Analyze Up to 100 Urls for On-page SEO and Export Results to CSV

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 →

{
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "b02b270d-4d79-4881-ba3e-2973c8e88710",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -320,
        -48
      ],
      "parameters": {
        "width": 736,
        "height": 464,
        "content": "# Workflow Technical Overview\n- **Purpose:** Automated bulk extraction of 27+ On-Page SEO metrics and HTTP header metadata.\n- **Core Constraint:** Hard-coded limit of 100 URLs per chat trigger to ensure stability.\n- **Logic Flow:** Sequential double-loop architecture for validation and extraction.\n\n## Who's it for\nTechnical SEO analysts requiring automated bulk on-page data extraction without external API dependencies.\n\n## How to use\n1. Open the chat trigger interface.\n2. Input a list of target URLs (maximum 100).\n3. Monitor chat notifications for validation alerts and processing status.\n4. Click the output link to download the generated CSV file.\n\n## Setup Requirements\n- Active n8n instance.\n- Outbound network access for HTTP requests."
      },
      "typeVersion": 1
    },
    {
      "id": "d3513989-a85b-42e9-a903-bc9bbbf00b4a",
      "name": "Loop Through URL Batches",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        2480,
        368
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 3
    },
    {
      "id": "39883d32-02bf-4a4c-b455-4516fdbfac8a",
      "name": "Fetch Page HTML Payload",
      "type": "n8n-nodes-base.httpRequest",
      "onError": "continueErrorOutput",
      "position": [
        2896,
        384
      ],
      "parameters": {
        "url": "={{ $json.url }}",
        "options": {
          "redirect": {
            "redirect": {
              "followRedirects": false
            }
          },
          "response": {
            "response": {
              "fullResponse": true
            }
          }
        },
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "User-Agent",
              "value": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36 Edg/124.0.0.0"
            }
          ]
        }
      },
      "executeOnce": false,
      "typeVersion": 4.1
    },
    {
      "id": "be5e7bed-7702-463f-85c2-3d3b963cd1b2",
      "name": "Verify HTTP 200 Status",
      "type": "n8n-nodes-base.if",
      "position": [
        3584,
        368
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 3,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "f6c29bd9-b913-46c2-af81-e62a46717b0e",
              "operator": {
                "type": "number",
                "operation": "equals"
              },
              "leftValue": "={{ $json.statusCode }}",
              "rightValue": 200
            }
          ]
        }
      },
      "typeVersion": 2.3,
      "alwaysOutputData": false
    },
    {
      "id": "ee2ae600-d0a0-432b-ac87-49e54017afef",
      "name": "Inspect HTML Content Structure",
      "type": "n8n-nodes-base.code",
      "position": [
        3968,
        352
      ],
      "parameters": {
        "jsCode": "return items.map(item => {\n  const html = String(item.json.body || item.json.data || item.json.html || '').trim();\n\n  const hasHtmlLike = /<(html|head|title|body|meta|link|h1)\\b/i.test(html);\n  const hasSeoSignals =\n    /<title\\b[^>]*>[\\s\\S]*?<\\/title>/i.test(html) ||\n    /<meta\\b[^>]+name=[\"']description[\"'][^>]*content=/i.test(html) ||\n    /<link\\b[^>]+rel=[\"']canonical[\"'][^>]*href=/i.test(html) ||\n    /<h1\\b[^>]*>[\\s\\S]*?<\\/h1>/i.test(html);\n\n  const blockedPattern =\n    /javascript is disabled|enable javascript to continue|verify you are human|captcha|access denied|request blocked|temporarily unavailable|sorry, you have been blocked|attention required/i.test(html);\n\n  const clearlyNotHtml =\n    !html ||\n    (!hasHtmlLike && !/<!doctype html/i.test(html));\n\n  let reason = 'ok';\n\n  if (!html) reason = 'empty-body';\n  else if (blockedPattern) reason = 'blocked-or-interstitial';\n  else if (clearlyNotHtml) reason = 'not-html';\n  else if (!hasSeoSignals && html.length < 150) reason = 'thin-non-seo-html';\n\n  item.json.html_compliant = reason === 'ok';\n  item.json.html_compliance_reason = reason;\n\n  return item;\n});"
      },
      "executeOnce": false,
      "typeVersion": 2
    },
    {
      "id": "5d93fec7-9650-4443-8a43-ad10f578fd4d",
      "name": "Validate HTML Compliance Status",
      "type": "n8n-nodes-base.if",
      "position": [
