{ "edges": [ { "to": "694fb2d1-c31a-4b07-b320-434f7dfe8c3a", "from": "1933da34-7848-4659-b0c9-0ea81029e472", "toPort": "0", "fromPort": "0" }, { "to": "4879f75c-c085-406b-9465-8e1dcacc408a", "from": "7b721510-5fb1-4fc4-b9ee-16040e783f06", "toPort": "0", "fromPort": "0" }, { "to": "78dbbd3e-ab76-4832-89b5-6169ac0a6577", "from": "4879f75c-c085-406b-9465-8e1dcacc408a", "toPort": "0", "fromPort": "0" }, { "to": "022156ac-a677-4e25-96d4-fc4a5433bb20", "from": "694fb2d1-c31a-4b07-b320-434f7dfe8c3a", "toPort": "0", "fromPort": "0" }, { "to": "3a6f5dc9-0528-41c3-829b-9f8fb6414b96", "from": "694fb2d1-c31a-4b07-b320-434f7dfe8c3a", "toPort": "0", "fromPort": "0" }, { "to": "1933da34-7848-4659-b0c9-0ea81029e472", "from": "39d8d355-9c4a-4202-9ca9-0c3219d4e207", "toPort": "0", "fromPort": "0" }, { "to": "69f800ff-39b6-4158-a0e7-8cfa966f208e", "from": "022156ac-a677-4e25-96d4-fc4a5433bb20", "toPort": "0", "fromPort": "0" }, { "to": "7b721510-5fb1-4fc4-b9ee-16040e783f06", "from": "69f800ff-39b6-4158-a0e7-8cfa966f208e", "toPort": "1", "fromPort": "0" }, { "to": "48a348f7-2988-4dfe-84ff-638216262486", "from": "3a6f5dc9-0528-41c3-829b-9f8fb6414b96", "toPort": "0", "fromPort": "0" }, { "to": "7b721510-5fb1-4fc4-b9ee-16040e783f06", "from": "48a348f7-2988-4dfe-84ff-638216262486", "toPort": "0", "fromPort": "0" } ], "nodes": [ { "id": "39d8d355-9c4a-4202-9ca9-0c3219d4e207", "name": "When clicking ‘Execute workflow’", "type": "manualTrigger", "params": {}, "position": [ -1168, 1376 ] }, { "id": "1933da34-7848-4659-b0c9-0ea81029e472", "name": "Get many messages", "type": "integration", "params": { "simple": false, "filters": { "sender": "user@example.com", "readStatus": "unread", "includeSpamTrash": true }, "options": {}, "service": "gmail", "operation": "getAll" }, "position": [ -912, 1376 ] }, { "id": "694fb2d1-c31a-4b07-b320-434f7dfe8c3a", "name": "Extract Hero Image SRC From HTML", "type": "code", "params": { "jsCode": "/**\n * n8n Function node\n * Extract hero src, alt, and title from Gmail HTML.\n *\n * Input: items[0].json.html (string)\n * Output: { hero: { src, alt, title }, validations: {...}, raw: { imgTag, container } }\n */\n\nfunction extractAttr(tag, attrName) {\n // Extracts attribute values from a tag string safely\n const re = new RegExp(`${attrName}\\\\s*=\\\\s*(\"([^\"]*)\"|'([^']*)'|([^\\\\s>]+))`, 'i');\n const m = tag.match(re);\n return m ? (m[2] || m[3] || m[4] || '') : '';\n}\n\nfunction firstImgTag(html) {\n // Find the hero container and the first inside it\n\n // 1) Prefer a container with id=\"heroImage...\"\n const heroDivMatch = html.match(\n /[\\s\\S]*?<\\/div>/i\n );\n if (heroDivMatch) {\n const heroDiv = heroDivMatch[0];\n const imgMatch = heroDiv.match(/]*>/i);\n return { imgTag: imgMatch ? imgMatch[0] : '', container: heroDiv };\n }\n\n // 2) Fallback: module row with id starting \"fullWidthImageModule\"\n const moduleMatch = html.match(\n /[\\s\\S]*?<\\/tr>/i\n );\n if (moduleMatch) {\n const mod = moduleMatch[0];\n const imgMatch = mod.match(/]*>/i);\n return { imgTag: imgMatch ? imgMatch[0] : '', container: mod };\n }\n\n // 3) Last resort: first centered hero-like with max-width ~ 680\n const genericMatch = html.match(\n /]*\\b(max-width:\\s*680px|width\\s*=\\s*[\"']680[\"'])[^>]*>/i\n );\n return { imgTag: genericMatch ? genericMatch[0] : '', container: '' };\n}\n\nconst itemsOut = [];\n\nfor (const item of items) {\n const html = (item.json && item.json.html) ? item.json.html : '';\n\n if (!html || typeof html !