feat: support firecrawl frontend code (#5226)

web/i18n/en-US/common.ts

@@ -37,6 +37,10 @@ const translation = {
     duplicate: 'Duplicate',
     rename: 'Rename',
   },
+  errorMsg: {
+    fieldRequired: '{{field}} is required',
+    urlError: 'url should start with http:// or https://',
+  },
   placeholder: {
     input: 'Please enter',
     select: 'Please select',
@@ -360,6 +364,7 @@ const translation = {
   dataSource: {
     add: 'Add a data source',
     connect: 'Connect',
+    configure: 'Configure',
     notion: {
       title: 'Notion',
       description: 'Using Notion as a data source for the Knowledge.',
@@ -379,6 +384,14 @@ const translation = {
         preview: 'PREVIEW',
       },
     },
+    website: {
+      title: 'Website',
+      description: 'Import content from websites using web crawler.',
+      with: 'With',
+      configuredCrawlers: 'Configured crawlers',
+      active: 'Active',
+      inactive: 'Inactive',
+    },
   },
   plugin: {
     serpapi: {

web/i18n/en-US/dataset-creation.ts

@@ -11,6 +11,12 @@ const translation = {
   error: {
     unavailable: 'This Knowledge is not available',
   },
+  firecrawl: {
+    configFirecrawl: 'Configure 🔥Firecrawl',
+    apiKeyPlaceholder: 'API key from firecrawl.dev, starting with "fc-"',
+    apiKeyFormatError: 'API key should start with "fc-"',
+    getApiKeyLinkText: 'Get your API key from firecrawl.dev',
+  },
   stepOne: {
     filePreview: 'File Preview',
     pagePreview: 'Page Preview',
@@ -50,6 +56,30 @@ const translation = {
       confirmButton: 'Create',
       failed: 'Creation failed',
     },
+    website: {
+      fireCrawlNotConfigured: 'Firecrawl is not configured',
+      fireCrawlNotConfiguredDescription: 'Configure Firecrawl with API key to use it.',
+      configure: 'Configure',
+      run: 'Run',
+      firecrawlTitle: 'Extract web content with 🔥Firecrawl',
+      firecrawlDoc: 'Firecrawl docs',
+      firecrawlDocLink: 'https://docs.dify.ai/guides/knowledge-base/sync_from_website',
+      options: 'Options',
+      crawlSubPage: 'Crawl sub-pages',
+      limit: 'Limit',
+      maxDepth: 'Max depth',
+      excludePaths: 'Exclude paths',
+      includeOnlyPaths: 'Include only paths',
+      extractOnlyMainContent: 'Extract only main content (no headers, navs, footers, etc.)',
+      exceptionErrorTitle: 'An exception occurred while running Firecrawl job:',
+      unknownError: 'Unknown error',
+      totalPageScraped: 'Total pages scraped:',
+      selectAll: 'Select All',
+      resetAll: 'Reset All',
+      scrapTimeInfo: 'Scraped {{total}} pages in total within {{time}}s',
+      preview: 'Preview',
+      maxDepthTooltip: 'Maximum depth to crawl. Depth 1 is the base URL, depth 2 includes the base URL and its direct children, and so on.',
+    },
   },
   stepTwo: {
     segmentation: 'Chunk settings',
@@ -86,9 +116,11 @@ const translation = {
     calculating: 'Calculating...',
     fileSource: 'Preprocess documents',
     notionSource: 'Preprocess pages',
+    websiteSource: 'Preprocess website',
     other: 'and other ',
     fileUnit: ' files',
     notionUnit: ' pages',
+    webpageUnit: ' pages',
     previousStep: 'Previous step',
     nextStep: 'Save & Process',
     save: 'Save & Process',

web/i18n/en-US/dataset-documents.ts

@@ -2,8 +2,9 @@ const translation = {
   list: {
     title: 'Documents',
     desc: 'All files of the Knowledge are shown here, and the entire Knowledge can be linked to Dify citations or indexed via the Chat plugin.',
-    addFile: 'add file',
+    addFile: 'Add file',
     addPages: 'Add Pages',
+    addUrl: 'Add URL',
     table: {
       header: {
         fileName: 'FILE NAME',