        4192,
        352
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 3,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "9724955d-7bee-4eca-a836-e8cb0ee7ecfe",
              "operator": {
                "type": "boolean",
                "operation": "true",
                "singleValue": true
              },
              "leftValue": "={{ $json.html_compliant === true }}",
              "rightValue": "={{   $json.body &&   /<html|<head|<title|<body/i.test($json.body) &&   !/javascript is disabled|enable javascript|not a robot|captcha|access denied|forbidden|temporarily unavailable|verify you are human|cloudflare|attention required/i.test($json.body) }}"
            }
          ]
        }
      },
      "typeVersion": 2.3
    },
    {
      "id": "cbdaaf6e-65d9-4a0b-85c0-8faa815da49f",
      "name": "Receive Chat Message Input",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        512,
        208
      ],
      "parameters": {
        "options": {
          "responseMode": "responseNodes"
        }
      },
      "typeVersion": 1.4
    },
    {
      "id": "fec05fe9-1eb8-4abf-9d29-ca179c5dadd2",
      "name": "Extract and Normalize URLs",
      "type": "n8n-nodes-base.code",
      "position": [
        848,
        208
      ],
      "parameters": {
        "jsCode": "const rawInput = $input.first().json.chatInput || \"\";\nconst rawUrls = rawInput.split(/[\\s,]+/).filter(Boolean);\n\nlet validUrls = [];\nlet skipped = [];\nconst urlRegex = /^(https?:\\/\\/)?([\\da-z\\.-]+)\\.([a-z\\.]{2,6})([\\/\\w \\.-]*)*\\/?$/i;\n\nfor (let url of rawUrls) {\n  if (!urlRegex.test(url)) {\n    skipped.push(url);\n    continue;\n  }\n  let clean = url.toLowerCase();\n  if (!clean.startsWith('http://') && !clean.startsWith('https://')) {\n    clean = 'https://' + clean;\n  }\n  if (!validUrls.includes(clean)) {\n    validUrls.push(clean);\n  }\n}\n\nlet warning = \"\";\nif (validUrls.length > 10000) {\n  warning = \"\u26a0\ufe0f Only the first 10,000 URLs will be processed. Remaining URLs have been skipped.\";\n  validUrls = validUrls.slice(0, 10);\n}\n\nreturn [{\n  json: {\n    valid_urls: validUrls,\n    skipped_input: skipped,\n    warning: warning,\n    total_valid: validUrls.length\n  }\n}];"
      },
      "typeVersion": 2
    },
    {
      "id": "ced5ec21-a5ba-473a-8ccd-786504eb0480",
      "name": "Check Empty URL List",
      "type": "n8n-nodes-base.if",
      "position": [
        1104,
        208
      ],
      "parameters": {
        "conditions": {
          "number": [
            {
              "value1": "={{ $json.total_valid }}",
              "operation": "equal"
            }
          ]
        }
      },
      "typeVersion": 1
    },
    {
      "id": "87aa1a6e-2eaa-4b54-96f1-769c6740549d",
      "name": "Verify Maximum URL Limit",
      "type": "n8n-nodes-base.if",
      "position": [
        1152,
        384
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 3,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "9eb3b4a9-e3ff-4dd6-9c18-bcfb55b7e4ce",
              "operator": {
                "type": "number",
                "operation": "lte"
              },
              "leftValue": "={{ $json.total_valid }}",
              "rightValue": 100
            }
          ]
        }
      },
      "typeVersion": 2.3
    },
    {
      "id": "e3b349af-4f94-4a3e-85ab-b6a9051c9900",
      "name": "Format URL JSON Objects",
      "type": "n8n-nodes-base.code",
      "position": [
        1520,
        368
      ],
      "parameters": {
        "jsCode": "const urls = $json.valid_urls || [];\n\nreturn [\n  {\n    json: {\n      valid_urls: urls.map((url) => ({\n        url,\n        url_index: url\n      })),\n      skipped_input: $json.skipped_input ?? [],\n      warning: $json.warning ?? '',\n      total_valid: $json.total_valid ?? urls.length\n    }\n  }\n];"
      },
      "typeVersion": 2
    },
    {
      "id": "e0c3e125-5ea5-4c03-aea6-45189f90cc08",
      "name": "Split Into Individual Items",
      "type": "n8n-nodes-base.itemLists",
      "position": [
        1888,
        368
      ],
      "parameters": {
        "options": {
          "destinationFieldName": ""
        },
        "fieldToSplitOut": "valid_urls"
      },
      "typeVersion": 3
    },
    {
      "id": "215d7870-4713-4d7e-9b13-658b48da74bc",
      "name": "Check For Skipped Inputs",
      "type": "n8n-nodes-base.if",
      "position": [
        1488,
        224
