AutomationFlowsWeb Scraping › Wf-discovery - Xhs内容发现

Wf-discovery - Xhs内容发现

WF-Discovery - XHS内容发现. Uses httpRequest. Scheduled trigger; 15 nodes.

Cron / scheduled trigger★★★★☆ complexity15 nodesHTTP Request
Web Scraping Trigger: Cron / scheduled Nodes: 15 Complexity: ★★★★☆ Added:

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

Download .json
{
  "name": "WF-Discovery - XHS\u5185\u5bb9\u53d1\u73b0",
  "nodes": [
    {
      "parameters": {
        "rule": {
          "interval": [
            {
              "field": "minutes",
              "minutesInterval": 30
            }
          ]
        }
      },
      "id": "schedule-trigger",
      "name": "Schedule Trigger",
      "type": "n8n-nodes-base.scheduleTrigger",
      "typeVersion": 1.2,
      "position": [
        250,
        300
      ],
      "notes": "\u6bcf30\u5206\u949f\u81ea\u52a8\u6267\u884c"
    },
    {
      "parameters": {
        "httpMethod": "POST",
        "path": "xhs-discovery",
        "responseMode": "responseNode"
      },
      "id": "webhook-trigger",
      "name": "Webhook Trigger",
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 2,
      "position": [
        250,
        500
      ],
      "notes": "\u624b\u52a8\u89e6\u53d1\u5165\u53e3"
    },
    {
      "parameters": {
        "method": "POST",
        "url": "https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal",
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "app_id",
              "value": "={{ $env.LARK_APP_ID }}"
            },
            {
              "name": "app_secret",
              "value": "={{ $env.LARK_APP_SECRET }}"
            }
          ]
        },
        "options": {}
      },
      "id": "get-lark-token",
      "name": "Get Lark Token",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        500,
        400
      ],
      "notes": "\u83b7\u53d6\u98de\u4e66\u8bbf\u95ee\u4ee4\u724c"
    },
    {
      "parameters": {
        "method": "GET",
        "url": "={{ 'https://open.feishu.cn/open-apis/bitable/v1/apps/' + $env.LARK_APP_TOKEN + '/tables/' + $env.LARK_KEYWORDS_TABLE_ID + '/records' }}",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Authorization",
              "value": "=Bearer {{ $node['Get Lark Token'].json.tenant_access_token }}"
            }
          ]
        },
        "sendQuery": true,
        "queryParameters": {
          "parameters": [
            {
              "name": "filter",
              "value": "CurrentValue.[status]=\"\u5f85\u91c7\u96c6\""
            },
            {
              "name": "page_size",
              "value": "5"
            }
          ]
        },
        "options": {}
      },
      "id": "query-keywords",
      "name": "Query Keywords",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        750,
        400
      ],
      "notes": "\u67e5\u8be2\u5f85\u91c7\u96c6\u7684\u5173\u952e\u8bcd"
    },
    {
      "parameters": {
        "conditions": {
          "options": {
            "caseSensitive": true,
            "leftValue": "",
            "typeValidation": "strict"
          },
          "conditions": [
            {
              "id": "check-records",
              "leftValue": "={{ $json.data.items.length }}",
              "rightValue": "0",
              "operator": {
                "type": "number",
                "operation": "gt"
              }
            }
          ],
          "combinator": "and"
        },
        "options": {}
      },
      "id": "check-has-keywords",
      "name": "Has Keywords?",
      "type": "n8n-nodes-base.if",
      "typeVersion": 2,
      "position": [
        1000,
        400
      ],
      "notes": "\u68c0\u67e5\u662f\u5426\u6709\u5f85\u91c7\u96c6\u5173\u952e\u8bcd"
    },
    {
      "parameters": {
        "jsCode": "// \u63d0\u53d6\u5173\u952e\u8bcd\u5217\u8868\nconst items = $input.first().json.data.items || [];\n\nconst keywords = items.map(item => ({\n  record_id: item.record_id,\n  keyword: item.fields.keyword,\n  category: item.fields.category,\n  min_likes: item.fields.min_likes || 100,\n  crawl_limit: item.fields.crawl_limit || 10\n}));\n\nreturn keywords.map(k => ({ json: k }));"
      },
      "id": "extract-keywords",
      "name": "Extract Keywords",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1250,
        300
      ],
      "notes": "\u63d0\u53d6\u5173\u952e\u8bcd\u6570\u636e"
    },
    {
      "parameters": {
        "method": "PATCH",
        "url": "={{ 'https://open.feishu.cn/open-apis/bitable/v1/apps/' + $env.LARK_APP_TOKEN + '/tables/' + $env.LARK_KEYWORDS_TABLE_ID + '/records/' + $json.record_id }}",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Authorization",
              "value": "=Bearer {{ $node['Get Lark Token'].json.tenant_access_token }}"
            }
          ]
        },
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "={\n  \"fields\": {\n    \"status\": \"\u91c7\u96c6\u4e2d\",\n    \"locked_at\": \"{{ $now.toISO() }}\"\n  }\n}",
        "options": {}
      },
      "id": "lock-keyword",
      "name": "Lock Keyword",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        1500,
        300
      ],
      "notes": "\u9501\u5b9a\u5173\u952e\u8bcd\u72b6\u6001\u4e3a\u91c7\u96c6\u4e2d"
    },
    {
      "parameters": {
        "method": "POST",
        "url": "={{ $env.CRAWLER_API_URL + '/api/search/human' }}",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "X-API-Key",
              "value": "={{ $env.CRAWLER_API_KEY }}"
            }
          ]
        },
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "={\n  \"keyword\": \"{{ $node['Extract Keywords'].json.keyword }}\",\n  \"limit\": {{ $node['Extract Keywords'].json.crawl_limit }}\n}",
        "options": {
          "timeout": 60000
        }
      },
      "id": "search-xhs",
      "name": "Search XHS",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        1750,
        300
      ],
      "notes": "\u8c03\u7528\u722c\u866bAPI\u641c\u7d22\u5c0f\u7ea2\u4e66"
    },
    {
      "parameters": {
        "conditions": {
          "options": {
            "caseSensitive": true,
            "leftValue": "",
            "typeValidation": "strict"
          },
          "conditions": [
            {
              "id": "check-success",
              "leftValue": "={{ $json.success }}",
              "rightValue": true,
              "operator": {
                "type": "boolean",
                "operation": "equals"
              }
            }
          ],
          "combinator": "and"
        },
        "options": {}
      },
      "id": "check-search-result",
      "name": "Search Success?",
      "type": "n8n-nodes-base.if",
      "typeVersion": 2,
      "position": [
        2000,
        300
      ],
      "notes": "\u68c0\u67e5\u641c\u7d22\u662f\u5426\u6210\u529f"
    },
    {
