@agent-infra/browser-context 0.1.1 → 0.1.2

package/dist/content/extract-content.d.ts

@@ -1,7 +1,23 @@
 import type { Page } from 'puppeteer-core';
+import { DefuddleOptions } from 'defuddle/node';
+export declare const extractWithReadability: (page: Page, options?: {
+    markdown?: boolean;
+}) => Promise<{
+    title: string;
+    content: string;
+}>;
+export declare const extractWithDefuddle: (html: string, url: string, options: DefuddleOptions) => Promise<{
+    title: string;
+    content: string;
+}>;
+/**
+ * Extract content from a page using Defuddle or Readability
+ * page html -> markdown
+ * @param page - The page to extract content from
+ * @returns The title and content of the page
+ */
 export declare const extractContent: (page: Page) => Promise<{
-    content: any;
-    title: any;
-    fullContent: any;
+    title: string;
+    content: string;
 }>;
 //# sourceMappingURL=extract-content.d.ts.map

package/dist/content/extract-content.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"extract-content.d.ts","sourceRoot":"","sources":["../../src/content/extract-content.ts"],"names":[],"mappings":"AAIA,OAAO,KAAK,EAAE,IAAI,EAAE,MAAM,gBAAgB,CAAC;AAG3C,eAAO,MAAM,cAAc,GAAU,MAAM,IAAI;;;;EAgC9C,CAAC"}
+{"version":3,"file":"extract-content.d.ts","sourceRoot":"","sources":["../../src/content/extract-content.ts"],"names":[],"mappings":"AAIA,OAAO,KAAK,EAAE,IAAI,EAAE,MAAM,gBAAgB,CAAC;AAC3C,OAAO,EAAY,eAAe,EAAE,MAAM,eAAe,CAAC;AAI1D,eAAO,MAAM,sBAAsB,GACjC,MAAM,IAAI,EACV,UAAS;IACP,QAAQ,CAAC,EAAE,OAAO,CAAC;CACf,KACL,OAAO,CAAC;IAAE,KAAK,EAAE,MAAM,CAAC;IAAC,OAAO,EAAE,MAAM,CAAA;CAAE,CAoC5C,CAAC;AAEF,eAAO,MAAM,mBAAmB,GAC9B,MAAM,MAAM,EACZ,KAAK,MAAM,EACX,SAAS,eAAe,KACvB,OAAO,CAAC;IAAE,KAAK,EAAE,MAAM,CAAC;IAAC,OAAO,EAAE,MAAM,CAAA;CAAE,CAO5C,CAAC;AAEF;;;;;GAKG;AACH,eAAO,MAAM,cAAc,GACzB,MAAM,IAAI,KACT,OAAO,CAAC;IAAE,KAAK,EAAE,MAAM,CAAC;IAAC,OAAO,EAAE,MAAM,CAAA;CAAE,CAY5C,CAAC"}

