fetchHTML API parameter can be Object type

Author: coder-hxl

README.md

@@ -2,7 +2,7 @@
 
 English | <a href="#cn" style="text-decoration: none">简体中文</a>
 
-XCrawl is a Nodejs multifunctional crawler library. Provide configuration to batch fetch HTML, JSON, images, etc.
+XCrawl is a Nodejs multifunctional crawler library. Crawl HTML, JSON, file resources, etc. through simple configuration.
 
 ## Install
 
@@ -47,7 +47,7 @@ class XCrawl {
   constructor(baseConfig?: IXCrawlBaseConifg)
   fetchData<T = any>(config: IFetchDataConfig): Promise<IFetchCommon<T>>
   fetchFile(config: IFetchFileConfig): Promise<IFetchCommon<IFileInfo>>
-  fetchHTML(url: string): Promise<JSDOM>
+  fetchHTML(config: string | IFetchHTMLConfig): Promise<JSDOM>
 }
 ```
 
@@ -130,7 +130,7 @@ fetchHTML is the method of the above <a href="#myXCrawl"  style="text-decoration
 - Type
 
 ```ts
-function fetchHTML(url: string): Promise<JSDOM>
+function fetchHTML(config: string | IFetchHTMLConfig): Promise<JSDOM>
 ```
 
 - Example
@@ -237,6 +237,12 @@ interface IFetchFileConfig extends IFetchBaseConifg {
 }
 ```
 
+- IFetchHTMLConfig
+
+```ts
+interface IFetchHTMLConfig extends IRequestConfig {}
+```
+
 ## More
 
 If you have any **questions** or **needs** , please submit **Issues in** https://github.com/coder-hxl/x-crawl/issues .
@@ -249,7 +255,7 @@ If you have any **questions** or **needs** , please submit **Issues in** https:/
 
 <a href="#en"  style="text-decoration: none">English</a> | 简体中文
 
-XCrawl 是 Nodejs 多功能爬虫库。提供配置即可批量抓取 HTML 、JSON、图片等等。
+XCrawl 是 Nodejs 多功能爬虫库。只需简单的配置即可抓取 HTML 、JSON、文件资源等等。
 
 ## 安装
 
@@ -294,7 +300,7 @@ class XCrawl {
   constructor(baseConfig?: IXCrawlBaseConifg)
   fetchData<T = any>(config: IFetchDataConfig): Promise<IFetchCommon<T>>
   fetchFile(config: IFetchFileConfig): Promise<IFetchCommon<IFileInfo>>
-  fetchHTML(url: string): Promise<JSDOM>
+  fetchHTML(config: string | IFetchHTMLConfig): Promise<JSDOM>
 }
 ```
 
@@ -377,7 +383,7 @@ fetchHTML 是上面 <a href="#cn-myXCrawl"  style="text-decoration: none">myXCra
 - 类型
 
 ```ts
-function fetchHTML(url: string): Promise<JSDOM>
+function fetchHTML(config: string | IFetchHTMLConfig): Promise<JSDOM>
 ```
 
 - 示例
@@ -484,6 +490,12 @@ interface IFetchFileConfig extends IFetchBaseConifg {
 }
 ```
 
+- IFetchHTMLConfig
+
+```ts
+interface IFetchHTMLConfig extends IRequestConfig {}
+```
+
 ## 更多
 
 如有 **问题** 或 **需求** 请在 https://github.com/coder-hxl/x-crawl/issues 中提 **Issues** 。

package.json

@@ -1,9 +1,9 @@
 {
   "private": true,
   "name": "x-crawl",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "author": "CoderHxl",
-  "description": "XCrawl is a Nodejs multifunctional crawler library.",
+  "description": "XCrawl is a Nodejs multifunctional crawler library. Crawl HTML, JSON, file resources, etc. through simple configuration.",
   "license": "MIT",
   "main": "src/index.ts",
   "scripts": {

publish/README.md

@@ -2,7 +2,7 @@
 
 English | <a href="#cn" style="text-decoration: none">简体中文</a>
 
-XCrawl is a Nodejs multifunctional crawler library. Provide configuration to batch fetch HTML, JSON, images, etc.
+XCrawl is a Nodejs multifunctional crawler library. Crawl HTML, JSON, file resources, etc. through simple configuration.
 
 ## Install
 
@@ -249,7 +249,7 @@ If you have any **questions** or **needs** , please submit **Issues in** https:/
 
 <a href="#en"  style="text-decoration: none">English</a> | 简体中文
 
-XCrawl 是 Nodejs 多功能爬虫库。提供配置即可批量抓取 HTML 、JSON、图片等等。
+XCrawl 是 Nodejs 多功能爬虫库。只需简单的配置即可抓取 HTML 、JSON、文件资源等等。
 
 ## 安装
 

publish/package.json

@@ -1,8 +1,8 @@
 {
   "name": "x-crawl",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "author": "CoderHxl",
-  "description": "XCrawl is a Nodejs multifunctional crawler library.",
+  "description": "XCrawl is a Nodejs multifunctional crawler library. Crawl HTML, JSON, file resources, etc. through simple configuration.",
   "license": "MIT",
   "keywords": [
     "nodejs",

src/index.ts

@@ -3,12 +3,13 @@ import path from 'node:path'
 import { JSDOM } from 'jsdom'
 
 import { batchRequest, request } from './request'
-import { isArray, isUndefined } from './utils'
+import { isArray, isString, isUndefined } from './utils'
 
 import {
   IXCrawlBaseConifg,
   IFetchDataConfig,
   IFetchFileConfig,
+  IFetchHTMLConfig,
   IFetchBaseConifg,
   IFileInfo,
   IFetchCommon,
@@ -145,9 +146,13 @@ export default class XCrawl {
     })
   }
 
-  async fetchHTML(url: string): Promise<JSDOM> {
+  async fetchHTML(config: string | IFetchHTMLConfig): Promise<JSDOM> {
+    const rawRequestConifg: IFetchHTMLConfig = isString(config)
+      ? { url: config }
+      : config
+
     const { requestConifg } = mergeConfig(this.baseConfig, {
-      requestConifg: { url }
+      requestConifg: rawRequestConifg
     })
 
     const requestResItem = await request(requestConifg)

src/types.ts

@@ -74,6 +74,8 @@ export interface IFetchFileConfig extends IFetchBaseConifg {
   }
 }
 
+export interface IFetchHTMLConfig extends IRequestConfig {}
+
 export interface IFileInfo {
   fileName: string
   mimeType: string

test/start/index.js

@@ -22,7 +22,7 @@ const testXCrawl = new XCrawl({
 //     console.log(res)
 //   })
 
-testXCrawl.fetchHTML('https://www.bilibili.com/').then((jsdom) => {
+testXCrawl.fetchHTML({ url: 'https://www.bilibili.com/' }).then((jsdom) => {
   const document = jsdom.window.document
   const imgBoxEl = document.querySelectorAll('.bili-video-card__cover')