      "parameters": {
        "jsCode": "// \u8f6c\u6362\u641c\u7d22\u7ed3\u679c\u4e3a\u98de\u4e66\u8bb0\u5f55\u683c\u5f0f\nconst searchResult = $input.first().json;\nconst keywordData = $node['Extract Keywords'].json;\nconst items = searchResult.data?.items || [];\nconst minLikes = keywordData.min_likes || 0;\n\n// \u8fc7\u6ee4\u4f4e\u4e8e\u6700\u4f4e\u70b9\u8d5e\u6570\u7684\u7b14\u8bb0\nconst filteredItems = items.filter(item => {\n  const likes = parseInt(item.likes) || 0;\n  return likes >= minLikes;\n});\n\n// \u8f6c\u6362\u4e3a\u98de\u4e66\u8bb0\u5f55\u683c\u5f0f\nconst records = filteredItems.map(item => ({\n  fields: {\n    keyword_id: keywordData.record_id,\n    note_id: item.note_id,\n    title: item.title || '',\n    author: item.author || '',\n    likes: parseInt(item.likes) || 0,\n    cover_url: item.cover || '',\n    status: '\u5f85\u63d0\u53d6',\n    crawled_at: new Date().toISOString()\n  }\n}));\n\nreturn [{ json: { records, keyword_record_id: keywordData.record_id, total: records.length } }];"
      },
      "id": "transform-results",
      "name": "Transform Results",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        2250,
        200
      ],
      "notes": "\u8f6c\u6362\u641c\u7d22\u7ed3\u679c\u683c\u5f0f"
    },
    {
      "parameters": {
        "method": "POST",
        "url": "={{ 'https://open.feishu.cn/open-apis/bitable/v1/apps/' + $env.LARK_APP_TOKEN + '/tables/' + $env.LARK_TOPICS_TABLE_ID + '/records/batch_create' }}",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Authorization",
              "value": "=Bearer {{ $node['Get Lark Token'].json.tenant_access_token }}"
            }
          ]
        },
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "={{ JSON.stringify({ records: $json.records }) }}",
        "options": {}
      },
      "id": "save-to-topics",
      "name": "Save to Topics",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        2500,
        200
      ],
      "notes": "\u6279\u91cf\u5199\u5165Topics\u8868"
    },
    {
      "parameters": {
        "method": "PATCH",
        "url": "={{ 'https://open.feishu.cn/open-apis/bitable/v1/apps/' + $env.LARK_APP_TOKEN + '/tables/' + $env.LARK_KEYWORDS_TABLE_ID + '/records/' + $json.keyword_record_id }}",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Authorization",
              "value": "=Bearer {{ $node['Get Lark Token'].json.tenant_access_token }}"
            }
          ]
        },
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "={\n  \"fields\": {\n    \"status\": \"\u5df2\u91c7\u96c6\",\n    \"last_crawl_time\": \"{{ $now.toISO() }}\",\n    \"locked_at\": null\n  }\n}",
        "options": {}
      },
      "id": "update-keyword-success",
      "name": "Update Keyword Success",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        2750,
        200
      ],
      "notes": "\u66f4\u65b0\u5173\u952e\u8bcd\u72b6\u6001\u4e3a\u5df2\u91c7\u96c6"
    },
    {
      "parameters": {
        "method": "PATCH",
        "url": "={{ 'https://open.feishu.cn/open-apis/bitable/v1/apps/' + $env.LARK_APP_TOKEN + '/tables/' + $env.LARK_KEYWORDS_TABLE_ID + '/records/' + $node['Extract Keywords'].json.record_id }}",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Authorization",
              "value": "=Bearer {{ $node['Get Lark Token'].json.tenant_access_token }}"
            }
          ]
        },
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "={\n  \"fields\": {\n    \"status\": \"\u91c7\u96c6\u5931\u8d25\",\n    \"error_message\": \"{{ $json.error?.message || 'Unknown error' }}\",\n    \"locked_at\": null\n  }\n}",
        "options": {}
      },
      "id": "update-keyword-failed",
      "name": "Update Keyword Failed",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        2250,
        400
      ],
      "notes": "\u66f4\u65b0\u5173\u952e\u8bcd\u72b6\u6001\u4e3a\u91c7\u96c6\u5931\u8d25"
    },
    {
      "parameters": {
        "respondWith": "json",
        "responseBody": "={{ { success: true, message: 'Discovery completed', total: $json.total || 0 } }}"
      },
      "id": "respond-success",
      "name": "Respond Success",
      "type": "n8n-nodes-base.respondToWebhook",
      "typeVersion": 1.1,
      "position": [
        3000,
        200
      ],
      "notes": "\u8fd4\u56de\u6210\u529f\u54cd\u5e94"
    },
    {
      "parameters": {
        "respondWith": "json",
        "responseBody": "={{ { success: false, message: 'No keywords to process' } }}"
      },
      "id": "respond-no-keywords",
      "name": "Respond No Keywords",
      "type": "n8n-nodes-base.respondToWebhook",
      "typeVersion": 1.1,
      "position": [
        1250,
        500
      ],
      "notes": "\u65e0\u5173\u952e\u8bcd\u65f6\u8fd4\u56de"
    }
  ],
  "connections": {
    "Schedule Trigger": {
      "main": [
        [
          {
            "node": "Get Lark Token",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Webhook Trigger": {
      "main": [
        [
          {
            "node": "Get Lark Token",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get Lark Token": {
      "main": [
        [
          {
            "node": "Query Keywords",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Query Keywords": {
      "main": [
        [
          {
            "node": "Has Keywords?",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Has Keywords?": {
      "main": [
        [
          {
            "node": "Extract Keywords",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Respond No Keywords",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Keywords": {
      "main": [
        [
          {
            "node": "Lock Keyword",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Lock Keyword": {
      "main": [
        [
          {
            "node": "Search XHS",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Search XHS": {
      "main": [
        [
          {
            "node": "Search Success?",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Search Success?": {
      "main": [
        [
          {
            "node": "Transform Results",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Update Keyword Failed",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Transform Results": {
      "main": [
        [
          {
            "node": "Save to Topics",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Save to Topics": {
      "main": [
        [
          {
            "node": "Update Keyword Success",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Update Keyword Success": {
      "main": [
        [
          {
            "node": "Respond Success",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {
    "executionOrder": "v1"
  },
  "staticData": null,
  "tags": [
    {
      "name": "XHS-Pipeline"
    }
  ],
  "triggerCount": 2
}
Pro

