Add agent component for web crawler (#2878)

### What problem does this PR solve?

Add agent component for  web crawler

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

web/src/assets/svg/crawler.svg

@@ -0,0 +1 @@
+<?xml version="1.0" standalone="no"?><!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"><svg class="icon" width="200px" height="200.00px" viewBox="0 0 1024 1024" version="1.1" xmlns="http://www.w3.org/2000/svg"><path d="M 777.121 313.158 a 265.121 265.121 0 0 0 -530.243 0 Z m 165.7 265.121 H 843.402 V 425.836 l 84.176 -84.176 a 33.1402 33.1402 0 1 0 -47.0591 -47.0591 l -66.2803 66.2803 h -596.524 l -66.2803 -66.2803 a 33.1402 33.1402 0 1 0 -47.0591 47.0591 L 180.598 425.836 V 578.281 H 81.177 a 33.1402 33.1402 0 0 0 0 66.2803 H 180.598 v 33.1402 a 294.285 294.285 0 0 0 39.7682 145.817 l -96.1069 95.4441 a 33.1402 33.1402 0 0 0 47.0591 47.0591 l 88.8157 -88.1529 A 296.937 296.937 0 0 0 478.859 975.959 h 3.97682 V 401.974 h 66.2803 V 975.959 a 296.937 296.937 0 0 0 215.411 -98.0944 l 88.8157 88.8157 a 33.1402 33.1402 0 0 0 47.0591 -47.0591 l -93.4554 -93.4554 a 293.621 293.621 0 0 0 36.4542 -149.131 V 644.561 h 99.4209 a 33.1402 33.1402 0 0 0 0 -66.2803 Z" fill="#1B69FD" /></svg>

web/src/locales/en.ts

@@ -928,6 +928,16 @@ The above is the content you need to summarize.`,
       yahooFinance: 'YahooFinance',
       yahooFinanceDescription:
         'The component queries information about the company based on the provided ticker symbol.',
+      crawler: 'Web Crawler',
+      crawlerDescription:
+        'This component can be used to crawl HTML source code from a specified URL.',
+      proxy: 'Proxy',
+      crawlerResultOptions: {
+        html: 'Html',
+        markdown: 'Markdown',
+        content: 'Content',
+      },
+      extractType: 'extractType',
       info: 'Info',
       history: 'History',
       financials: 'Financials',

web/src/locales/zh-traditional.ts

@@ -877,6 +877,15 @@ export default {
       akShareDescription: '此組件可用於從東方財富網取得對應股票的新聞資訊。',
       yahooFinance: '雅虎財經',
       yahooFinanceDescription: '該組件根據提供的股票代碼查詢有關公司的資訊。',
+      crawler: '網頁爬蟲',
+      crawlerDescription: '該組件可用於從指定url爬取HTML源碼。',
+      proxy: '代理',
+      crawlerResultOptions: {
+        html: 'Html',
+        markdown: 'Markdown',
+        content: '文本',
+      },
+      extractType: '提取類型',
       info: '訊息',
       history: '歷史',
       financials: '財務',

web/src/locales/zh.ts

@@ -897,6 +897,15 @@ export default {
       akShareDescription: '该组件可用于从东方财富网站获取相应股票的新闻信息。',
       yahooFinance: '雅虎财经',
       yahooFinanceDescription: '该组件根据提供的股票代码查询有关公司的信息。',
+      crawler: '网页爬虫',
+      crawlerDescription: '该组件可用于从指定url爬取html源码。',
+      proxy: '代理',
+      crawlerResultOptions: {
+        html: 'Html',
+        markdown: 'Markdown',
+        content: '文本',
+      },
+      extractType: '提取类型',
       info: '信息',
       history: '历史',
       financials: '财务',

web/src/pages/flow/constant.tsx

@@ -4,6 +4,7 @@ import { ReactComponent as baiduFanyiIcon } from '@/assets/svg/baidu-fanyi.svg';
 import { ReactComponent as BaiduIcon } from '@/assets/svg/baidu.svg';
 import { ReactComponent as BingIcon } from '@/assets/svg/bing.svg';
 import { ReactComponent as ConcentratorIcon } from '@/assets/svg/concentrator.svg';
+import { ReactComponent as CrawlerIcon } from '@/assets/svg/crawler.svg';
 import { ReactComponent as DeepLIcon } from '@/assets/svg/deepl.svg';
 import { ReactComponent as DuckIcon } from '@/assets/svg/duck.svg';
 import { ReactComponent as ExeSqlIcon } from '@/assets/svg/exesql.svg';
@@ -73,6 +74,7 @@ export enum Operator {
   Concentrator = 'Concentrator',
   TuShare = 'TuShare',
   Note = 'Note',
+  Crawler = 'Crawler',
 }
 