package/dist/content/extract-content.js

@@ -28,10 +28,14 @@ var __webpack_require__ = {};
 var __webpack_exports__ = {};
 __webpack_require__.r(__webpack_exports__);
 __webpack_require__.d(__webpack_exports__, {
-    extractContent: ()=>extractContent
+    extractWithReadability: ()=>extractWithReadability,
+    extractContent: ()=>extractContent,
+    extractWithDefuddle: ()=>extractWithDefuddle
 });
+const node_namespaceObject = require("defuddle/node");
 const external_readability_script_js_namespaceObject = require("./readability-script.js");
-const extractContent = async (page)=>{
+const external_to_markdown_js_namespaceObject = require("./to-markdown.js");
+const extractWithReadability = async (page, options = {})=>{
     const extractionResult = await page.evaluate((readabilityScript)=>{
         const Readability = new Function('module', `${readabilityScript}\nreturn module.exports`)({});
         const documentClone = document.cloneNode(true);
@@ -41,15 +45,40 @@ const extractContent = async (page)=>{
         const title = document.title;
         return {
             content,
-            title: (null == article ? void 0 : article.title) || title,
-            fullContent: content
+            title: (null == article ? void 0 : article.title) || title
         };
     }, external_readability_script_js_namespaceObject.READABILITY_SCRIPT);
-    return extractionResult;
+    return (null == options ? void 0 : options.markdown) ? {
+        title: extractionResult.title,
+        content: (0, external_to_markdown_js_namespaceObject.toMarkdown)(extractionResult.content)
+    } : extractionResult;
+};
+const extractWithDefuddle = async (html, url, options)=>{
+    const { title, content } = await (0, node_namespaceObject.Defuddle)(html, url, options);
+    return {
+        title,
+        content
+    };
+};
+const extractContent = async (page)=>{
+    const pageSourceHTML = await page.content();
+    try {
+        return await extractWithDefuddle(pageSourceHTML, page.url(), {
+            markdown: true
+        });
+    } catch (e) {
+        return await extractWithReadability(page, {
+            markdown: true
+        });
+    }
 };
 exports.extractContent = __webpack_exports__.extractContent;
+exports.extractWithDefuddle = __webpack_exports__.extractWithDefuddle;
+exports.extractWithReadability = __webpack_exports__.extractWithReadability;
 for(var __webpack_i__ in __webpack_exports__)if (-1 === [
-    "extractContent"
+    "extractContent",
+    "extractWithDefuddle",
+    "extractWithReadability"
 ].indexOf(__webpack_i__)) exports[__webpack_i__] = __webpack_exports__[__webpack_i__];
 Object.defineProperty(exports, '__esModule', {
     value: true