== 'string') {\n itemsOut.push({\n json: {\n error: 'HTML content not found at items[0].json.html',\n },\n });\n continue;\n }\n\n const { imgTag, container } = firstImgTag(html);\n\n if (!imgTag) {\n itemsOut.push({\n json: {\n error: 'Hero image tag not found',\n hint: 'Ensure the hero block has id=\"heroImage...\" or the module id starts with \"fullWidthImageModule\".',\n },\n });\n continue;\n }\n\n // Extract attributes\n const src = extractAttr(imgTag, 'src');\n const alt = extractAttr(imgTag, 'alt');\n const title = extractAttr(imgTag, 'title');\n\n // Minimal validations\n const validations = {\n hasSrc: Boolean(src),\n srcIsHttps: /^https:\\/\\//i.test(src),\n altPresent: alt.trim().length > 0,\n titlePresent: title.trim().length > 0,\n altTitleSame: alt.trim() && title.trim() ? alt.trim() === title.trim() : null,\n };\n\n itemsOut.push({\n json: {\n hero: { src, alt, title },\n validations,\n raw: { imgTag, container },\n },\n });\n}\n\nreturn itemsOut;" }, "position": [ -544, 1376 ] }, { "id": "022156ac-a677-4e25-96d4-fc4a5433bb20", "name": "Convert Image File from HTML to Binary", "type": "http", "params": { "url": "={\n \"hero\": {\n \"src\": \"https://dl.dropboxusercontent.com/scl/fi//\",\n \"alt\": \"Hero Image\",\n \"title\": \"Hero Image Title\"\n }\n}", "options": { "response": { "response": { "responseFormat": "file" } } } }, "position": [ -224, 1504 ] }, { "id": "3a6f5dc9-0528-41c3-829b-9f8fb6414b96", "name": "Convert Image File from Dropbox to Binary", "type": "http", "params": { "url": "=https://dl.dropboxusercontent.com/scl/fi//", "options": { "response": { "response": { "responseFormat": "file" } } } }, "position": [ -240, 1312 ] }, { "id": "7b721510-5fb1-4fc4-b9ee-16040e783f06", "name": "Combine Image Outputs", "type": "merge", "params": {}, "position": [ 256, 1408 ] }, { "id": "4879f75c-c085-406b-9465-8e1dcacc408a", "name": "Extract Content Match Results", "type": "code", "params": { "jsCode": "// Get all input items\nconst items = $input.all();\n\n// Extract ParsedText from input1 and input2\nconst sourceAText = items[0]?.json?.ParsedResults?.[0]?.ParsedText || \"\";\nconst sourceBText = items[1]?.json?.ParsedResults?.[0]?.ParsedText || \"\";\n\n// Normalize strings\nfunction normalize(str) {\n return str.replace(/\\s+/g, \" \").trim().toLowerCase();\n}\n\nconst normA = normalize(sourceAText);\nconst normB = normalize(sourceBText);\n\n// Comparison logic\nlet result;\nif (!normA && !normB) {\n result = \"No content in either source\";\n} else if (!normA || !normB) {\n result = \"Missing content in one source\";\n} else if (normA === normB) {\n result = \"Exact Match\";\n} else if (normA.includes(normB) || normB.includes(normA)) {\n result = \"Partial Match\";\n} else {\n result = \"Mismatch\";\n}\n\n// Return as columns\nreturn [\n {\n \"Column A (Source A Content)\": sourceAText,\n \"Column B (Source B Content)\": sourceBText,\n \"Column C (Result)\": result\n }\n];" }, "position": [ 464, 1408 ] }, { "id": "78dbbd3e-ab76-4832-89b5-6169ac0a6577", "name": "Log Image Checks to Excel", "type": "integration", "params": { "columns": { "value": { "Result": "={{ $json['Column C (Result)'] }}", "HTML Hero Content": "={{ $json['Column B (HTML Content)'] }}", "Dropbox Hero Content": "={{ $json['Column A (Dropbox Content)'] }}" }, "schema": [ { "id": "Dropbox Hero Content", "type": "string", "display": true, "removed": false, "required": false, "displayName": "Dropbox Hero Content", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "HTML Hero Content", "type": "string", "display": true, "required": false, "displayName": "HTML Hero Content", "defaultMatch": false, "canBeUsedToMatch": true }, { "id": "Result", "type": "string", "display": true, "required": false, "displayName": "Result", "defaultMatch": false, "canBeUsedToMatch": true } ], "mappingMode": "defineBelow", "matchingColumns": [ "Dropbox Hero Content" ], "attemptToConvertTypes": false, "convertFieldsToString": false }, "options": {}, "service": "googleSheets", "operation": "appendOrUpdate", "sheetName": { "__rl": true, "mode": "id", "value": "=// Parameters provided by user in node config\nconst sheetId = this.getNodeParameter(\"sheetId\", 0) || \"YOUR_SPREADSHEET_ID\";\nconst sheetName = this.getNodeParameter(\"sheetName\", 0) || \"Sheet1\";\n\nconst { google } = require(\"googleapis\");\nconst sheets = google.sheets({ version: \"v4\", auth });\n\nconst response = await sheets.spreadsheets.values.get({\n spreadsheetId: sheetId,\n range: sheetName,\n});\n\nreturn response.data.values.map(row => ({ json: { row } }));" }, "documentId": { "__rl": true, "mode": "url", "value": "=https://docs.google.com/spreadsheets/d//edit" } }, "position": [ 704, 1408 ] }, { "id": "48a348f7-2988-4dfe-84ff-638216262486", "name": "Extracting Expected Image Content from OCR1", "type": "http", "params": { "url": "=const response = await fetch(\"https://api.ocr.space/parse/image\", {\n method: \"POST\",\n headers: {\n \"apikey\": process.env.OCR_API_KEY, // use environment variable\n },\n body: new FormData({\n file: myFile, // user-provided file\n language: \"eng\", // configurable language\n })\n});", "method": "POST", "options": {}, "sendBody": true, "contentType": "multipart-form-data", "sendHeaders": true, "bodyParameters": { "parameters": [ { "name": "data", "parameterType": "formBinaryData", "inputDataFieldName": "data" } ] }, "headerParameters": { "parameters": [ { "name": "=headers: {\n \"apikey\": process.env.OCR_API_KEY\n}", "value": "=headers: {\n \"apikey\": process.env.OCR_API_KEY\n}" } ] } }, "position": [ 16, 1312 ] }, { "id": "69f800ff-39b6-4158-a0e7-8cfa966f208e", "name": "Extracting Actual Image Content from OCR", "type": "http", "params": { "url": "=const response = await fetch(\"https://api.ocr.space/parse/image\", {\n method: \"POST\",\n headers: {\n \"apikey\": process.env.OCR_API_KEY, // use environment variable\n },\n body: new FormData({\n file: myFile, // user-provided file\n language: \"eng\", // configurable language\n })\n});", "method": "POST", "options": {}, "sendBody": true, "contentType": "multipart-form-data", "sendHeaders": true, "bodyParameters": { "parameters": [ { "name": "data", "parameterType": "formBinaryData", "inputDataFieldName": "=data" } ] }, "headerParameters": { "parameters": [ { "name": "=headers: {\n \"apikey\": process.env.OCR_API_KEY\n}", "value": "=headers: {\n \"apikey\": process.env.OCR_API_KEY\n}" } ] } }, "position": [ 32, 1488 ] } ] }

Validate email hero images with Gmail, Dropbox, OCR.Space and Google Sheets