{ "id": "b0NmRs9o4fvmw3vi", "meta": { "templateCredsSetupCompleted": true }, "name": "Niche History Generator", "tags": [ { "id": "lZKSh2IoxHklnOUw", "name": "ScrapeOps", "createdAt": "2025-10-20T20:27:13.410Z", "updatedAt": "2025-10-20T20:27:13.410Z" }, { "id": "yh7XX4GObvd3np2S", "name": "google sheets", "createdAt": "2025-11-06T11:10:29.979Z", "updatedAt": "2025-11-06T11:10:29.979Z" }, { "id": "g2HXimaqnEo1MFUR", "name": "wikipedia", "createdAt": "2025-12-04T06:41:29.909Z", "updatedAt": "2025-12-04T06:41:29.909Z" }, { "id": "LxkPKH8N5AyDKJ18", "name": "research", "createdAt": "2025-12-04T06:41:34.063Z", "updatedAt": "2025-12-04T06:41:34.063Z" }, { "id": "uJLE6LNaDOFm3yTZ", "name": "ContentGeneration", "createdAt": "2025-12-04T06:41:47.080Z", "updatedAt": "2025-12-04T06:41:47.080Z" }, { "id": "EPiKzzzTnU1nVITY", "name": "OpenAI", "createdAt": "2025-12-04T06:41:56.401Z", "updatedAt": "2025-12-04T06:41:56.401Z" } ], "nodes": [ { "id": "5734320a-5061-4438-a690-2b8524e26243", "name": "When clicking \"Execute Workflow\"", "type": "n8n-nodes-base.manualTrigger", "position": [ -1072, -48 ], "parameters": {}, "typeVersion": 1 }, { "id": "92c4455f-4db1-4021-aed9-69f33fc0fb5f", "name": "Set Topic", "type": "n8n-nodes-base.set", "position": [ -848, -48 ], "parameters": { "fields": { "values": [ { "name": "topic", "stringValue": "n8n" } ] }, "options": {} }, "typeVersion": 3.2 }, { "id": "2a11e959-ef81-4c1d-ae38-f76b1903f277", "name": "Wikipedia Search API", "type": "n8n-nodes-base.httpRequest", "position": [ -624, -48 ], "parameters": { "url": "https://en.wikipedia.org/w/api.php", "options": {}, "sendQuery": true, "sendHeaders": true, "queryParameters": { "parameters": [ { "name": "action", "value": "query" }, { "name": "list", "value": "search" }, { "name": "srsearch", "value": "={{ $json.topic }}" }, { "name": "format", "value": "json" } ] }, "headerParameters": { "parameters": [ { "name": "User-Agent", "value": "n8n-workflow/1.0 (https://n8n.io; user@example.com)" } ] } }, "typeVersion": 4.1 }, { "id": "c0765484-7583-43f5-83aa-905761c8d878", "name": "ScrapeOps Scraper", "type": "@scrapeops/n8n-nodes-scrapeops.ScrapeOps", "position": [ -176, -48 ], "parameters": { "url": "={{ $json.wikipedia_page_url }}", "advancedOptions": { "render_js": true } }, "credentials": { "scrapeOpsApi": { "name": "" } }, "typeVersion": 1 }, { "id": "8814f99a-63a2-4494-a38a-853230986a97", "name": "Append row in sheet", "type": "n8n-nodes-base.googleSheets", "position": [ 848, -48 ], "parameters": { "columns": { "value": { "Topic": "={{ $json.Topic }}", "Timeline": "={{ $json.Timeline }}", "History_Raw": "={{ $json.History_Raw }}", "History_Cleaned": "={{ $json.History_Cleaned }}", "History_Summary": "={{ $json.History_Summary }}", "Search_Query_URL\r": "={{ $json.Search_Query_URL }}", "Wikipedia_Page_URL": "={{ $json.Wikipedia_PAGE_URL }}", "Wikipedia_Page_Title\r": "={{ $json.Wikipedia_Page_Title }}" }, "schema": [ { "id": "Topic", "type": "string", "display": true, "required": false, "displayName": "Topic", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Search_Query_URL\r", "type": "string", "display": true, "required": false, "displayName": "Search_Query_URL\r", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Wikipedia_Page_Title\r", "type": "string", "display": true, "required": false, "displayName": "Wikipedia_Page_Title\r", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Wikipedia_Page_URL", "type": "string", "display": true, "required": false, "displayName": "Wikipedia_Page_URL", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "History_Raw", "type": "string", "display": true, "required": false, "displayName": "History_Raw", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "History_Cleaned", "type": "string", "display": true, "required": false, "displayName": "History_Cleaned", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "History_Summary", "type": "string", "display": true, "required": false, "displayName": "History_Summary", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Timeline", "type": "string", "display": true, "required": false, "displayName": "Timeline", "defaultMatch": false, "canBeUsedToMatch": true } ], "mappingMode": "defineBelow", "matchingColumns": [], "attemptToConvertTypes": false, "convertFieldsToString": false }, "options": {}, "operation": "append", "sheetName": { "__rl": true, "mode": "list", "value": "gid=0", "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1WZNqkpZV-xSVvv4hj3TwKyjINWWe6AHOWJ2eEkUdRzE/edit#gid=0", "cachedResultName": "Sheet1" }, "documentId": { "__rl": true, "mode": "url", "value": "https://docs.google.com/spreadsheets/d/1P0wZ449wVNndhSa6cJtK3VA3Aulv1k18zdpwWYY13gE/edit?gid=0#gid=0" } }, "credentials": { "googleSheetsOAuth2Api": { "name": "" } }, "typeVersion": 4.7 }, { "id": "950ac15e-6f9a-4cc2-a170-fa09031dc131", "name": "Message a model", "type": "@n8n/n8n-nodes-langchain.openAi", "position": [ 272, -48 ], "parameters": { "modelId": { "__rl": true, "mode": "list", "value": "gpt-4o-mini", "cachedResultName": "GPT-4O-MINI" }, "options": {}, "messages": { "values": [ { "role": "system", "content": "== You are the Niche History Generator AI. Return EXACTLY and ONLY a single valid JSON object \u2014 nothing else. Do NOT include explanation, commentary, markdown, triple backticks, or any extra text. The JSON must contain exactly these keys: Topic, Search_Query_URL, Wikipedia_Page_Title, Wikipedia_PAGE_URL, History_Raw, History_Cleaned, History_Summary, Timeline. Use \\\\n\\\\n inside paragraphs only. Timeline entries must use single-line entries starting with - **YYYY:**. Return a JSON object (not a JSON string)." }, { "content": "=Topic:{{ $json.topic }}\nWikipedia Page Title: {{ $json.wikipedia_page_title }}\nWikipedia Page URL:{{ $json.wikipedia_page_url }}\nSearch Query URL:{{ $json.search_query_url }}\nRaw History:{{ $json.history_raw }}" }, {} ] } }, "credentials": { "openAiApi": { "name": "" } }, "executeOnce": true, "typeVersion": 1.8 }, { "id": "603d4e6c-a86e-4995-a253-e6cf31b524e5", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [ -1840, -464 ], "parameters": { "width": 656, "height": 608, "content": "# \ud83d\udcdc Wikipedia Niche History Generator\n\nThis workflow automates the research process by scraping Wikipedia for a specific topic, extracting its history, and using AI to generate a structured summary and timeline.\n\n### How it works\n1. **Input**: You provide a topic (e.g., \"n8n\", \"Tesla\", \"Coffee\").\n2. **Search**: The workflow searches Wikipedia to find the most relevant page.\n3. **Scrape**: It uses **ScrapeOps** to reliably scrape the full page content without getting blocked.\n4. **Process**: A custom code node extracts the \"History\" or \"Origins\" section from the HTML.