package/dist/content/extract-content.js.map

@@ -1 +1 @@
-{"version":3,"file":"content/extract-content.js","sources":["webpack://@agent-infra/browser-context/webpack/runtime/define_property_getters","webpack://@agent-infra/browser-context/webpack/runtime/has_own_property","webpack://@agent-infra/browser-context/webpack/runtime/make_namespace_object","webpack://@agent-infra/browser-context/./src/content/extract-content.ts"],"sourcesContent":["__webpack_require__.d = (exports, definition) => {\n\tfor(var key in definition) {\n        if(__webpack_require__.o(definition, key) && !__webpack_require__.o(exports, key)) {\n            Object.defineProperty(exports, key, { enumerable: true, get: definition[key] });\n        }\n    }\n};","__webpack_require__.o = (obj, prop) => (Object.prototype.hasOwnProperty.call(obj, prop))","// define __esModule on exports\n__webpack_require__.r = (exports) => {\n\tif(typeof Symbol !== 'undefined' && Symbol.toStringTag) {\n\t\tObject.defineProperty(exports, Symbol.toStringTag, { value: 'Module' });\n\t}\n\tObject.defineProperty(exports, '__esModule', { value: true });\n};","/*\n * Copyright (c) 2025 Bytedance, Inc. and its affiliates.\n * SPDX-License-Identifier: Apache-2.0\n */\nimport type { Page } from 'puppeteer-core';\nimport { READABILITY_SCRIPT } from './readability-script.js';\n\nexport const extractContent = async (page: Page) => {\n  // Extract content using Readability algorithm on a document clone to prevent DOM flickering\n  const extractionResult = await page.evaluate((readabilityScript) => {\n    // Initialize Readability from script\n    const Readability = new Function(\n      'module',\n      `${readabilityScript}\\nreturn module.exports`,\n    )({});\n\n    // Create a deep clone of the document to avoid modifying the visible DOM\n    const documentClone = document.cloneNode(true) as Document;\n\n    // Clean up the cloned document\n    documentClone\n      .querySelectorAll(\n        'script,noscript,style,link,svg,img,video,iframe,canvas,.reflist',\n      )\n      .forEach((el) => el.remove());\n\n    // Parse content from the clone\n    const article = new Readability(documentClone).parse();\n    const content = article?.content || '';\n    const title = document.title;\n\n    return {\n      content,\n      title: article?.title || title,\n      fullContent: content,\n    };\n  }, READABILITY_SCRIPT);\n\n  return extractionResult;\n};\n"],"names":["__webpack_require__","definition","key","Object","obj","prop","Symbol","extractContent","page","extractionResult","readabilityScript","Readability","Function","documentClone","document","el","article","content","title","READABILITY_SCRIPT"],"mappings":";;;;;;;IAAAA,oBAAoB,CAAC,GAAG,CAAC,UAASC;QACjC,IAAI,IAAIC,OAAOD,WACR,IAAGD,oBAAoB,CAAC,CAACC,YAAYC,QAAQ,CAACF,oBAAoB,CAAC,CAAC,UAASE,MACzEC,OAAO,cAAc,CAAC,UAASD,KAAK;YAAE,YAAY;YAAM,KAAKD,UAAU,CAACC,IAAI;QAAC;IAGzF;;;ICNAF,oBAAoB,CAAC,GAAG,CAACI,KAAKC,OAAUF,OAAO,SAAS,CAAC,cAAc,CAAC,IAAI,CAACC,KAAKC;;;ICClFL,oBAAoB,CAAC,GAAG,CAAC;QACxB,IAAG,AAAkB,eAAlB,OAAOM,UAA0BA,OAAO,WAAW,EACrDH,OAAO,cAAc,CAAC,UAASG,OAAO,WAAW,EAAE;YAAE,OAAO;QAAS;QAEtEH,OAAO,cAAc,CAAC,UAAS,cAAc;YAAE,OAAO;QAAK;IAC5D;;;;;;;;ACCO,MAAMI,iBAAiB,OAAOC;IAEnC,MAAMC,mBAAmB,MAAMD,KAAK,QAAQ,CAAC,CAACE;QAE5C,MAAMC,cAAc,IAAIC,SACtB,UACA,GAAGF,kBAAkB,uBAAuB,CAAC,EAC7C,CAAC;QAGH,MAAMG,gBAAgBC,SAAS,SAAS,CAAC;QAGzCD,cACG,gBAAgB,CACf,mEAED,OAAO,CAAC,CAACE,KAAOA,GAAG,MAAM;QAG5B,MAAMC,UAAU,IAAIL,YAAYE,eAAe,KAAK;QACpD,MAAMI,UAAUD,AAAAA,CAAAA,QAAAA,UAAAA,KAAAA,IAAAA,QAAS,OAAO,AAAD,KAAK;QACpC,MAAME,QAAQJ,SAAS,KAAK;QAE5B,OAAO;YACLG;YACA,OAAOD,AAAAA,CAAAA,QAAAA,UAAAA,KAAAA,IAAAA,QAAS,KAAK,AAAD,KAAKE;YACzB,aAAaD;QACf;IACF,GAAGE,+CAAAA,kBAAkBA;IAErB,OAAOV;AACT"}
+{"version":3,"file":"content/extract-content.js","sources":["webpack://@agent-infra/browser-context/webpack/runtime/define_property_getters","webpack://@agent-infra/browser-context/webpack/runtime/has_own_property","webpack://@agent-infra/browser-context/webpack/runtime/make_namespace_object","webpack://@agent-infra/browser-context/./src/content/extract-content.ts"],"sourcesContent":["__webpack_require__.d = (exports, definition) => {\n\tfor(var key in definition) {\n        if(__webpack_require__.o(definition, key) && !__webpack_require__.o(exports, key)) {\n            Object.defineProperty(exports, key, { enumerable: true, get: definition[key] });\n        }\n    }\n};","__webpack_require__.o = (obj, prop) => (Object.prototype.hasOwnProperty.call(obj, prop))","// define __esModule on exports\n__webpack_require__.r = (exports) => {\n\tif(typeof Symbol !