Robot de résumé FireCrawl

Intermédiaire

Ceci est unAI, Marketingworkflow d'automatisation du domainecontenant 10 nœuds.Utilise principalement des nœuds comme Code, Slack, HttpRequest, Agent, ScheduleTrigger, combinant la technologie d'intelligence artificielle pour une automatisation intelligente. Robot de renseignement du marché alimenté par Firecrawl AI : livraison automatique d'informations d'actualité

Prérequis
  • Token Bot Slack ou URL Webhook
  • Peut nécessiter les informations d'identification d'authentification de l'API cible
  • Clé API OpenAI
Aperçu du workflow
Visualisation des connexions entre les nœuds, avec support du zoom et du déplacement
Exporter le workflow
Copiez la configuration JSON suivante dans n8n pour importer et utiliser ce workflow
{
  "id": "iTYjhgQEFE4ap1c8",
  "meta": {
    "instanceId": "84ad02d6104594179f43f1ce9cfe3a81637b2faedb57dafcb9e649b7542988db",
    "templateCredsSetupCompleted": true
  },
  "name": "FireCrawl Summary Bot",
  "tags": [],
  "nodes": [
    {
      "id": "471044c1-cafd-4810-973d-b40c74ef6999",
      "name": "Déclencheur de Recherche Quotidienne du Marché",
      "type": "n8n-nodes-base.scheduleTrigger",
      "position": [
        -160,
        0
      ],
      "parameters": {
        "rule": {
          "interval": [
            {
              "triggerAtHour": 8
            }
          ]
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "8f6e97b6-6910-4c6b-8c9a-29a0cf95ac09",
      "name": "Exploration TechCrunch (FireCrawl)",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        140,
        0
      ],
      "parameters": {
        "url": "https://api.firecrawl.dev/v1/crawl",
        "method": "POST",
        "options": {},
        "sendBody": true,
        "sendHeaders": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "url",
              "value": "https://techcrunch.com"
            },
            {
              "name": "crawl_type",
              "value": "scrape"
            },
            {
              "name": "extract_article",
              "value": "true"
            }
          ]
        },
        "headerParameters": {
          "parameters": [
            {
              "name": "Authorization",
              "value": "Bearer YOUR_FIRECRAWL_API_KEY"
            }
          ]
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "7d446441-d882-4816-805e-2d52cd8aea87",
      "name": "Filtrage des Articles Pertinents",
      "type": "n8n-nodes-base.code",
      "position": [
        360,
        0
      ],
      "parameters": {
        "jsCode": "const keywords = ['AI', 'machine learning', 'startup', 'generative'];\nconst results = [];\n\nfor (const item of items) {\n  const title = item.json.article?.title?.toLowerCase() || '';\n  const content = item.json.article?.content?.toLowerCase() || '';\n\n  const isRelevant = keywords.some(keyword =>\n    title.includes(keyword.toLowerCase()) ||\n    content.includes(keyword.toLowerCase())\n  );\n\n  if (isRelevant) {\n    results.push(item); // keep only relevant articles\n  }\n}\n\nreturn results;\n"
      },
      "typeVersion": 2
    },
    {
      "id": "a326e8fd-bfc8-4380-9c66-20481aaa8a6c",
      "name": "Agent de Synthèse",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        700,
        0
      ],
      "parameters": {
        "text": "=Summarize the following article in 3 bullet points:\nTitle: {{ $json.article.title }}\ndescription: {{ $json.meta.description }}\nContent: {{ $json.article.content }}",
        "options": {},
        "promptType": "define"
      },
      "typeVersion": 1.9
    },
    {
      "id": "d8576228-6261-4654-84de-0864e398c22d",
      "name": "OpenAI Summarizer",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        640,
        240
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "wYwTjEv45IzlAOAu",
          "name": "OpenAi account 2"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "f5965b4a-4ab1-4e5f-868c-2dc11c59fc28",
      "name": "Envoyer le Résumé à Slack",
      "type": "n8n-nodes-base.slack",
      "position": [
        1060,
        0
      ],
      "webhookId": "c2e00b18-42bd-49b7-bc4c-05d60633a7c8",
      "parameters": {
        "text": "=🔍 AI Research Summary: \nTitle: {{ $('Filter Relevant Articles').item.json.article.title }}\nLink: {{ $('Filter Relevant Articles').item.json.url }}\nSummary: {{ $json.output }}",
        "select": "channel",
        "channelId": {
          "__rl": true,
          "mode": "list",
          "value": "C08TTV0CC3E",
          "cachedResultName": "all-nathing"
        },
        "otherOptions": {}
      },
      "credentials": {
        "slackApi": {
          "id": "L2vpqY0w5ba50NlR",
          "name": "Slack account 2"
        }
      },
      "typeVersion": 2.3
    },
    {
      "id": "295fae17-e75e-47db-a321-0379899f44cc",
      "name": "Note Adhésive",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        80,
        -580
      ],
      "parameters": {
        "color": 3,
        "width": 440,
        "height": 800,
        "content": "🌐💻 2. Crawling & Filtering\nNodes:\n🌐 Crawl TechCrunch (FireCrawl) (HTTP Request)\n\n🧠 Filter Relevant Articles (Code)\n\n🔍 What these nodes do:\n🌐 Crawl TechCrunch (FireCrawl)\nUses a POST request to FireCrawl’s API\n\nInputs:\n\nurl: Target site (e.g., https://techcrunch.com)\n\ncrawl_type: \"scrape\"\n\nextract_article: true\n\nRetrieves:\n\ntitle, content, author, published_at\n\n🧠 Filter Relevant Articles\nUses a Code node to check if the article is relevant\n\nKeywords like \"AI\", \"machine learning\", \"startup\" are matched\n\nFilters only the articles that matter to your domain"
      },
      "typeVersion": 1
    },
    {
      "id": "5fe2fbcc-8489-42cf-a578-48a46f18977d",
      "name": "Note Adhésive1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        580,
        -540
      ],
      "parameters": {
        "color": 5,
        "width": 640,
        "height": 920,
