@synstack/web 1.1.5 → 1.1.7

package/README.md

@@ -2,9 +2,6 @@
 
 Web utilities for fetching and parsing web content
 
-> [!WARNING]
-> This package is included in the [@synstack/synscript](../synscript/README.md) package. It is not recommended to install both packages at the same time.
-
 ## What is it for?
 
 This package provides utilities for fetching and parsing web content, including JSON data, plain text, and article extraction:

package/dist/web.index.cjs

@@ -39,7 +39,6 @@ __export(web_bundle_exports, {
 // src/web.lib.ts
 var import_readability = require("@mozilla/readability");
 var import_linkedom = require("linkedom");
-var import_zod = require("zod");
 var fetchJson = (url, options = {}) => fetch(url).then((response) => response.json()).then((data) => options.schema ? options.schema.parse(data) : data);
 var fetchText = (url) => fetch(url).then((response) => response.text());
 var fetchArticle = async (url) => {

package/dist/web.index.cjs.map

@@ -1 +1 @@
-{"version":3,"sources":["../src/web.index.ts","../src/web.bundle.ts","../src/web.lib.ts"],"sourcesContent":["export * from \"./web.bundle.ts\";\nexport * as web from \"./web.bundle.ts\";\nexport { ArticleNotFoundException } from \"./web.lib.ts\";\n","export { fetchArticle, fetchJson, fetchText } from \"./web.lib.ts\";\n","import { Readability } from \"@mozilla/readability\";\nimport { parseHTML } from \"linkedom\";\nimport { type ZodSchema } from \"zod\";\n\n/**\n * Retrieves an URL as JSON\n * @param url\n * @param options.schema an optional Zod schema to validate the data against\n * @returns the JSON as a JS object\n */\nexport const fetchJson = <T>(\n  url: string,\n  options: { schema?: ZodSchema<T> } = {},\n): Promise<T> =>\n  fetch(url)\n    .then((response) => response.json())\n    .then((data) => (options.schema ? options.schema.parse(data) : data));\n\n/**\n * Retrieves an URL as a string\n * @param url\n * @returns the plain text content of the URL\n */\nexport const fetchText = (url: string): Promise<string> =>\n  fetch(url).then((response) => response.text());\n\n/**\n * Extract an article from a URL\n * @param url\n * @returns the article content as a JS object\n */\nexport const fetchArticle = async (url: string) => {\n  const content = await fetchText(url);\n  const doc = parseHTML(content, { url });\n  const reader = new Readability(doc.window.document);\n  const article = reader.parse();\n\n  if (!article?.content) throw new ArticleNotFoundException(url);\n\n  return {\n    url,\n    content: article.content,\n    title: article.title,\n    byline: article.byline,\n    siteName: article.siteName,\n    lang: article.lang,\n    publishedTime: article.publishedTime,\n  };\n};\n\nexport class ArticleNotFoundException extends Error {\n  constructor(url: string) {\n    super(\n      `\nNo article found at the URL\nURL: ${url}\n`.trim(),\n    );\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;;;ACAA;AAAA;AAAA;AAAA;AAAA;AAAA;;;ACAA,yBAA4B;AAC5B,sBAA0B;AAC1B,iBAA+B;AAQxB,IAAM,YAAY,CACvB,KACA,UAAqC,CAAC,MAEtC,MAAM,GAAG,EACN,KAAK,CAAC,aAAa,SAAS,KAAK,CAAC,EAClC,KAAK,CAAC,SAAU,QAAQ,SAAS,QAAQ,OAAO,MAAM,IAAI,IAAI,IAAK;AAOjE,IAAM,YAAY,CAAC,QACxB,MAAM,GAAG,EAAE,KAAK,CAAC,aAAa,SAAS,KAAK,CAAC;AAOxC,IAAM,eAAe,OAAO,QAAgB;AACjD,QAAM,UAAU,MAAM,UAAU,GAAG;AACnC,QAAM,UAAM,2BAAU,SAAS,EAAE,IAAI,CAAC;AACtC,QAAM,SAAS,IAAI,+BAAY,IAAI,OAAO,QAAQ;AAClD,QAAM,UAAU,OAAO,MAAM;AAE7B,MAAI,CAAC,SAAS,QAAS,OAAM,IAAI,yBAAyB,GAAG;AAE7D,SAAO;AAAA,IACL;AAAA,IACA,SAAS,QAAQ;AAAA,IACjB,OAAO,QAAQ;AAAA,IACf,QAAQ,QAAQ;AAAA,IAChB,UAAU,QAAQ;AAAA,IAClB,MAAM,QAAQ;AAAA,IACd,eAAe,QAAQ;AAAA,EACzB;AACF;AAEO,IAAM,2BAAN,cAAuC,MAAM;AAAA,EAClD,YAAY,KAAa;AACvB;AAAA,MACE;AAAA;AAAA,OAEC,GAAG;AAAA,EACR,KAAK;AAAA,IACH;AAAA,EACF;AACF;","names":[]}
+{"version":3,"sources":["../src/web.index.ts","../src/web.bundle.ts","../src/web.lib.ts"],"sourcesContent":["export * from \"./web.bundle.ts\";\nexport * as web from \"./web.bundle.ts\";\nexport { ArticleNotFoundException } from \"./web.lib.ts\";\n","export { fetchArticle, fetchJson, fetchText } from \"./web.lib.ts\";\n","import { Readability } from \"@mozilla/readability\";\nimport { parseHTML } from \"linkedom\";\nimport type { ZodSchema } from \"zod\";\n\n/**\n * Retrieves an URL as JSON\n * @param url\n * @param options.schema an optional Zod schema to validate the data against\n * @returns the JSON as a JS object\n */\nexport const fetchJson = <T>(\n  url: string,\n  options: { schema?: ZodSchema<T> } = {},\n): Promise<T> =>\n  fetch(url)\n    .then((response) => response.json())\n    .then((data) => (options.schema ? options.schema.parse(data) : data));\n\n/**\n * Retrieves an URL as a string\n * @param url\n * @returns the plain text content of the URL\n */\nexport const fetchText = (url: string): Promise<string> =>\n  fetch(url).then((response) => response.text());\n\n/**\n * Extract an article from a URL\n * @param url\n * @returns the article content as a JS object\n */\nexport const fetchArticle = async (url: string) => {\n  const content = await fetchText(url);\n  const doc = parseHTML(content, { url });\n  const reader = new Readability(doc.window.document);\n  const article = reader.parse();\n\n  if (!article?.content) throw new ArticleNotFoundException(url);\n\n  return {\n    url,\n    content: article.content,\n    title: article.title,\n    byline: article.byline,\n    siteName: article.siteName,\n    lang: article.lang,\n    publishedTime: article.publishedTime,\n  };\n};\n\nexport class ArticleNotFoundException extends Error {\n  constructor(url: string) {\n    super(\n      `\nNo article found at the URL\nURL: ${url}\n`.trim(),\n    );\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;;;ACAA;AAAA;AAAA;AAAA;AAAA;AAAA;;;ACAA,yBAA4B;AAC5B,sBAA0B;AASnB,IAAM,YAAY,CACvB,KACA,UAAqC,CAAC,MAEtC,MAAM,GAAG,EACN,KAAK,CAAC,aAAa,SAAS,KAAK,CAAC,EAClC,KAAK,CAAC,SAAU,QAAQ,SAAS,QAAQ,OAAO,MAAM,IAAI,IAAI,IAAK;AAOjE,IAAM,YAAY,CAAC,QACxB,MAAM,GAAG,EAAE,KAAK,CAAC,aAAa,SAAS,KAAK,CAAC;AAOxC,IAAM,eAAe,OAAO,QAAgB;AACjD,QAAM,UAAU,MAAM,UAAU,GAAG;AACnC,QAAM,UAAM,2BAAU,SAAS,EAAE,IAAI,CAAC;AACtC,QAAM,SAAS,IAAI,+BAAY,IAAI,OAAO,QAAQ;AAClD,QAAM,UAAU,OAAO,MAAM;AAE7B,MAAI,CAAC,SAAS,QAAS,OAAM,IAAI,yBAAyB,GAAG;AAE7D,SAAO;AAAA,IACL;AAAA,IACA,SAAS,QAAQ;AAAA,IACjB,OAAO,QAAQ;AAAA,IACf,QAAQ,QAAQ;AAAA,IAChB,UAAU,QAAQ;AAAA,IAClB,MAAM,QAAQ;AAAA,IACd,eAAe,QAAQ;AAAA,EACzB;AACF;AAEO,IAAM,2BAAN,cAAuC,MAAM;AAAA,EAClD,YAAY,KAAa;AACvB;AAAA,MACE;AAAA;AAAA,OAEC,GAAG;AAAA,EACR,KAAK;AAAA,IACH;AAAA,EACF;AACF;","names":[]}