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 3,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "02a29791-0c3d-484e-8dbf-f895191453ca",
              "operator": {
                "type": "array",
                "operation": "notEmpty",
                "singleValue": true
              },
              "leftValue": "={{ $json.skipped_input }}",
              "rightValue": ""
            }
          ]
        }
      },
      "typeVersion": 2.3
    },
    {
      "id": "bc285d42-799d-4896-9c21-13bde8d956f5",
      "name": "Send Empty Input Error",
      "type": "@n8n/n8n-nodes-langchain.chat",
      "position": [
        2112,
        192
      ],
      "parameters": {
        "message": "\u274c No valid URLs were found in your input. Please enter at least one properly formatted URL (e.g. https://seobatter.com) and try again.",
        "options": {},
        "waitUserReply": false
      },
      "typeVersion": 1
    },
    {
      "id": "3245e1f6-03b5-48d0-97f4-ae5cd3d9ee87",
      "name": "Send Maximum Limit Error",
      "type": "@n8n/n8n-nodes-langchain.chat",
      "position": [
        1392,
        528
      ],
      "parameters": {
        "message": "The valid URLs are more than 100. For preventing system abuse, please enter 100 or lesser URLs.",
        "options": {},
        "waitUserReply": false
      },
      "typeVersion": 1
    },
    {
      "id": "bdff6f86-45f0-4045-b253-88c5bff32722",
      "name": "Send Skipped Input Warning",
      "type": "@n8n/n8n-nodes-langchain.chat",
      "position": [
        1808,
        208
      ],
      "parameters": {
        "message": "=During initial validation, the some input was excluded from the analysis - Example:\n{{ $json.skipped_input.join('\\n') }}",
        "options": {},
        "waitUserReply": false
      },
      "typeVersion": 1
    },
    {
      "id": "4aa82248-78c7-4622-ba42-de25dfcecd12",
      "name": "Remove Duplicate Records",
      "type": "n8n-nodes-base.removeDuplicates",
      "position": [
        2416,
        -112
      ],
      "parameters": {
        "compare": "selectedFields",
        "options": {},
        "fieldsToCompare": "address"
      },
      "typeVersion": 2
    },
    {
      "id": "305ff240-e54d-46dc-b6ed-cbb348cdec1b",
      "name": "Send Progress Update",
      "type": "@n8n/n8n-nodes-langchain.chat",
      "position": [
        2624,
        -112
      ],
      "parameters": {
        "message": "Processing data from the valid URLs. Please wait for the complete execution.",
        "options": {},
        "waitUserReply": false
      },
      "typeVersion": 1
    },
    {
      "id": "de866c70-ddfc-462d-86fe-e57de8bcff86",
      "name": "Verify Processed URLs",
      "type": "n8n-nodes-base.if",
      "position": [
        2880,
        -112
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 3,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "1477eb10-5580-4e50-b69b-c20db5b24835",
              "operator": {
                "type": "string",
                "operation": "notEmpty",
                "singleValue": true
              },
              "leftValue": "={{ $json.data }}",
              "rightValue": ""
            }
          ]
        }
      },
      "typeVersion": 2.3
    },
    {
      "id": "ebc293f8-a266-4dc3-8564-f52af846286f",
      "name": "Loop Tag Extraction",
      "type": "n8n-nodes-base.splitInBatches",
      "position": [
        3216,
        -128
      ],
      "parameters": {
        "options": {}
      },
      "executeOnce": false,
      "typeVersion": 3
    },
    {
      "id": "191a564d-d639-4a58-b7be-aa1d0ae4c7e0",
      "name": "Aggregate Loop Data",
      "type": "n8n-nodes-base.merge",
      "position": [
        3744,
        -16
      ],
      "parameters": {
        "mode": "combine",
        "options": {},
        "combineBy": "combineByPosition"
      },
      "typeVersion": 3.2
    },
    {
      "id": "d9b137a3-99bb-4e30-9ea8-36604eab2488",
      "name": "Format Final Dataset",
      "type": "n8n-nodes-base.set",
      "position": [
        4080,
        -144
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "7dc8b263-bc95-4d2a-b363-a9121dd97bf1",
              "name": "URL",
              "type": "string",
              "value": "={{ Array.isArray($json.address) ? $json.address.join('\\n') : $json.address }}"
            },
            {
              "id": "90b396fc-6f73-48d1-ace5-5ae7e0441032",
              "name": "HTTP Status Code",
              "type": "number",
              "value": "={{ Array.isArray($json.statusCode) ? $json.statusCode.join('\\n') : $json.statusCode }}"