web/i18n/zh-Hans/common.ts

@@ -37,6 +37,10 @@ const translation = {
     duplicate: '复制',
     rename: '重命名',
   },
+  errorMsg: {
+    fieldRequired: '{{field}} 为必填项',
+    urlError: 'url 应该以 http:// 或 https:// 开头',
+  },
   placeholder: {
     input: '请输入',
     select: '请选择',
@@ -356,6 +360,7 @@ const translation = {
   dataSource: {
     add: '添加数据源',
     connect: '绑定',
+    configure: '配置',
     notion: {
       title: 'Notion',
       description: '使用 Notion 作为知识库的数据源。',
@@ -375,6 +380,14 @@ const translation = {
         preview: '预览',
       },
     },
+    website: {
+      title: '网站',
+      description: '使用网络爬虫从网站导入内容。',
+      with: '使用',
+      configuredCrawlers: '已配置的爬虫',
+      active: '可用',
+      inactive: '不可用',
+    },
   },
   plugin: {
     serpapi: {

web/i18n/zh-Hans/dataset-creation.ts

@@ -11,6 +11,12 @@ const translation = {
   error: {
     unavailable: '该知识库不可用',
   },
+  firecrawl: {
+    configFirecrawl: '配置 🔥Firecrawl',
+    apiKeyPlaceholder: '从 firecrawl.dev 获取 API Key，以 "fc-" 开头',
+    apiKeyFormatError: 'API Key 应以 "fc-" 开头',
+    getApiKeyLinkText: '从 firecrawl.dev 获取您的 API Key',
+  },
   stepOne: {
     filePreview: '文件预览',
     pagePreview: '页面预览',
@@ -50,6 +56,30 @@ const translation = {
       confirmButton: '创建',
       failed: '创建失败',
     },
+    website: {
+      fireCrawlNotConfigured: 'Firecrawl 未配置',
+      fireCrawlNotConfiguredDescription: '请配置 Firecrawl 的 API 密钥以使用它。',
+      configure: '配置',
+      run: '运行',
+      firecrawlTitle: '使用 🔥Firecrawl 提取网页内容',
+      firecrawlDoc: 'Firecrawl 文档',
+      firecrawlDocLink: 'https://docs.dify.ai/v/zh-hans/guides/knowledge-base/sync_from_website',
+      options: '选项',
+      crawlSubPage: '爬取子页面',
+      limit: '限制数量',
+      maxDepth: '最大深度',
+      excludePaths: '排除路径',
+      includeOnlyPaths: '仅包含路径',
+      extractOnlyMainContent: '仅提取主要内容（无标题、导航、页脚等）',
+      exceptionErrorTitle: '运行 Firecrawl 时发生异常:',
+      unknownError: '未知错误',
+      totalPageScraped: '抓取页面总数:',
+      selectAll: '全选',
+      resetAll: '重置全部',
+      scrapTimeInfo: '总共在 {{time}}秒 内抓取了 {{total}} 个页面',
+      preview: '预览',
+      maxDepthTooltip: '最大抓取深度。深度 1 表示 Base URL，深度 2 表示 Base URL及其直接子页面，依此类推。',
+    },
   },
   stepTwo: {
     segmentation: '分段设置',
@@ -86,9 +116,11 @@ const translation = {
     calculating: '计算中...',
     fileSource: '预处理文档',
     notionSource: '预处理页面',
+    websiteSource: '预处理页面',
     other: '和其他 ',
     fileUnit: ' 个文件',
     notionUnit: ' 个页面',
+    webpageUnit: ' 个页面',
     previousStep: '上一步',
     nextStep: '保存并处理',
     save: '保存并处理',

web/i18n/zh-Hans/dataset-documents.ts

@@ -4,6 +4,7 @@ const translation = {
     desc: '知识库的所有文件都在这里显示，整个知识库都可以链接到 Dify 引用或通过 Chat 插件进行索引。',
     addFile: '添加文件',
     addPages: '添加页面',
+    addUrl: '添加 URL',
     table: {
       header: {
         fileName: '文件名',