package/dist/web.index.d.cts

@@ -23,11 +23,11 @@ declare const fetchText: (url: string) => Promise<string>;
 declare const fetchArticle: (url: string) => Promise<{
     url: string;
     content: string;
-    title: string;
-    byline: string;
-    siteName: string;
-    lang: string;
-    publishedTime: string;
+    title: string | null | undefined;
+    byline: string | null | undefined;
+    siteName: string | null | undefined;
+    lang: string | null | undefined;
+    publishedTime: string | null | undefined;
 }>;
 declare class ArticleNotFoundException extends Error {
     constructor(url: string);

package/dist/web.index.d.ts

@@ -23,11 +23,11 @@ declare const fetchText: (url: string) => Promise<string>;
 declare const fetchArticle: (url: string) => Promise<{
     url: string;
     content: string;
-    title: string;
-    byline: string;
-    siteName: string;
-    lang: string;
-    publishedTime: string;
+    title: string | null | undefined;
+    byline: string | null | undefined;
+    siteName: string | null | undefined;
+    lang: string | null | undefined;
+    publishedTime: string | null | undefined;
 }>;
 declare class ArticleNotFoundException extends Error {
     constructor(url: string);

package/dist/web.index.js

@@ -15,7 +15,6 @@ __export(web_bundle_exports, {
 // src/web.lib.ts
 import { Readability } from "@mozilla/readability";
 import { parseHTML } from "linkedom";
-import "zod";
 var fetchJson = (url, options = {}) => fetch(url).then((response) => response.json()).then((data) => options.schema ? options.schema.parse(data) : data);
 var fetchText = (url) => fetch(url).then((response) => response.text());
 var fetchArticle = async (url) => {