            },
            {
              "id": "41f111b1-3804-4716-b8d8-35e5130233ee",
              "name": "Title",
              "type": "string",
              "value": "={{ Array.isArray($json.title) ? $json.title.join('\\n') : $json.title }}"
            },
            {
              "id": "961e22e2-c48a-4fe6-bd6b-28b9b94e7bc8",
              "name": "Meta Description",
              "type": "string",
              "value": "={{ Array.isArray($json.meta_description) ? $json.meta_description.join('\\n') : $json.meta_description }}"
            },
            {
              "id": "23f4bfc2-f8fa-4cbc-a2f7-4e16088f8ef8",
              "name": "H1",
              "type": "string",
              "value": "={{ Array.isArray($json.h1) ? $json.h1.join('\\n') : $json.h1 }}"
            },
            {
              "id": "ccec095c-2e91-44d8-a4ff-f95d2fae68b5",
              "name": "H2",
              "type": "string",
              "value": "={{ Array.isArray($json.h2) ? $json.h2.join('\\n') : $json.h2 }}"
            },
            {
              "id": "2190d715-1828-48ed-9e69-b64def1d631f",
              "name": "Meta Robots",
              "type": "string",
              "value": "={{ Array.isArray($json.meta_robots) ? $json.meta_robots.join('\\n') : $json.meta_robots }}"
            },
            {
              "id": "e98741e2-eb06-4346-b4ed-f3dcf4f6073e",
              "name": "x_robots_tag",
              "type": "string",
              "value": "={{ Array.isArray($json.x_robots_tag) ? $json.x_robots_tag.join('\\n') : $json.x_robots_tag }}"
            },
            {
              "id": "36812f35-cf7a-4235-9ac3-90ece700b474",
              "name": "meta_charset",
              "type": "string",
              "value": "={{ Array.isArray($json.meta_charset) ? $json.meta_charset.join('\\n') : $json.meta_charset }}"
            },
            {
              "id": "dc2527f1-ce73-4b78-b279-14b5d9bdf08d",
              "name": "meta_viewport",
              "type": "string",
              "value": "={{ Array.isArray($json.meta_viewport) ? $json.meta_viewport.join('\\n') : $json.meta_viewport }}"
            },
            {
              "id": "68d10bb4-a2bc-409a-b406-21a376d51e98",
              "name": "HTML Lang",
              "type": "string",
              "value": "={{ Array.isArray($json.html_lang) ? $json.html_lang.join('\\n') : $json.html_lang }}"
            },
            {
              "id": "d09d61ac-5d58-4f47-8288-c9201ca96d90",
              "name": "Canonical",
              "type": "string",
              "value": "={{ Array.isArray($json.canonical) ? $json.canonical.join('\\n') : $json.canonical }}"
            },
            {
              "id": "659e3283-0ff4-4d3f-9a58-df69db5985cc",
              "name": "Hreflang",
              "type": "string",
              "value": "={{ Array.isArray($json.hreflang) ? $json.hreflang.join('\\n') : $json.hreflang }}"
            },
            {
              "id": "6602787c-6399-4ffc-a845-0960df1b6076",
              "name": "Hreflang URL",
              "type": "string",
              "value": "={{ Array.isArray($json.hreflang_url) ? $json.hreflang_url.join('\\n') : $json.hreflang_url }}"
            },
            {
              "id": "d7b4e6b2-de5e-434a-9783-4aef2c5a082f",
              "name": "OG Title",
              "type": "string",
              "value": "={{ Array.isArray($json.og_title) ? $json.og_title.join('\\n') : $json.og_title }}"
            },
            {
              "id": "84d41988-7261-4ce8-869c-94c01b23b42b",
              "name": "OG Description",
              "type": "string",
              "value": "={{ Array.isArray($json.og_description) ? $json.og_description.join('\\n') : $json.og_description }}"
            },
            {
              "id": "62a48b0d-ee18-40c3-9818-686277b0419a",
              "name": "OG URL",
              "type": "string",
              "value": "={{ Array.isArray($json.og_url) ? $json.og_url.join('\\n') : $json.og_url }}"
            },
            {
              "id": "83bf1fb7-9e3e-4118-a9ed-f44154afe624",
              "name": "OG Type",
              "type": "string",
              "value": "={{ Array.isArray($json.og_type) ? $json.og_type.join('\\n') : $json.og_type }}"
            },
            {
              "id": "c8606b2d-6330-49c8-990c-0da8a5eeffd5",
              "name": "OG Site Name",
              "type": "string",