For the full experience including quality scoring and batch install features for each workflow upgrade to Pro

About this workflow

WF-Discovery - XHS内容发现. Uses httpRequest. Scheduled trigger; 15 nodes.

Source: https://github.com/wade56754/XHS/blob/b5b999f35721bcfe8ffc6b518245e1d8dbaab5c5/workflows/WF-Discovery.json — original creator credit. Request a take-down →

More Web Scraping workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.

Web Scraping

As n8n instances scale, teams often lose track of sub-workflows—who uses them, where they are referenced, and whether they can be safely updated. This leads to inefficiencies like unnecessary copies o

HTTP Request, n8n, N8N Trigger +1
Web Scraping

This workflow is an improvement of this workflow by Greg Brzezinka.

HTTP Request, Email Send, XML +1
Web Scraping

N8N-Workflow-Github-Manager. Uses github, httpRequest, n8n. Scheduled trigger; 38 nodes.

GitHub, HTTP Request, n8n
Web Scraping

This workflow uses KlickTipp community nodes, available for self-hosted n8n instances only.

N8N Nodes Klicktipp, Salesforce, Salesforce Trigger +1
Web Scraping

This workflow acts as an automated engagement bot. It sends a Direct Message (DM) with a link or resource to any follower who replies to your post with a specific target keyword.

HTTP Request