package/dist/web.index.js.map

@@ -1 +1 @@
-{"version":3,"sources":["../src/web.bundle.ts","../src/web.lib.ts"],"sourcesContent":["export { fetchArticle, fetchJson, fetchText } from \"./web.lib.ts\";\n","import { Readability } from \"@mozilla/readability\";\nimport { parseHTML } from \"linkedom\";\nimport { type ZodSchema } from \"zod\";\n\n/**\n * Retrieves an URL as JSON\n * @param url\n * @param options.schema an optional Zod schema to validate the data against\n * @returns the JSON as a JS object\n */\nexport const fetchJson = <T>(\n  url: string,\n  options: { schema?: ZodSchema<T> } = {},\n): Promise<T> =>\n  fetch(url)\n    .then((response) => response.json())\n    .then((data) => (options.schema ? options.schema.parse(data) : data));\n\n/**\n * Retrieves an URL as a string\n * @param url\n * @returns the plain text content of the URL\n */\nexport const fetchText = (url: string): Promise<string> =>\n  fetch(url).then((response) => response.text());\n\n/**\n * Extract an article from a URL\n * @param url\n * @returns the article content as a JS object\n */\nexport const fetchArticle = async (url: string) => {\n  const content = await fetchText(url);\n  const doc = parseHTML(content, { url });\n  const reader = new Readability(doc.window.document);\n  const article = reader.parse();\n\n  if (!article?.content) throw new ArticleNotFoundException(url);\n\n  return {\n    url,\n    content: article.content,\n    title: article.title,\n    byline: article.byline,\n    siteName: article.siteName,\n    lang: article.lang,\n    publishedTime: article.publishedTime,\n  };\n};\n\nexport class ArticleNotFoundException extends Error {\n  constructor(url: string) {\n    super(\n      `\nNo article found at the URL\nURL: ${url}\n`.trim(),\n    );\n  }\n}\n"],"mappings":";;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;;;ACAA,SAAS,mBAAmB;AAC5B,SAAS,iBAAiB;AAC1B,OAA+B;AAQxB,IAAM,YAAY,CACvB,KACA,UAAqC,CAAC,MAEtC,MAAM,GAAG,EACN,KAAK,CAAC,aAAa,SAAS,KAAK,CAAC,EAClC,KAAK,CAAC,SAAU,QAAQ,SAAS,QAAQ,OAAO,MAAM,IAAI,IAAI,IAAK;AAOjE,IAAM,YAAY,CAAC,QACxB,MAAM,GAAG,EAAE,KAAK,CAAC,aAAa,SAAS,KAAK,CAAC;AAOxC,IAAM,eAAe,OAAO,QAAgB;AACjD,QAAM,UAAU,MAAM,UAAU,GAAG;AACnC,QAAM,MAAM,UAAU,SAAS,EAAE,IAAI,CAAC;AACtC,QAAM,SAAS,IAAI,YAAY,IAAI,OAAO,QAAQ;AAClD,QAAM,UAAU,OAAO,MAAM;AAE7B,MAAI,CAAC,SAAS,QAAS,OAAM,IAAI,yBAAyB,GAAG;AAE7D,SAAO;AAAA,IACL;AAAA,IACA,SAAS,QAAQ;AAAA,IACjB,OAAO,QAAQ;AAAA,IACf,QAAQ,QAAQ;AAAA,IAChB,UAAU,QAAQ;AAAA,IAClB,MAAM,QAAQ;AAAA,IACd,eAAe,QAAQ;AAAA,EACzB;AACF;AAEO,IAAM,2BAAN,cAAuC,MAAM;AAAA,EAClD,YAAY,KAAa;AACvB;AAAA,MACE;AAAA;AAAA,OAEC,GAAG;AAAA,EACR,KAAK;AAAA,IACH;AAAA,EACF;AACF;","names":[]}
+{"version":3,"sources":["../src/web.bundle.ts","../src/web.lib.ts"],"sourcesContent":["export { fetchArticle, fetchJson, fetchText } from \"./web.lib.ts\";\n","import { Readability } from \"@mozilla/readability\";\nimport { parseHTML } from \"linkedom\";\nimport type { ZodSchema } from \"zod\";\n\n/**\n * Retrieves an URL as JSON\n * @param url\n * @param options.schema an optional Zod schema to validate the data against\n * @returns the JSON as a JS object\n */\nexport const fetchJson = <T>(\n  url: string,\n  options: { schema?: ZodSchema<T> } = {},\n): Promise<T> =>\n  fetch(url)\n    .then((response) => response.json())\n    .then((data) => (options.schema ? options.schema.parse(data) : data));\n\n/**\n * Retrieves an URL as a string\n * @param url\n * @returns the plain text content of the URL\n */\nexport const fetchText = (url: string): Promise<string> =>\n  fetch(url).then((response) => response.text());\n\n/**\n * Extract an article from a URL\n * @param url\n * @returns the article content as a JS object\n */\nexport const fetchArticle = async (url: string) => {\n  const content = await fetchText(url);\n  const doc = parseHTML(content, { url });\n  const reader = new Readability(doc.window.document);\n  const article = reader.parse();\n\n  if (!article?.content) throw new ArticleNotFoundException(url);\n\n  return {\n    url,\n    content: article.content,\n    title: article.title,\n    byline: article.byline,\n    siteName: article.siteName,\n    lang: article.lang,\n    publishedTime: article.publishedTime,\n  };\n};\n\nexport class ArticleNotFoundException extends Error {\n  constructor(url: string) {\n    super(\n      `\nNo article found at the URL\nURL: ${url}\n`.trim(),\n    );\n  }\n}\n"],"mappings":";;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;;;ACAA,SAAS,mBAAmB;AAC5B,SAAS,iBAAiB;AASnB,IAAM,YAAY,CACvB,KACA,UAAqC,CAAC,MAEtC,MAAM,GAAG,EACN,KAAK,CAAC,aAAa,SAAS,KAAK,CAAC,EAClC,KAAK,CAAC,SAAU,QAAQ,SAAS,QAAQ,OAAO,MAAM,IAAI,IAAI,IAAK;AAOjE,IAAM,YAAY,CAAC,QACxB,MAAM,GAAG,EAAE,KAAK,CAAC,aAAa,SAAS,KAAK,CAAC;AAOxC,IAAM,eAAe,OAAO,QAAgB;AACjD,QAAM,UAAU,MAAM,UAAU,GAAG;AACnC,QAAM,MAAM,UAAU,SAAS,EAAE,IAAI,CAAC;AACtC,QAAM,SAAS,IAAI,YAAY,IAAI,OAAO,QAAQ;AAClD,QAAM,UAAU,OAAO,MAAM;AAE7B,MAAI,CAAC,SAAS,QAAS,OAAM,IAAI,yBAAyB,GAAG;AAE7D,SAAO;AAAA,IACL;AAAA,IACA,SAAS,QAAQ;AAAA,IACjB,OAAO,QAAQ;AAAA,IACf,QAAQ,QAAQ;AAAA,IAChB,UAAU,QAAQ;AAAA,IAClB,MAAM,QAAQ;AAAA,IACd,eAAe,QAAQ;AAAA,EACzB;AACF;AAEO,IAAM,2BAAN,cAAuC,MAAM;AAAA,EAClD,YAAY,KAAa;AACvB;AAAA,MACE;AAAA;AAAA,OAEC,GAAG;AAAA,EACR,KAAK;AAAA,IACH;AAAA,EACF;AACF;","names":[]}

