA,EAClC;AACF;;;ACJA,SAAS,YAAY;AAErB,IAAM,oBAAoB,CAAC,SAAS,QAAQ;AAC5C,IAAM,iBAAiB;AACvB,IAAM,sBAAsB;AAAA,EAC1B;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA;AACF;AAYA,SAAS,kBAAkB,UAA2B;AACpD,QAAM,aAAa,SAAS,YAAY;AAExC,MAAI,eAAe,eAAe,WAAW,SAAS,YAAY,GAAG;AACnE,WAAO;AAAA,EACT;AAEA,QAAM,SAAS,KAAK,UAAU;AAC9B,MAAI,WAAW,GAAG;AAChB,WAAO;AAAA,EACT;AAEA,MAAI,WAAW,GAAG;AAChB,UAAM,SAAS,WAAW,MAAM,GAAG,EAAE,IAAI,MAAM;AAC/C,QAAI,OAAO,WAAW,KAAK,OAAO,KAAK,CAAC,UAAU,OAAO,MAAM,KAAK,CAAC,GAAG;AACtE,aAAO;AAAA,IACT;AAEA,UAAM,CAAC,GAAG,CAAC,IAAI;AACf,WACE,MAAM,MACN,MAAM,OACL,MAAM,OAAO,MAAM,OACnB,MAAM,OAAO,KAAK,MAAM,KAAK,MAC7B,MAAM,OAAO,MAAM,OACpB,MAAM;AAAA,EAEV;AAGA,SACE,eAAe,SACf,eAAe,QACf,WAAW,WAAW,IAAI,KAC1B,WAAW,WAAW,IAAI,KAC1B,WAAW,WAAW,KAAK,KAC3B,WAAW,WAAW,KAAK,KAC3B,WAAW,WAAW,KAAK,KAC3B,WAAW,WAAW,KAAK;AAE/B;AAOO,SAAS,YAAY,KAAa,UAAgC,CAAC,GAAqB;AAE7F,MAAI,CAAC,OAAO,CAAC,IAAI,KAAK,GAAG;AACvB,WAAO;AAAA,MACL,SAAS;AAAA,MACT,OAAO;AAAA,IACT;AAAA,EACF;AAEA,QAAM,aAAa,IAAI,KAAK;AAG5B,MAAI,WAAW,SAAS,gBAAgB;AACtC,WAAO;AAAA,MACL,SAAS;AAAA,MACT,OAAO,iCAAiC,cAAc;AAAA,IACxD;AAAA,EACF;AAGA,aAAW,WAAW,qBAAqB;AACzC,QAAI,QAAQ,KAAK,UAAU,GAAG;AAC5B,aAAO;AAAA,QACL,SAAS;AAAA,QACT,OAAO;AAAA,MACT;AAAA,IACF;AAAA,EACF;AAGA,MAAI;AACJ,MAAI;AACF,gBAAY,IAAI,IAAI,UAAU;AAAA,EAChC,QAAQ;AACN,WAAO;AAAA,MACL,SAAS;AAAA,MACT,OAAO;AAAA,IACT;AAAA,EACF;AAGA,MAAI,CAAC,kBAAkB,SAAS,UAAU,QAAQ,GAAG;AACnD,WAAO;AAAA,MACL,SAAS;AAAA,MACT,OAAO,YAAY,UAAU,QAAQ,uCAAuC,kBAAkB,KAAK,IAAI,CAAC;AAAA,IAC1G;AAAA,EACF;AAEA,MAAI,UAAU,YAAY,UAAU,UAAU;AAC5C,WAAO;AAAA,MACL,SAAS;AAAA,MACT,OAAO;AAAA,IACT;AAAA,EACF;AAEA,MAAI,CAAC,QAAQ,qBAAqB,kBAAkB,UAAU,QAAQ,GAAG;AACvE,WAAO;AAAA,MACL,SAAS;AAAA,MACT,OACE;AAAA,IACJ;AAAA,EACF;AAEA,SAAO;AAAA,IACL,SAAS;AAAA,IACT,cAAc,UAAU,SAAS;AAAA,EACnC;AACF;AAOO,SAAS,aACd,MACA,UAAgC,CAAC,GAIjC;AACA,QAAM,YAAsB,CAAC;AAC7B,QAAM,SAAgD,CAAC;AAEvD,aAAW,OAAO,MAAM;AACtB,UAAM,SAAS,YAAY,KAAK,OAAO;AACvC,QAAI,OAAO,WAAW,OAAO,cAAc;AACzC,gBAAU,KAAK,OAAO,YAAY;AAAA,IACpC,OAAO;AACL,aAAO,KAAK;AAAA,QACV;AAAA,QACA,OAAO,OAAO,SAAS;AAAA,MACzB,CAAC;AAAA,IACH;AAAA,EACF;AAEA,SAAO,EAAE,WAAW,OAAO;AAC7B;;;AT9JA,IAAMC,WAAU,cAAc,YAAY,GAAG;AAC7C,IAAM,MAAMA,SAAQ,iBAAiB;AAMrC,IAAM,EAAE,aAAa,MAAM,QAAQ,IAAI;AAEvC,IAAM,UAAU,IAAI,QAAQ;AAE5B,IAAM,SAAS,eAAe,YAAY,oCAAoC;AAC9E,IAAM,UAAU,eAAe,cAAc,kCAAkC;AAG/E,IAAM,gBAAgB,IAAI,cAAc;AACxC,IAAM,oBAAoB,IAAI,kBAAkB,CAAC,KAAK,QAAQ,QAAQ,SAAS,QAAQ,CAAC;AACxF,IAAM,UAAU,IAAI,iBAAiB;AAErC,eAAe,kBACb,WAMyB;AACzB,QAAM,gBAAgC,CAAC;AAEvC,aAAW,EAAE,SAAS,KAAK,aAAa,MAAM,MAAM,KAAK,WAAW;AAClE,UAAM,cAAc,eAAe,QAAQ;AAC3C,UAAM,YACJ,UAAU,UAAa,CAAC,UAAU,CAAC,IAAI,MAAM,kBAAkB,QAAQ,OAAO;AAChF,UAAM,aACJ,UAAU,UAAa,CAAC,UACpB,EAAE,KAAK,aAAa,OAAO,SAAS,iBAAiB,UAAU,IAC/D,MAAM,cAAc,QAAQ,OAAO;AACzC,kBAAc,KAAK,EAAE,GAAG,YAAY,UAAU,CAAC;AAAA,EACjD;AAEA,SAAO;AACT;AAEA,SAAS,mBAAmB,OAAuB;AACjD,MAAI,MAAM,WAAW,SAAS,GAAG;AAC/B,WAAO,cAAc,KAAK;AAAA,EAC5B;AAEA,SAAO;AACT;AAEA,eAAe,eAAe,OAAiB,SAA+C;AAC5F,MAAI,QAAQ,YAAY,MAAM,SAAS,oBAAoB;AACzD,YAAQ;AAAA,MACN;AAAA,SAAO,MAAM,MAAM,gDAAgD,kBAAkB;AAAA,IACvF;AACA,YAAQ,MAAM,mEAAmE;AACjF,YAAQ,KAAK,CAAC;AAAA,EAChB;AAEA,MAAI,CAAC,QAAQ,YAAY,MAAM,SAAS,oBAAoB;AAC1D,YAAQ;AAAA,MACN;AAAA,8CAAuC,MAAM,MAAM,oBAAoB,kBAAkB;AAAA,IAC3F;AAAA,EACF;AAEA,UAAQ,MAAM;AAAA,oBAAkB,MAAM,MAAM,aAAa;AAEzD,QAAM,cAAc,IAAI,YAAY;AACpC,QAAM,kBAAkB,MAAM,IAAI,CAAC,cAAc,mBAAmB,SAAS,CAAC;AAC9E,QAAM,YAAY,MAAM,YAAY,SAAS,eAAe;AAC5D,QAAM,gBAAgB,MAAM;AAAA,IAC1B,UAAU,IAAI,CAAC,EAAE,MAAM,SAAS,MAAM,OAAO,EAAE,MAAM,SAAS,MAAM,EAAE;AAAA,EACxE;AAEA,QAAM,QAAQ,MAAM,GAAG,aAAa;AACtC;AAEA,SAAS,kBAA2B;AAClC,QAAM,cAAc,QAAQ,KAAK,CAAC;AAClC,MAAI,CAAC,aAAa;AAChB