\n5. **Analyze**: GPT-4o-mini summarizes the history and creates a timeline.\n6. **Save**: The final structured data is appended to a Google Sheet.\n\n### Setup steps\n1. **ScrapeOps**: [Get your free API key](https://scrapeops.io/app/register/n8n) and add it to the ScrapeOps node.\n2. **OpenAI**: Configure your OpenAI credentials for the LLM node.\n3. **Google Sheets**:\n - Duplicate this [Template Sheet](https://docs.google.com/spreadsheets/d/1P0wZ449wVNndhSa6cJtK3VA3Aulv1k18zdpwWYY13gE/edit?gid=0#gid=0).\n - Connect your Google account and select the new sheet in the \"Append row\" node.\n\n### Customization\n- **Topic**: Change the value in the \"Set Topic\" node.\n- **Docs**: Read the [ScrapeOps n8n docs](https://scrapeops.io/docs/n8n/overview/) for more info." }, "typeVersion": 1 }, { "id": "de7b3fe5-a62f-4c64-8a18-6965bdca9d92", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [ -1120, -144 ], "parameters": { "color": 7, "width": 416, "height": 256, "content": "## 1. Input\nDefine your research topic here.\t" }, "typeVersion": 1 }, { "id": "88efd19f-4100-4da2-bf1b-3506d1cbc5af", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [ -680, -144 ], "parameters": { "color": 7, "width": 656, "height": 256, "content": "## 2. Search & Scrape\nFind and retrieve the Wikipedia page using ScrapeOps." }, "typeVersion": 1 }, { "id": "256c58ef-1543-4a5f-86b7-4e98c4f00ee9", "name": "Sticky Note3", "type": "n8n-nodes-base.stickyNote", "position": [ 8, -144 ], "parameters": { "color": 7, "width": 752, "height": 256, "content": "## 3. Process & Analyze\nExtract history sections and use AI to summarize." }, "typeVersion": 1 }, { "id": "3fc32852-8314-42d1-ac85-4396068b43d5", "name": "Sticky Note4", "type": "n8n-nodes-base.stickyNote", "position": [ 776, -144 ], "parameters": { "color": 7, "height": 256, "content": "## 4. Output\nSave the structured data to Google Sheets." }, "typeVersion": 1 }, { "id": "6d76b574-3f8d-45e9-96cd-421e6b1b2d8b", "name": "Extract History Section", "type": "n8n-nodes-base.code", "position": [ 48, -48 ], "parameters": { "jsCode": "// Clean Wikipedia Text (Regex version - No Cheerio)\nconst item = items[0].json;\nlet html = '';\n\n// 1. Extract HTML from Input\nif (typeof item === 'string') {\n html = item;\n} else if (item.response?.body) {\n html = item.response.body;\n} else if (item.body) {\n html = item.body;\n} else if (item.content) {\n html = item.content;\n} else if (item.data) {\n html = item.data;\n} else {\n // Handle \"exploded\" string (numeric keys) from ScrapeOps\n const keys = Object.keys(item).filter(k => !isNaN(k));\n if (keys.length > 0) {\n keys.sort((a, b) => parseInt(a) - parseInt(b));\n html = keys.map(k => item[k]).join('');\n }\n}\n\n// 2. Basic Cleanup (Remove scripts, styles, tables, references)\nhtml = html.replace(/]*>[\\s\\S]*?<\\/script>/gim, \"\");\nhtml = html.replace(/]*>[\\s\\S]*?<\\/style>/gim, \"\");\nhtml = html.replace(/]*>[\\s\\S]*?<\\/table>/gim, \"\"); \nhtml = html.replace(/]*class=[\"'][^\"']*reference[^\"']*[\"'][^>]*>[\\s\\S]*?<\\/sup>/gim, \"\");\nhtml = html.replace(/]*class=[\"'][^\"']*mw-editsection[^\"']*[\"'][^>]*>[\\s\\S]*?<\\/span>/gim, \"\");\n\n// 3. Find the History/Origins/Background Section\nconst headerRegex = /]*>.*?(?:History|Origins|Background).*?