package/package.json

@@ -4,7 +4,7 @@
   "publishConfig": {
     "access": "public"
   },
-  "version": "1.1.5",
+  "version": "1.1.7",
   "description": "Web scraping utilities",
   "keywords": [
     "web",
@@ -46,14 +46,14 @@
     }
   },
   "dependencies": {
-    "@mozilla/readability": "^0.5.0",
-    "linkedom": "^0.18.5"
+    "@mozilla/readability": "^0.6.0",
+    "linkedom": "^0.18.9"
   },
   "devDependencies": {
     "@types/node": "^22.10.1",
-    "tsup": "^8.3.5",
-    "typescript": "^5.7.2",
-    "zod": "^3.23.8"
+    "tsup": "^8.4.0",
+    "typescript": "^5.8.2",
+    "zod": "^3.24.2"
   },
   "peerDependencies": {
     "zod": "*"
@@ -63,5 +63,5 @@
     "!src/**/*.test.ts",
     "dist/**/*"
   ],
-  "gitHead": "886036553ab02c6c1b98289b1de64240de866521"
+  "gitHead": "4aae6e86f7664e5b928ecb3a492ec035307168d1"
 }

package/src/web.lib.ts

@@ -1,6 +1,6 @@
 import { Readability } from "@mozilla/readability";
 import { parseHTML } from "linkedom";
-import { type ZodSchema } from "zod";
+import type { ZodSchema } from "zod";
 
 /**
  * Retrieves an URL as JSON