        "content": "🤖💬 3. Summarization & Delivery\nNodes:\n🧠 Summarize Article with AI (AI Agent)\n\n🔗 OpenAI Chat (Summarizer) (OpenAI Chat Model)\n\n💬 Send Summary to Slack (Slack)\n\n📌 What happens here:\n🤖 Summarize Article with AI\nPasses the article to a GPT-4 or GPT-3.5 agent\n\nUses a prompt like:\n\n“Summarize the following article in 3 bullet points…”\n\n💡 OpenAI Chat (Summarizer)\nExecutes the actual summarization\n\nOutputs a short, clean summary ideal for fast reading\n\n💬 Send Summary to Slack\nPosts the summary to a specific Slack channel (e.g., #market-research)"
      },
      "typeVersion": 1
    },
    {
      "id": "97ecbbb2-e763-47f0-82b8-2fede05b486f",
      "name": "Note Adhésive9",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -2100,
        -560
      ],
      "parameters": {
        "color": 4,
        "width": 1300,
        "height": 320,
        "content": "=======================================\n            WORKFLOW ASSISTANCE\n=======================================\nFor any questions or support, please contact:\n    Yaron@nofluff.online\n\nExplore more tips and tutorials here:\n   - YouTube: https://www.youtube.com/@YaronBeen/videos\n   - LinkedIn: https://www.linkedin.com/in/yaronbeen/\n=======================================\n"
      },
      "typeVersion": 1
    },
    {
      "id": "d28d5f04-db81-4833-869f-158b4586a337",
      "name": "Note Adhésive4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -2100,
        -220
      ],
      "parameters": {
        "color": 4,
        "width": 1289,
        "height": 2758,
        "content": "Absolutely! Here's your **Market Research Automation Workflow** beautifully divided into logical sections, with clear explanations and fitting icons to help you grasp each part at a glance.\n\n---\n\n# 🚀 **n8n Market Research Automation Workflow**\n\nAutomate the process of **crawling news sites**, **filtering for relevant content**, **summarizing it with AI**, and **posting it to Slack** — all in a seamless flow.\n\n---\n\n## ⏰ 1. **Trigger & Scheduling**\n\n**Node:** `🕒 Daily Market Research Trigger`\n\n> Starts the workflow on a recurring schedule.\n\n🔧 **What it does:**\n\n* Runs every morning (or your defined time)\n* Ensures your team receives fresh updates daily\n\n📅 **Example Cron Setting:**\n\n* Every day at 8:00 AM\n\n---\n\n## 🌐💻 2. **Crawling & Filtering**\n\n### **Nodes:**\n\n* `🌐 Crawl TechCrunch (FireCrawl)` *(HTTP Request)*\n* `🧠 Filter Relevant Articles` *(Code)*\n\n### 🔍 What these nodes do:\n\n#### 🌐 **Crawl TechCrunch (FireCrawl)**\n\n* Uses a **POST** request to FireCrawl’s API\n* Inputs:\n\n  * `url`: Target site (e.g., `https://techcrunch.com`)\n  * `crawl_type`: `\"scrape\"`\n  * `extract_article`: `true`\n* Retrieves:\n\n  * `title`, `content`, `author`, `published_at`\n\n#### 🧠 **Filter Relevant Articles**\n\n* Uses a `Code` node to check if the article is relevant\n* Keywords like `\"AI\"`, `\"machine learning\"`, `\"startup\"` are matched\n* Filters only the articles that **matter to your domain**\n\n📄 **Sample Code:**\n\n```javascript\nconst keywords = ['AI', 'machine learning', 'startup', 'generative'];\nconst results = [];\n\nfor (const item of items) {\n  const title = item.json.article?.title?.toLowerCase() || '';\n  const content = item.json.article?.content?.toLowerCase() || '';\n\n  const isRelevant = keywords.some(keyword =>\n    title.includes(keyword.toLowerCase()) ||\n    content.includes(keyword.toLowerCase())\n  );\n\n  if (isRelevant) {\n    results.push(item); // keep only relevant articles\n  }\n}\n\nreturn results;\n```\n\n---\n\n## 🤖💬 3. **Summarization & Delivery**\n\n### **Nodes:**\n\n* `🧠 Summarize Article with AI` *(AI Agent)*\n* `🔗 OpenAI Chat (Summarizer)` *(OpenAI Chat Model)*\n* `💬 Send Summary to Slack` *(Slack)*\n\n### 📌 What happens here:\n\n#### 🤖 **Summarize Article with AI**\n\n* Passes the article to a GPT-4 or GPT-3.5 agent\n* Uses a prompt like:\n\n  > “Summarize the following article in 3 bullet points…”\n\n#### 💡 **OpenAI Chat (Summarizer)**\n\n* Executes the actual summarization\n* Outputs a short, clean summary ideal for fast reading\n\n#### 💬 **Send Summary to Slack**\n\n* Posts the summary to a specific Slack channel (e.g., `#market-research`)\n* Message format example:\n\n  ```\n  🔍 *Market Research Summary*\n  *Title:* OpenAI launches GPT-5\n  *Link:* https://techcrunch.com/article\n  *Summary:*\n  - GPT-5 improves reasoning\n  - Enhanced safety mechanisms\n  - Better multilingual performance\n  ```\n\n"
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "pinData": {
    "Crawl TechCrunch (FireCrawl)": [
      {
        "json": {
          "url": "https://techcrunch.com",
          "meta": {
            "description": "The latest technology news and information on startups."
          },
          "title": "TechCrunch - Startup and Technology News",
          "status": "success",
          "article": {
            "title": "OpenAI launches GPT-5",
            "author": "Jane Doe",
            "content": "OpenAI has officially released GPT-5, a major upgrade with enhanced reasoning and safety improvements...",
            "published_at": "2025-05-28T13:00:00Z"
          },
          "content": "<html>...</html>"
        }
      }
    ]
  },
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "8d64bd18-6a8f-4a2b-a952-5d8417122a2e",
  "connections": {
    "a326e8fd-bfc8-4380-9c66-20481aaa8a6c": {
      "main": [
        [
          {
            "node": "f5965b4a-4ab1-4e5f-868c-2dc11c59fc28",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "d8576228-6261-4654-84de-0864e398c22d": {
      "ai_languageModel": [
        [
          {
            "node": "a326e8fd-bfc8-4380-9c66-20481aaa8a6c",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "7d446441-d882-4816-805e-2d52cd8aea87": {
      "main": [
        [
          {
            "node": "a326e8fd-bfc8-4380-9c66-20481aaa8a6c",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "8f6e97b6-6910-4c6b-8c9a-29a0cf95ac09": {
      "main": [
        [
          {
            "node": "7d446441-d882-4816-805e-2d52cd8aea87",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "471044c1-cafd-4810-973d-b40c74ef6999": {
      "main": [
        [
          {
            "node": "8f6e97b6-6910-4c6b-8c9a-29a0cf95ac09",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}
Foire aux questions