== 'undefined' && Symbol.toStringTag) {\n\t\tObject.defineProperty(exports, Symbol.toStringTag, { value: 'Module' });\n\t}\n\tObject.defineProperty(exports, '__esModule', { value: true });\n};","/*\n * Copyright (c) 2025 Bytedance, Inc. and its affiliates.\n * SPDX-License-Identifier: Apache-2.0\n */\nimport type { Page } from 'puppeteer-core';\nimport { Defuddle, DefuddleOptions } from 'defuddle/node';\nimport { READABILITY_SCRIPT } from './readability-script.js';\nimport { toMarkdown } from './to-markdown.js';\n\nexport const extractWithReadability = async (\n  page: Page,\n  options: {\n    markdown?: boolean;\n  } = {},\n): Promise<{ title: string; content: string }> => {\n  // Extract content using Readability algorithm on a document clone to prevent DOM flickering\n  const extractionResult = await page.evaluate((readabilityScript) => {\n    // Initialize Readability from script\n    const Readability = new Function(\n      'module',\n      `${readabilityScript}\\nreturn module.exports`,\n    )({});\n\n    // Create a deep clone of the document to avoid modifying the visible DOM\n    const documentClone = document.cloneNode(true) as Document;\n\n    // Clean up the cloned document\n    documentClone\n      .querySelectorAll(\n        'script,noscript,style,link,svg,img,video,iframe,canvas,.reflist',\n      )\n      .forEach((el) => el.remove());\n\n    // Parse content from the clone\n    const article = new Readability(documentClone).parse();\n    const content = article?.content || '';\n    const title = document.title;\n\n    return {\n      content,\n      title: article?.title || title,\n    };\n  }, READABILITY_SCRIPT);\n\n  return options?.markdown\n    ? {\n        title: extractionResult.title,\n        content: toMarkdown(extractionResult.content),\n      }\n    : extractionResult;\n};\n\nexport const extractWithDefuddle = async (\n  html: string,\n  url: string,\n  options: DefuddleOptions,\n): Promise<{ title: string; content: string }> => {\n  const { title, content } = await Defuddle(html, url, options);\n\n  return {\n    title,\n    content,\n  };\n};\n\n/**\n * Extract content from a page using Defuddle or Readability\n * page html -> markdown\n * @param page - The page to extract content from\n * @returns The title and content of the page\n */\nexport const extractContent = async (\n  page: Page,\n): Promise<{ title: string; content: string }> => {\n  const pageSourceHTML = await page.content();\n\n  try {\n    return await extractWithDefuddle(pageSourceHTML, page.url(), {\n      markdown: true,\n    });\n  } catch (e) {\n    return await extractWithReadability(page as any, {\n      markdown: true,\n    });\n  }\n};\n"],"names":["__webpack_require__","definition","key","Object","obj","prop","Symbol","extractWithReadability","page","options","extractionResult","readabilityScript","Readability","Function","documentClone","document","el","article","content","title","READABILITY_SCRIPT","toMarkdown","extractWithDefuddle","html","url","Defuddle","extractContent","pageSourceHTML","e"],"mappings":";;;;;;;IAAAA,oBAAoB,CAAC,GAAG,CAAC,UAASC;QACjC,IAAI,IAAIC,OAAOD,WACR,IAAGD,oBAAoB,CAAC,CAACC,YAAYC,QAAQ,CAACF,oBAAoB,CAAC,CAAC,UAASE,MACzEC,OAAO,cAAc,CAAC,UAASD,KAAK;YAAE,YAAY;YAAM,KAAKD,UAAU,CAACC,IAAI;QAAC;IAGzF;;;ICNAF,oBAAoB,CAAC,GAAG,CAACI,KAAKC,OAAUF,OAAO,SAAS,CAAC,cAAc,CAAC,IAAI,CAACC,KAAKC;;;ICClFL,oBAAoB,CAAC,GAAG,CAAC;QACxB,IAAG,AAAkB,eAAlB,OAAOM,UAA0BA,OAAO,WAAW,EACrDH,OAAO,cAAc,CAAC,UAASG,OAAO,WAAW,EAAE;YAAE,OAAO;QAAS;QAEtEH,OAAO,cAAc,CAAC,UAAS,cAAc;YAAE,OAAO;QAAK;IAC5D;;;;;;;;;;;;ACGO,MAAMI,yBAAyB,OACpCC,MACAC,UAEI,CAAC,CAAC;IAGN,MAAMC,mBAAmB,MAAMF,KAAK,QAAQ,CAAC,CAACG;QAE5C,MAAMC,cAAc,IAAIC,SACtB,UACA,GAAGF,kBAAkB,uBAAuB,CAAC,EAC7C,CAAC;QAGH,MAAMG,gBAAgBC,SAAS,SAAS,CAAC;QAGzCD,cACG,gBAAgB,CACf,mEAED,OAAO,CAAC,CAACE,KAAOA,GAAG,MAAM;QAG5B,MAAMC,UAAU,IAAIL,YAAYE,eAAe,KAAK;QACpD,MAAMI,UAAUD,AAAAA,CAAAA,QAAAA,UAAAA,KAAAA,IAAAA,QAAS,OAAO,AAAD,KAAK;QACpC,MAAME,QAAQJ,SAAS,KAAK;QAE5B,OAAO;YACLG;YACA,OAAOD,AAAAA,CAAAA,QAAAA,UAAAA,KAAAA,IAAAA,QAAS,KAAK,AAAD,KAAKE;QAC3B;IACF,GAAGC,+CAAAA,kBAAkBA;IAErB,OAAOX,AAAAA,CAAAA,QAAAA,UAAAA,KAAAA,IAAAA,QAAS,QAAQ,AAAD,IACnB;QACE,OAAOC,iBAAiB,KAAK;QAC7B,SAASW,AAAAA,IAAAA,wCAAAA,UAAAA,AAAAA,EAAWX,iBAAiB,OAAO;IAC9C,IACAA;AACN;AAEO,MAAMY,sBAAsB,OACjCC,MACAC,KACAf;IAEA,MAAM,EAAEU,KAAK,EAAED,OAAO,EAAE,GAAG,MAAMO,AAAAA,IAAAA,qBAAAA,QAAAA,AAAAA,EAASF,MAAMC,KAAKf;IAErD,OAAO;QACLU;QACAD;IACF;AACF;AAQO,MAAMQ,iBAAiB,OAC5BlB;IAEA,MAAMmB,iBAAiB,MAAMnB,KAAK,OAAO;IAEzC,IAAI;QACF,OAAO,MAAMc,oBAAoBK,gBAAgBnB,KAAK,GAAG,IAAI;YAC3D,UAAU;QACZ;IACF,EAAE,OAAOoB,GAAG;QACV,OAAO,MAAMrB,uBAAuBC,MAAa;YAC/C,UAAU;QACZ;IACF;AACF"}