              "value": "={{ Array.isArray($json.og_site_name) ? $json.og_site_name.join('\\n') : $json.og_site_name }}"
            },
            {
              "id": "29b6e219-b20e-4d66-b600-1f6fd1a8af0a",
              "name": "OG Locale",
              "type": "string",
              "value": "={{ Array.isArray($json.og_locale) ? $json.og_locale.join('\\n') : $json.og_locale }}"
            },
            {
              "id": "e2712bb6-c6c5-4609-8226-c2e02ed82ed1",
              "name": "OG Image",
              "type": "string",
              "value": "={{ Array.isArray($json.og_image) ? $json.og_image.join('\\n') : $json.og_image }}"
            },
            {
              "id": "18e128c6-4b72-4879-bf9d-7d0dc78b58b7",
              "name": "Twitter Card",
              "type": "string",
              "value": "={{ Array.isArray($json.twitter_card) ? $json.twitter_card.join('\\n') : $json.twitter_card }}"
            },
            {
              "id": "c8fc32ce-71ff-4823-93ef-4585fe3e81ad",
              "name": "Twitter Title",
              "type": "string",
              "value": "={{ Array.isArray($json.twitter_title) ? $json.twitter_title.join('\\n') : $json.twitter_title }}"
            },
            {
              "id": "4e27e6ac-0d32-41de-93a2-3a7a37b7c74a",
              "name": "Twitter Description",
              "type": "string",
              "value": "={{ Array.isArray($json.twitter_description) ? $json.twitter_description.join('\\n') : $json.twitter_description }}"
            },
            {
              "id": "48dcc1ce-68e4-4863-8a22-de31a377c0fc",
              "name": "Twitter Image",
              "type": "string",
              "value": "={{ Array.isArray($json.twitter_image) ? $json.twitter_image.join('\\n') : $json.twitter_image }}"
            },
            {
              "id": "4062a4b8-70e7-4994-b689-8687532932d3",
              "name": "Twitter Site",
              "type": "string",
              "value": "={{ Array.isArray($json.twitter_site) ? $json.twitter_site.join('\\n') : $json.twitter_site }}"
            },
            {
              "id": "fbfa34fc-2c0a-4344-a4b5-bf83e3073c2d",
              "name": "Twitter Creator",
              "type": "string",
              "value": "={{ Array.isArray($json.twitter_creator) ? $json.twitter_creator.join('\\n') : $json.twitter_creator }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "f0b79ba0-8603-4732-a388-efcc598977bb",
      "name": "Generate CSV File",
      "type": "n8n-nodes-base.convertToFile",
      "position": [
        4288,
        -144
      ],
      "parameters": {
        "options": {}
      },
      "executeOnce": false,
      "typeVersion": 1.1
    },
    {
      "id": "cfa3fa90-f41f-49fd-843a-dadfac6cc0f5",
      "name": "Upload to Server",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        4480,
        -144
      ],
      "parameters": {
        "url": "https://uguu.se/upload",
        "method": "POST",
        "options": {},
        "sendBody": true,
        "contentType": "multipart-form-data",
        "bodyParameters": {
          "parameters": [
            {
              "name": "files[]",
              "parameterType": "formBinaryData",
              "inputDataFieldName": "data"
            }
          ]
        }
      },
      "executeOnce": true,
      "typeVersion": 4,
      "continueOnFail": true
    },
    {
      "id": "689fe512-275e-40ee-ac3d-deeaf7d0a1d9",
      "name": "Extract Download URL",
      "type": "n8n-nodes-base.code",
      "position": [
        4720,
        -144
      ],
      "parameters": {
        "jsCode": "const url = $json.files?.[0]?.url;\nreturn [\n  {\n    json: {\n      message: `<${url}>`\n    }\n  }\n];"
      },
      "typeVersion": 2
    },
    {
      "id": "1f27a501-b0ef-49c3-a190-4195374d4f11",
      "name": "Send Download Link",
      "type": "@n8n/n8n-nodes-langchain.chat",
      "position": [
        4896,
        -144
      ],
      "parameters": {
        "message": "=The process is complete. Download your SEO On-page audit results here:\n{{ $json.message }}\n",
        "options": {},
        "waitUserReply": false
      },
      "executeOnce": true,
      "typeVersion": 1
    },
    {
      "id": "b37b8114-f866-4dba-8d80-94d251375042",
      "name": "Extract Header Data",
      "type": "n8n-nodes-base.set",
      "position": [
        3568,
        -112
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "a2c79cdd-16a9-4c00-a980-6e98019a8d62",
              "name": "address",
              "type": "string",