,WAAO;AAAA,EACT;AAEA,MAAI;AACF,WAAO,aAAa,cAAc,YAAY,GAAG,CAAC,MAAM,aAAa,QAAQ,WAAW,CAAC;AAAA,EAC3F,QAAQ;AACN,WAAO;AAAA,EACT;AACF;AAEA,eAAsB,OAAO,OAAiB,QAAQ,MAAqB;AACzE,UAAQ,KAAK,IAAI,EAAE,QAAQ,SAAS,eAAe,EAAE,YAAY,WAAW;AAE5E,UACG,YAAY,OAAO,EACnB;AAAA,IACC,IAAI,OAAO,iBAAiB,cAAc,kBAAkB,0BAA0B;AAAA,EACxF,EACC,OAAO,OAAO,OAAiB,YAAmC;AACjE,QAAI;AACF,YAAM,eAAe,OAAO,OAAO;AAAA,IACrC,SAAS,OAAO;AACd,cAAQ,MAAM,+BAA0B,iBAAiB,QAAQ,MAAM,UAAU,KAAK;AACtF,cAAQ,KAAK,CAAC;AAAA,IAChB;AAAA,EACF,CAAC;AAGH,UACG,QAAQ,OAAO,EACf,YAAY,gDAAgD,EAC5D,YAAY,MAAM,EAClB;AAAA,IACC,IAAI;AAAA,MACF;AAAA,MACA;AAAA,IACF;AAAA,EACF,EACC,UAAU,IAAI,OAAO,4BAA4B,qCAAqC,CAAC,EACvF;AAAA,IACC,IAAI;AAAA,MACF;AAAA,MACA;AAAA,IACF;AAAA,EACF,EACC;AAAA,IACC,OACE,MACA,YACG;AACH,UAAI;AACF,cAAM,EAAE,WAAW,OAAO,IAAI,aAAa,MAAM;AAAA,UAC/C,mBAAmB,QAAQ;AAAA,QAC7B,CAAC;AAED,YAAI,OAAO,SAAS,GAAG;AACrB,kBAAQ,MAAM,iCAA4B;AAC1C,iBAAO,QAAQ,CAAC,EAAE,KAAK,YAAY,MAAM,MAAM;AAC7C,oBAAQ,MAAM,OAAO,UAAU,KAAK,KAAK,EAAE;AAAA,UAC7C,CAAC;AAAA,QACH;AAEA,YAAI,UAAU,WAAW,GAAG;AAC1B,kBAAQ,MAAM,6CAAwC;AACtD,kBAAQ,KAAK,CAAC;AAAA,QAChB;AAEA,gBAAQ,MAAM;AAAA,oBAAkB,UAAU,MAAM,kBAAkB;AAElE,cAAM,cAAc,IAAI,YAAY,QAAQ,QAAQ,IAAI,KAAO,GAAG,QAAQ,SAAS;AAEnF,cAAM,UAAU,YAA2B;AACzC,gBAAM,YAAY,MAAM,YAAY,SAAS,SAAS;AACtD,gBAAM,gBAAgB,MAAM,kBAAkB,SAAS;AACvD,gBAAM,QAAQ,MAAM,GAAG,aAAa;AAAA,QACtC;AAEA,YAAI,QAAQ,OAAO;AACjB,kBAAQ,MAAM,OAAO;AACrB,kBAAQ,GAAG,UAAU,MAAM,QAAQ,KAAK,CAAC,CAAC;AAE1C,cAAI,kBAAwC;AAC5C,kBAAQ,MAAM,GAAG,OAAO,MAAM;AAC5B,8BAAkB;AAAA,UACpB,CAAC;AAED,cAAI,aAAmD;AACvD,kBAAQ,GAAG,YAAY,MAAM;AAC3B,gBAAI,eAAe,KAAM,cAAa,UAAU;AAChD,yBAAa,WAAW,MAAM;AAC5B,2BAAa;AACb,gCAAkB,QAAQ,EAAE,MAAM,CAAC,QAAiB;AAClD,wBAAQ;AAAA,kBACN;AAAA,kBACA,eAAe,QAAQ,IAAI,UAAU;AAAA,gBACvC;AAAA,cACF,CAAC;AAAA,YACH,GAAG,GAAG;AAAA,UACR,CAAC;AAED,4BAAkB,QAAQ;AAC1B,gBAAM;AAAA,QACR,OAAO;AACL,gBAAM,QAAQ;AAAA,QAChB;AAAA,MACF,SAAS,OAAO;AACd,gBAAQ,MAAM,+BAA0B,iBAAiB,QAAQ,MAAM,UAAU,KAAK;AACtF,gBAAQ,KAAK,CAAC;AAAA,MAChB;AAAA,IACF;AAAA,EACF;AAGF,UACG,QAAQ,MAAM,EACd,YAAY,mEAAmE,EAC/E,YAAY,OAAO,EACnB;AAAA,IACC,IAAI,OAAO,iBAAiB,cAAc,kBAAkB,0BAA0B;AAAA,EACxF,EACC,OAAO,OAAO,OAAiB,YAAmC;AACjE,QAAI;AACF,YAAM,eAAe,OAAO,OAAO;AAAA,IACrC,SAAS,OAAO;AACd,cAAQ,MAAM,+BAA0B,iBAAiB,QAAQ,MAAM,UAAU,KAAK;AACtF,cAAQ,KAAK,CAAC;AAAA,IAChB;AAAA,EACF,CAAC;AAEH,QAAM,QAAQ,WAAW,IAAI;AAC/B;AAEA,IAAI,gBAAgB,GAAG;AACrB,SAAO,EAAE,MAAM,CAAC,UAAmB;AACjC,YAAQ,MAAM,+BAA0B,iBAAiB,QAAQ,MAAM,UAAU,KAAK;AACtF,YAAQ,KAAK,CAAC;AAAA,EAChB,CAAC;AACH;",
   "names": ["name", "resolve", "parseHTML", "require"]
 }

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pagerts",
   "description": "A tool for viewing external relations in a webpage",
-  "version": "1.5.2",
+  "version": "1.5.5",
   "type": "module",
   "main": "main.js",
   "bin": {
@@ -43,18 +43,18 @@
   },
   "homepage": "https://github.com/akinevz2/pagerts",
   "dependencies": {
-    "@exodus/bytes": "^1.15.0",
     "commander": "^14.0.3",
     "linkedom": "^0.18.9"
   },
   "devDependencies": {
+    "@eslint/js": "^9.39.1",
     "@swc/core": "^1.15.33",
     "@swc/jest": "^0.2.39",
     "@types/jest": "^30.0.0",
     "@types/node": "^25.8.0",
     "@typescript-eslint/eslint-plugin": "^8.20.0",
     "@typescript-eslint/parser": "^8.20.0",
-    "esbuild": "^0.25.1",
+    "esbuild": "^0.28.1",
     "eslint": "^9.18.0",
     "eslint-config-prettier": "^9.1.0",
     "eslint-plugin-security": "^3.0.1",
@@ -66,6 +66,7 @@
   "overrides": {
     "babel-plugin-istanbul": "^8.0.0",
     "test-exclude": "^8.0.0",
-    "glob": "^13.0.6"
+    "glob": "^13.0.6",
+    "js-yaml": "^4.1.1"
   }
 }