docs: update

Author: coder-hxl

README.md

@@ -70,26 +70,57 @@ npm install x-crawl
 
 ## Example
 
-Get the title of https://docs.github.com/zh/get-started as an example:
+Example of fetching featured video cover image for youtube homepage every other day:
 
 ```js
-// Import module ES/CJS
+// 1.Import module ES/CJS
 import xCrawl from 'x-crawl'
 
-// Create a crawler instance
-const docsXCrawl = xCrawl({
-  baseUrl: 'https://docs.github.com',
-  timeout: 10000,
-  intervalTime: { max: 2000, min: 1000 }
+// 2.Create a crawler instance
+const myXCrawl = xCrawl({
+  timeout: 10000, // overtime time
+  intervalTime: { max: 3000, min: 2000 } // control request frequency
 })
 
-// Call fetchHTML API to crawl
-docsXCrawl.fetchHTML('/zh/get-started').then((res) => {
-  const { jsdom } = res.data
-  console.log(jsdom.window.document.querySelector('title')?.textContent)
+// 3.Set the crawling task
+// Call the startPolling API to start the polling function, and the callback function will be called every other day
+myXCrawl.startPolling({ d: 1 }, () => {
+    // Call fetchHTML API to crawl HTML
+  myXCrawl.fetchHTML('https://www.youtube.com/').then((res) => {
+    const { jsdom } = res.data // By default, the JSDOM library is used to parse HTML
+
+    // Get the cover image element of the Promoted Video
+    const imgEls = jsdom.window.document.querySelectorAll(
+      '.yt-core-image--fill-parent-width'
+    )
+
+    // set request configuration
+    const requestConfig = []
+    imgEls.forEach((item) => {
+      if (item.src) {
+        requestConfig.push({ url: item.src })
+      }
+    })
+
+    // Call the fetchFile API to crawl pictures
+    myXCrawl.fetchFile({ requestConfig, fileConfig: { storeDir: './upload' } })
+  })
 })
+
 ```
 
+running result:
+
+<div align="center">
+  <img src="https://raw.githubusercontent.com/coder-hxl/x-crawl/main/assets/en/crawler.png" />
+</div>
+
+<div align="center">
+  <img src="https://raw.githubusercontent.com/coder-hxl/x-crawl/main/assets/en/crawler-result.png" />
+</div>
+
+**Note:** Do not crawl randomly, here is just to demonstrate how to use XCrawl, and control the request frequency within 3000ms to 2000ms.
+
 ## Core concepts
 
 ### x-crawl

assets/crawler-result.png renamed to assets/cn/crawler-result.png

@@ -78,8 +78,8 @@ import xCrawl from 'x-crawl'
 
 // 2.创建一个爬虫实例
 const myXCrawl = xCrawl({
-  timeout: 10000, // 超时时间
-  intervalTime: { max: 3000, min: 2000 } // 控制请求频率
+  timeout: 10000, // overtime time
+  intervalTime: { max: 3000, min: 2000 } // control request frequency
 })
 
 // 3.设置爬取任务
@@ -105,11 +105,11 @@ myXCrawl.startPolling({ d: 1 }, () => {
 运行效果:
 
 <div align="center">
-  <img src="https://raw.githubusercontent.com/coder-hxl/x-crawl/main/assets/crawler.png" />
+  <img src="https://raw.githubusercontent.com/coder-hxl/x-crawl/main/assets/cn/crawler.png" />
 </div>
 
 <div align="center">
-  <img src="https://raw.githubusercontent.com/coder-hxl/x-crawl/main/assets/crawler-result.png" />
+  <img src="https://raw.githubusercontent.com/coder-hxl/x-crawl/main/assets/cn/crawler-result.png" />
 </div>
 
 **注意:** 请勿随意爬取，这里只是为了演示如何使用 XCrawl ，并将请求频率控制在 3000ms 到 2000ms 内。

assets/crawler.png renamed to assets/cn/crawler.png

@@ -28,3 +28,31 @@ import xCrawl from '../../src'
 //     fileConfig: { storeDir: path.resolve(__dirname, 'upload') }
 //   })
 // })
+
+const myXCrawl = xCrawl({
+  timeout: 10000,
+  intervalTime: { max: 3000, min: 2000 },
+  proxy: 'http://127.0.0.1:14892'
+})
+
+myXCrawl.startPolling({ d: 1 }, () => {
+  myXCrawl.fetchHTML('https://www.youtube.com/').then((res) => {
+    const { jsdom } = res.data
+
+    const imgEls = jsdom.window.document.querySelectorAll<HTMLImageElement>(
+      '.yt-core-image--fill-parent-width'
+    )
+
+    const requestConfig: any[] = []
+    imgEls.forEach((item) => {
+      if (item.src) {
+        requestConfig.push({ url: item.src })
+      }
+    })
+
+    myXCrawl.fetchFile({
+      requestConfig,
+      fileConfig: { storeDir: path.resolve(__dirname, './upload') }
+    })
+  })
+})