              "value": "={{ $json.address }}"
            },
            {
              "id": "3458f23b-c615-499d-b4d0-35656377bfda",
              "name": "x_robots_tag",
              "type": "string",
              "value": "={{$json.headers['x-robots-tag'] || $json.headers['X-Robots-Tag'] || ''}}"
            },
            {
              "id": "923a9675-048c-4e74-9186-31d909d48515",
              "name": "statusCode",
              "type": "number",
              "value": "={{ $json.statusCode }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "86eff2e8-b349-4e9a-85b2-017dfdfaf80a",
      "name": "Send Fetch Error",
      "type": "@n8n/n8n-nodes-langchain.chat",
      "position": [
        3152,
        496
      ],
      "parameters": {
        "message": "=URL Rejected: {{ $('Split Into Individual Items').item.json.url }}",
        "options": {},
        "waitUserReply": false
      },
      "executeOnce": false,
      "typeVersion": 1
    },
    {
      "id": "350b13db-1c63-4fd0-adbc-851a4755eac2",
      "name": "Map Failed Request Data",
      "type": "n8n-nodes-base.set",
      "position": [
        3376,
        496
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "97c84cac-a76e-40c7-98e8-a6d22964b522",
              "name": "address",
              "type": "string",
              "value": "={{ $json.url }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "fdbb82ed-a9e8-4a4b-8f13-920cfd8583b7",
      "name": "Send Status Code Error",
      "type": "@n8n/n8n-nodes-langchain.chat",
      "position": [
        3776,
        544
      ],
      "parameters": {
        "message": "=URL Rejected: {{ $('Split Into Individual Items').item.json.url }}",
        "options": {},
        "waitUserReply": false
      },
      "executeOnce": false,
      "typeVersion": 1
    },
    {
      "id": "a00e6911-89d3-40e5-ac0b-925c72946195",
      "name": "Map Status Error Data",
      "type": "n8n-nodes-base.set",
      "position": [
        3968,
        544
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "609c5844-7269-4d86-9d96-8e133c5c15cb",
              "name": "address",
              "type": "string",
              "value": "={{ $('Split Into Individual Items').item.json.url }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "938a1864-5936-4fd4-afa5-1aec47c4734d",
      "name": "Map Compliance Error Data",
      "type": "n8n-nodes-base.set",
      "position": [
        4560,
        576
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "7f0f48f2-2bd0-455b-b68e-3248e021920b",
              "name": "address",
              "type": "string",
              "value": "={{ $('Split Into Individual Items').item.json.url }}"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "ea14f997-5730-446d-bcca-60e506b12a0d",
      "name": "Format Valid Page Data",
      "type": "n8n-nodes-base.code",
      "position": [
        4896,
        336
      ],
      "parameters": {
        "jsCode": "return items.map(item => ({\n  json: {\n    address: $('Split Into Individual Items').item.json.url,\n    data: item.json.data,\n    headers: item.json.headers,\n    statusCode: item.json.statusCode\n  }\n}));"
      },
      "executeOnce": false,
      "typeVersion": 2
    },
    {
      "id": "c5bde9eb-c205-497a-889d-d77f864fe5d3",
      "name": "Send Success URL Notification",
      "type": "@n8n/n8n-nodes-langchain.chat",
      "position": [
        5008,
        624
      ],
      "parameters": {
        "message": "=URL Processed: {{ $('Split Into Individual Items').item.json.url }}",
        "options": {},
        "waitUserReply": false
      },
      "executeOnce": false,
      "typeVersion": 1
    },
    {
      "id": "1c991b45-cfd2-4cc2-8a1d-78f2fdd33285",
      "name": "Send Error URL",
      "type": "@n8n/n8n-nodes-langchain.chat",
      "position": [
        4400,
        576
      ],
      "parameters": {
        "message": "=URL Rejected: {{ $('Split Into Individual Items').item.json.url }}",
        "options": {},
        "waitUserReply": false
      },
      "executeOnce": false,
      "typeVersion": 1
    },
    {
      "id": "15c94976-d704-4008-9596-b6655d955cba",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        480,
        80
      ],
      "parameters": {
        "color": 7,
        "width": 1856,
        "height": 608,
        "content": "## 1\ufe0f\u20e3 Phase 1: Input & Validation\nProcesses chat input to extract URLs and enforces the 100-URL limit. Formats the data and splits it into independent items for loop processing."