package/dist/content/extract-content.mjs

@@ -2,8 +2,10 @@
 * Copyright (c) 2025 Bytedance, Inc. and its affiliates.
 * SPDX-License-Identifier: Apache-2.0
 */
+import { Defuddle } from "defuddle/node";
 import { READABILITY_SCRIPT } from "./readability-script.mjs";
-const extractContent = async (page)=>{
+import { toMarkdown } from "./to-markdown.mjs";
+const extractWithReadability = async (page, options = {})=>{
     const extractionResult = await page.evaluate((readabilityScript)=>{
         const Readability = new Function('module', `${readabilityScript}\nreturn module.exports`)({});
         const documentClone = document.cloneNode(true);
@@ -13,12 +15,33 @@ const extractContent = async (page)=>{
         const title = document.title;
         return {
             content,
-            title: (null == article ? void 0 : article.title) || title,
-            fullContent: content
+            title: (null == article ? void 0 : article.title) || title
         };
     }, READABILITY_SCRIPT);
-    return extractionResult;
+    return (null == options ? void 0 : options.markdown) ? {
+        title: extractionResult.title,
+        content: toMarkdown(extractionResult.content)
+    } : extractionResult;
+};
+const extractWithDefuddle = async (html, url, options)=>{
+    const { title, content } = await Defuddle(html, url, options);
+    return {
+        title,
+        content
+    };
+};
+const extractContent = async (page)=>{
+    const pageSourceHTML = await page.content();
+    try {
+        return await extractWithDefuddle(pageSourceHTML, page.url(), {
+            markdown: true
+        });
+    } catch (e) {
+        return await extractWithReadability(page, {
+            markdown: true
+        });
+    }
 };
-export { extractContent };
+export { extractContent, extractWithDefuddle, extractWithReadability };
 