<\\/h[23]>/i;\nconst headerMatch = headerRegex.exec(html);\n\nlet historyText = '';\n\nif (headerMatch) {\n const startIndex = headerMatch.index + headerMatch[0].length;\n const remainder = html.substring(startIndex);\n const nextHeaderRegex = /]*>/i;\n const nextHeaderMatch = nextHeaderRegex.exec(remainder);\n \n let sectionContent = remainder;\n if (nextHeaderMatch) {\n sectionContent = remainder.substring(0, nextHeaderMatch.index);\n }\n \n const pRegex = /]*>([\\s\\S]*?)<\\/p>/gi;\n let pMatch;\n while ((pMatch = pRegex.exec(sectionContent)) !== null) {\n let pText = pMatch[1];\n pText = pText.replace(/<[^>]+>/g, '');\n pText = pText.replace(/ /g, ' ').replace(/&/g, '&').replace(/"/g, '\"').replace(/</g, '<').replace(/>/g, '>');\n historyText += pText.trim() + '\\n\\n';\n }\n} else {\n // Fallback: Grab first 5 paragraphs\n const pRegex = /]*>([\\s\\S]*?)<\\/p>/gi;\n let pMatch;\n let count = 0;\n while ((pMatch = pRegex.exec(html)) !== null && count < 5) {\n let pText = pMatch[1];\n pText = pText.replace(/<[^>]+>/g, '');\n pText = pText.replace(/ /g, ' ').replace(/&/g, '&').replace(/"/g, '\"').replace(/</g, '<').replace(/>/g, '>');\n if (pText.trim().length > 50) {\n historyText += pText.trim() + '\\n\\n';\n count++;\n }\n }\n}\n\nhistoryText = historyText.replace(/\\[.*?\\]/g, '').trim();\n\n// 4. Return Data (Restore metadata from Build Wikipedia URL node)\n// We use $('Construct Page URL').first().json to get the original topic/url info\nconst originalData = $('Construct Page URL').first().json;\n\nreturn [\n {\n json: {\n ...originalData,\n history_raw: historyText\n }\n }\n];" }, "typeVersion": 2 }, { "id": "dfdb13c2-6c31-460c-908f-3f6a5304be71", "name": "Format AI Output", "type": "n8n-nodes-base.code", "position": [ 624, -48 ], "parameters": { "jsCode": "// Universal robust parser \u2014 handles many OpenAI node shapes including message.content\nconst item = items[0];\nlet raw = '';\n// try many known places the assistant text may appear\nif (item.json.output_text) {\n raw = item.json.output_text;\n} else if (item.json.content?.[0]?.text) {\n raw = item.json.content[0].text;\n} else if (item.json.output?.[0]?.content?.[0]?.text) {\n raw = item.json.output[0].content[0].text;\n} else if (item.json.choices?.[0]?.message?.content) {\n raw = item.json.choices[0].message.content;\n} else if (item.json.choices?.[0]?.text) {\n raw = item.json.choices[0].text;\n} else if (typeof item.json.message?.content === 'string') {\n // your specific shape: item.json.message.content is a string with JSON\n raw = item.json.message.content;\n} else if (Array.isArray(item.json.output) && item.json.output[0]?.content?.[0]?.text) {\n raw = item.json.output[0].content[0].text;\n} else {\n raw = JSON.stringify(item.json);\n}\n// normalize\nraw = String(raw).trim();\n// remove triple backticks if present\nraw = raw.replace(/^\\s*```(?:json)?\\s*/i, '');\nraw = raw.replace(/\\s*```\\s*$/i, '');\n// extract the first {...} JSON block\nconst match = raw.match(/\\{[\\s\\S]*\\}/);\nconst jsonText = match ? match[0] : raw;\n// parse with fallback (handle escaped newlines)\nlet parsed;\ntry {\n parsed = JSON.parse(jsonText);\n} catch (e1) {\n try {\n parsed = JSON.parse(jsonText.replace(/\\\\n/g, '\\n'));\n } catch (e2) {\n return [{ json: { parse_error: e2.message, raw } }];\n }\n}\n// tolerant key lookup\nfunction getVal(obj, names){\n for (const n of names){\n if (Object.prototype.hasOwnProperty.call(obj, n)) return obj[n];\n }\n // case-insensitive normalized\n const norm = {};\n for (const k of Object.keys(obj||{})) norm[k.toLowerCase().replace(/[_\\s]+/g,'')] = obj[k];\n for (const n of names){\n const key = n.toLowerCase().replace(/[_\\s]+/g,'');\n if (norm[key] !