Comment utiliser ce workflow ?

Copiez le code de configuration JSON ci-dessus, créez un nouveau workflow dans votre instance n8n et sélectionnez "Importer depuis le JSON", collez la configuration et modifiez les paramètres d'authentification selon vos besoins.

Dans quelles scénarios ce workflow est-il adapté ?

Intermédiaire - Intelligence Artificielle, Marketing

Est-ce payant ?

Ce workflow est entièrement gratuit et peut être utilisé directement. Veuillez noter que les services tiers utilisés dans le workflow (comme l'API OpenAI) peuvent nécessiter un paiement de votre part.

Workflows recommandés

Informations sur le workflow
Niveau de difficulté
Intermédiaire
Nombre de nœuds10
Catégorie2
Types de nœuds7
Description de la difficulté

Adapté aux utilisateurs expérimentés, avec des workflows de complexité moyenne contenant 6-15 nœuds

Auteur
Yaron Been

Yaron Been

@yaron-nofluff

Building AI Agents and Automations | Growth Marketer | Entrepreneur | Book Author & Podcast Host If you need any help with Automations, feel free to reach out via linkedin: https://www.linkedin.com/in/yaronbeen/ And check out my Youtube channel: https://www.youtube.com/@YaronBeen/videos

Liens externes
Voir sur n8n.io

Partager ce workflow

Catégories

Catégories: 34