 export const CommonOperatorList = Object.values(Operator).filter(
@@ -110,6 +112,7 @@ export const operatorIconMap = {
   [Operator.Concentrator]: ConcentratorIcon,
   [Operator.TuShare]: TuShareIcon,
   [Operator.Note]: NoteIcon,
+  [Operator.Crawler]: CrawlerIcon,
 };
 
 export const operatorMap: Record<
@@ -233,6 +236,9 @@ export const operatorMap: Record<
   },
   [Operator.TuShare]: { backgroundColor: '#f8cfa0' },
   [Operator.Note]: { backgroundColor: '#f8cfa0' },
+  [Operator.Crawler]: {
+    backgroundColor: '#dee0e2',
+  },
 };
 
 export const componentMenuList = [
@@ -323,6 +329,9 @@ export const componentMenuList = [
   {
     name: Operator.TuShare,
   },
+  {
+    name: Operator.Crawler,
+  },
 ];
 
 export const initialRetrievalValues = {
@@ -572,6 +581,7 @@ export const RestrictedUpstreamMap = {
   [Operator.Jin10]: [Operator.Begin],
   [Operator.Concentrator]: [Operator.Begin],
   [Operator.TuShare]: [Operator.Begin],
+  [Operator.Crawler]: [Operator.Begin],
 };
 
 export const NodeMap = {
@@ -605,6 +615,7 @@ export const NodeMap = {
   [Operator.Jin10]: 'ragNode',
   [Operator.TuShare]: 'ragNode',
   [Operator.Note]: 'noteNode',
+  [Operator.Crawler]: 'ragNode',
 };
 
 export const LanguageOptions = [
@@ -2791,3 +2802,4 @@ export const TuShareSrcOptions = [
   'fenghuang',
   'jinrongjie',
 ];
+export const CrawlerResultOptions = ['markdown', 'html', 'content'];

web/src/pages/flow/flow-drawer/index.tsx

@@ -12,6 +12,7 @@ import BaiduForm from '../form/baidu-form';
 import BeginForm from '../form/begin-form';
 import BingForm from '../form/bing-form';
 import CategorizeForm from '../form/categorize-form';
+import CrawlerForm from '../form/crawler-form';
 import DeepLForm from '../form/deepl-form';
 import DuckDuckGoForm from '../form/duckduckgo-form';
 import ExeSQLForm from '../form/exesql-form';
@@ -70,6 +71,7 @@ const FormMap = {
   [Operator.YahooFinance]: YahooFinanceForm,
   [Operator.Jin10]: Jin10Form,
   [Operator.TuShare]: TuShareForm,
+  [Operator.Crawler]: CrawlerForm,
 };
 
 const EmptyContent = () => <div>empty</div>;

web/src/pages/flow/form/crawler-form/index.tsx

@@ -0,0 +1,37 @@
+import { useTranslate } from '@/hooks/common-hooks';
+import { Form, Input, Select } from 'antd';
+import { useMemo } from 'react';
+import { CrawlerResultOptions } from '../../constant';
+import { IOperatorForm } from '../../interface';
+const CrawlerForm = ({ onValuesChange, form }: IOperatorForm) => {
+  const { t } = useTranslate('flow');
+  const crawlerResultOptions = useMemo(() => {
+    return CrawlerResultOptions.map((x) => ({
+      value: x,
+      label: t(`crawlerResultOptions.${x}`),
+    }));
+  }, [t]);
+  return (
+    <Form
+      name="basic"
+      labelCol={{ span: 6 }}
+      wrapperCol={{ span: 18 }}
+      autoComplete="off"
+      form={form}
+      onValuesChange={onValuesChange}
+    >
+      <Form.Item label={t('proxy')} name={'proxy'}>
+        <Input placeholder="like: http://127.0.0.1:8888"></Input>
+      </Form.Item>
+      <Form.Item
+        label={t('extractType')}
+        name={'extract_type'}
+        initialValue="markdown"
+      >
+        <Select options={crawlerResultOptions}></Select>
+      </Form.Item>
+    </Form>
+  );
+};
+
+export default CrawlerForm;