== undefined) return norm[key];\n }\n return undefined;\n}\n// build output\nconst out = {};\nout.Topic = getVal(parsed, ['Topic','topic']) || '';\nout.Search_Query_URL = getVal(parsed, ['Search_Query_URL','search_query_url','searchqueryurl']) || '';\nout.Wikipedia_Page_Title = getVal(parsed, ['Wikipedia_Page_Title','Wikipedia Page Title','wikipedia_page_title']) || '';\nout.Wikipedia_PAGE_URL = getVal(parsed, ['Wikipedia_PAGE_URL','Wikipedia Page URL','wikipedia_page_url']) || '';\nout.History_Raw = getVal(parsed, ['History_Raw','history_raw']) || '';\nout.History_Cleaned = getVal(parsed, ['History_Cleaned','history_cleaned']) || '';\nout.History_Summary = getVal(parsed, ['History_Summary','history_summary']) || '';\n// handle Timeline: array -> newline string, or string (maybe JSON string)\nlet timeline = getVal(parsed, ['Timeline','timeline','TimeLine']);\nif (Array.isArray(timeline)) {\n out.Timeline = timeline.join('\\n');\n} else if (typeof timeline === 'string') {\n try {\n const maybe = JSON.parse(timeline);\n out.Timeline = Array.isArray(maybe) ? maybe.join('\\n') : timeline;\n } catch (e) {\n out.Timeline = timeline;\n }\n} else {\n out.Timeline = '';\n}\n// unescape double-escaped newlines\nfor (const k of ['History_Raw','History_Cleaned','History_Summary','Timeline']) {\n if (typeof out[k] === 'string') out[k] = out[k].replace(/\\\\n/g, '\\n');\n}\nreturn [{ json: out }];" }, "typeVersion": 2 }, { "id": "d319b30d-ce61-43a8-bb41-7423b59f89ff", "name": "Construct Page URL", "type": "n8n-nodes-base.code", "position": [ -400, -48 ], "parameters": { "jsCode": "// Get topic from Set Topic node (not from Wikipedia API response)\nconst topic = $('Set Topic').first().json.topic;\nconst search = items[0].json.query.search;\n\nif (!search || search.length === 0) {\n throw new Error(\"No Wikipedia page found for: \" + topic);\n}\n\nconst title = search[0].title;\nconst encoded = encodeURIComponent(title.replace(/ /g, \"_\"));\n\nreturn [\n {\n json: {\n topic,\n wikipedia_page_title: title,\n wikipedia_page_url: `https://en.wikipedia.org/wiki/${encoded}`,\n search_query_url: `https://en.wikipedia.org/w/api.php?action=query&list=search&srsearch=${encodeURIComponent(topic)}&format=json`\n }\n }\n];" }, "typeVersion": 2 } ], "active": false, "settings": { "executionOrder": "v1" }, "versionId": "a392cdfb-8bf6-4257-869a-204f60d8d05e", "connections": { "Set Topic": { "main": [ [ { "node": "Wikipedia Search API", "type": "main", "index": 0 } ] ] }, "Message a model": { "main": [ [ { "node": "Format AI Output", "type": "main", "index": 0 } ] ] }, "Format AI Output": { "main": [ [ { "node": "Append row in sheet", "type": "main", "index": 0 } ] ] }, "ScrapeOps Scraper": { "main": [ [ { "node": "Extract History Section", "type": "main", "index": 0 } ] ] }, "Construct Page URL": { "main": [ [ { "node": "ScrapeOps Scraper", "type": "main", "index": 0 } ] ] }, "Wikipedia Search API": { "main": [ [ { "node": "Construct Page URL", "type": "main", "index": 0 } ] ] }, "Extract History Section": { "main": [ [ { "node": "Message a model", "type": "main", "index": 0 } ] ] }, "When clicking \"Execute Workflow\"": { "main": [ [ { "node": "Set Topic", "type": "main", "index": 0 } ] ] } } }