 //# sourceMappingURL=extract-content.mjs.map

package/dist/content/extract-content.mjs.map

@@ -1 +1 @@
-{"version":3,"file":"content/extract-content.mjs","sources":["webpack://@agent-infra/browser-context/./src/content/extract-content.ts"],"sourcesContent":["/*\n * Copyright (c) 2025 Bytedance, Inc. and its affiliates.\n * SPDX-License-Identifier: Apache-2.0\n */\nimport type { Page } from 'puppeteer-core';\nimport { READABILITY_SCRIPT } from './readability-script.js';\n\nexport const extractContent = async (page: Page) => {\n  // Extract content using Readability algorithm on a document clone to prevent DOM flickering\n  const extractionResult = await page.evaluate((readabilityScript) => {\n    // Initialize Readability from script\n    const Readability = new Function(\n      'module',\n      `${readabilityScript}\\nreturn module.exports`,\n    )({});\n\n    // Create a deep clone of the document to avoid modifying the visible DOM\n    const documentClone = document.cloneNode(true) as Document;\n\n    // Clean up the cloned document\n    documentClone\n      .querySelectorAll(\n        'script,noscript,style,link,svg,img,video,iframe,canvas,.reflist',\n      )\n      .forEach((el) => el.remove());\n\n    // Parse content from the clone\n    const article = new Readability(documentClone).parse();\n    const content = article?.content || '';\n    const title = document.title;\n\n    return {\n      content,\n      title: article?.title || title,\n      fullContent: content,\n    };\n  }, READABILITY_SCRIPT);\n\n  return extractionResult;\n};\n"],"names":["extractContent","page","extractionResult","readabilityScript","Readability","Function","documentClone","document","el","article","content","title","READABILITY_SCRIPT"],"mappings":";;;;;AAOO,MAAMA,iBAAiB,OAAOC;IAEnC,MAAMC,mBAAmB,MAAMD,KAAK,QAAQ,CAAC,CAACE;QAE5C,MAAMC,cAAc,IAAIC,SACtB,UACA,GAAGF,kBAAkB,uBAAuB,CAAC,EAC7C,CAAC;QAGH,MAAMG,gBAAgBC,SAAS,SAAS,CAAC;QAGzCD,cACG,gBAAgB,CACf,mEAED,OAAO,CAAC,CAACE,KAAOA,GAAG,MAAM;QAG5B,MAAMC,UAAU,IAAIL,YAAYE,eAAe,KAAK;QACpD,MAAMI,UAAUD,AAAAA,CAAAA,QAAAA,UAAAA,KAAAA,IAAAA,QAAS,OAAO,AAAD,KAAK;QACpC,MAAME,QAAQJ,SAAS,KAAK;QAE5B,OAAO;YACLG;YACA,OAAOD,AAAAA,CAAAA,QAAAA,UAAAA,KAAAA,IAAAA,QAAS,KAAK,AAAD,KAAKE;YACzB,aAAaD;QACf;IACF,GAAGE;IAEH,OAAOV;AACT"}
+{"version":3,"file":"content/extract-content.mjs","sources":["webpack://@agent-infra/browser-context/./src/content/extract-content.ts"],"sourcesContent":["/*\n * Copyright (c) 2025 Bytedance, Inc. and its affiliates.\n * SPDX-License-Identifier: Apache-2.0\n */\nimport type { Page } from 'puppeteer-core';\nimport { Defuddle, DefuddleOptions } from 'defuddle/node';\nimport { READABILITY_SCRIPT } from './readability-script.js';\nimport { toMarkdown } from './to-markdown.js';\n\nexport const extractWithReadability = async (\n  page: Page,\n  options: {\n    markdown?: boolean;\n  } = {},\n): Promise<{ title: string; content: string }> => {\n  // Extract content using Readability algorithm on a document clone to prevent DOM flickering\n  const extractionResult = await page.evaluate((readabilityScript) => {\n    // Initialize Readability from script\n    const Readability = new Function(\n      'module',\n      `${readabilityScript}\\nreturn module.exports`,\n    )({});\n\n    // Create a deep clone of the document to avoid modifying the visible DOM\n    const documentClone = document.cloneNode(true) as Document;\n\n    // Clean up the cloned document\n    documentClone\n      .querySelectorAll(\n        'script,noscript,style,link,svg,img,video,iframe,canvas,.reflist',\n      )\n      .forEach((el) => el.remove());\n\n    // Parse content from the clone\n    const article = new Readability(documentClone).parse();\n    const content = article?.content || '';\n    const title = document.title;\n\n    return {\n      content,\n      title: article?.title || title,\n    };\n  }, READABILITY_SCRIPT);\n\n  return options?.markdown\n    ? {\n        title: extractionResult.title,\n        content: toMarkdown(extractionResult.content),\n      }\n    : extractionResult;\n};\n\nexport const extractWithDefuddle = async (\n  html: string,\n  url: string,\n  options: DefuddleOptions,\n): Promise<{ title: string; content: string }> => {\n  const { title, content } = await Defuddle(html, url, options);\n\n  return {\n    title,\n    content,\n  };\n};\n\n/**\n * Extract content from a page using Defuddle or Readability\n * page html -> markdown\n * @param page - The page to extract content from\n * @returns The title and content of the page\n */\nexport const extractContent = async (\n  page: Page,\n): Promise<{ title: string; content: string }> => {\n  const pageSourceHTML = await page.content();\n\n  try {\n    return await extractWithDefuddle(pageSourceHTML, page.url(), {\n      markdown: true,\n    });\n  } catch (e) {\n    return await extractWithReadability(page as any, {\n      markdown: true,\n    });\n  }\n};\n"],"names":["extractWithReadability","page","options","extractionResult","readabilityScript","Readability","Function","documentClone","document","el","article","content","title","READABILITY_SCRIPT","toMarkdown","extractWithDefuddle","html","url","Defuddle","extractContent","pageSourceHTML","e"],"mappings":";;;;;;;AASO,MAAMA,yBAAyB,OACpCC,MACAC,UAEI,CAAC,CAAC;IAGN,MAAMC,mBAAmB,MAAMF,KAAK,QAAQ,CAAC,CAACG;QAE5C,MAAMC,cAAc,IAAIC,SACtB,UACA,GAAGF,kBAAkB,uBAAuB,CAAC,EAC7C,CAAC;QAGH,MAAMG,gBAAgBC,SAAS,SAAS,CAAC;QAGzCD,cACG,gBAAgB,CACf,mEAED,OAAO,CAAC,CAACE,KAAOA,GAAG,MAAM;QAG5B,MAAMC,UAAU,IAAIL,YAAYE,eAAe,KAAK;QACpD,MAAMI,UAAUD,AAAAA,CAAAA,QAAAA,UAAAA,KAAAA,IAAAA,QAAS,OAAO,AAAD,KAAK;QACpC,MAAME,QAAQJ,SAAS,KAAK;QAE5B,OAAO;YACLG;YACA,OAAOD,AAAAA,CAAAA,QAAAA,UAAAA,KAAAA,IAAAA,QAAS,KAAK,AAAD,KAAKE;QAC3B;IACF,GAAGC;IAEH,OAAOX,AAAAA,CAAAA,QAAAA,UAAAA,KAAAA,IAAAA,QAAS,QAAQ,AAAD,IACnB;QACE,OAAOC,iBAAiB,KAAK;QAC7B,SAASW,WAAWX,iBAAiB,OAAO;IAC9C,IACAA;AACN;AAEO,MAAMY,sBAAsB,OACjCC,MACAC,KACAf;IAEA,MAAM,EAAEU,KAAK,EAAED,OAAO,EAAE,GAAG,MAAMO,SAASF,MAAMC,KAAKf;IAErD,OAAO;QACLU;QACAD;IACF;AACF;AAQO,MAAMQ,iBAAiB,OAC5BlB;IAEA,MAAMmB,iBAAiB,MAAMnB,KAAK,OAAO;IAEzC,IAAI;QACF,OAAO,MAAMc,oBAAoBK,gBAAgBnB,KAAK,GAAG,IAAI;YAC3D,UAAU;QACZ;IACF,EAAE,OAAOoB,GAAG;QACV,OAAO,MAAMrB,uBAAuBC,MAAa;YAC/C,UAAU;QACZ;IACF;AACF"}

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@agent-infra/browser-context",
   "description": "get browser context for AI Agent",
-  "version": "0.1.1",
+  "version": "0.1.2",
   "main": "dist/index.js",
   "module": "dist/index.mjs",
   "types": "dist/index.d.ts",
@@ -30,6 +30,7 @@
     "test:e2e:local": "vitest --config vitest.e2e.config.ts local-browser.e2e.test.ts"
   },
   "dependencies": {
+    "defuddle": "^0.6.4",
     "puppeteer-core": "24.14.0",
     "turndown": "^7.2.0",
     "turndown-plugin-gfm": "^1.0.2"