      },
      "typeVersion": 1
    },
    {
      "id": "8f3cfcaf-11ea-4572-8ea0-31639d3c05aa",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        2400,
        224
      ],
      "parameters": {
        "color": 7,
        "width": 2800,
        "height": 704,
        "content": "## 2\ufe0f\u20e3 Phase 2: Fetching & Compliance\nExecutes HTTP GET requests to retrieve raw HTML and response headers. Evaluates status codes and DOM structure to filter bot-protection triggers and map failed requests."
      },
      "typeVersion": 1
    },
    {
      "id": "46d3f7de-9e72-48f9-9bb5-a9795489c2fe",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        2352,
        -288
      ],
      "parameters": {
        "color": 7,
        "width": 1616,
        "height": 496,
        "content": "## 3\ufe0f\u20e3 Phase 3: Extraction & Preservation\nParses HTML tags using CSS selectors and maps HTTP response headers. Aggregates the processed items into a single array."
      },
      "typeVersion": 1
    },
    {
      "id": "b3b5072d-808d-4231-8901-825f1618984e",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        4016,
        -272
      ],
      "parameters": {
        "color": 7,
        "width": 1072,
        "height": 320,
        "content": "## 4\ufe0f\u20e3 Phase 4: Compilation & Delivery\nFlattens the dataset to generate a binary CSV file. Uploads the file to an external server and delivers the download URL to the chat interface."
      },
      "typeVersion": 1
    },
    {
      "id": "272bfc44-9634-4156-8bb6-0c478a07f083",
      "name": "Sticky Note5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -320,
        448
      ],
      "parameters": {
        "color": 3,
        "width": 736,
        "height": 304,
        "content": "## Workflow Limitations\n\n* **Execution Time:** Processing a 100-URL batch requires approximately 25-30minutes. This duration results from sequential processing designed to avoid rate limits and manage network timeouts.\n* **Sequential Processing:** The workflow uses a batch size of one. This prevents parallel execution and increases the total time required for large lists.\n* **Security Rejections:** Target domains utilizing bot protection (such as Cloudflare or CAPTCHAs) may reject requests despite the compliance audit logic.\n* **Temporary Hosting:** CSV files are uploaded to an external service (Uguu.se). These download links are temporary and the files will be deleted according to the provider's retention policy.\n* **Resource Dependence:** Stability and speed are determined by the local hardware and network connection of the host machine.\n* **Input Ceiling:** There is a hard-coded limit of 100 URLs per execution to prevent system instability."
      },
      "typeVersion": 1
    },
    {
      "id": "82054043-0737-4afb-8a1f-76c0b238fd7e",
      "name": "Extract SEO Tags",
      "type": "n8n-nodes-base.html",
      "position": [
        3424,
        0
      ],
      "parameters": {
        "options": {},
        "operation": "extractHtmlContent",
        "extractionValues": {
          "values": [
            {
              "key": "title",
              "cssSelector": "title"
            },
            {
              "key": "meta_description",
              "attribute": "content",
              "cssSelector": "meta[name=\"description\"]",
              "returnValue": "attribute"
            },
            {
              "key": "meta_robots",
              "attribute": "content",
              "cssSelector": "meta[name=\"robots\"]",
              "returnValue": "attribute"
            },
            {
              "key": "meta_charset",
              "attribute": "charset",
              "cssSelector": "meta[charset]",
              "returnValue": "attribute"
            },
            {
              "key": "meta_viewport",
              "attribute": "content",
              "cssSelector": "meta[name=\"viewport\"]",
              "returnValue": "attribute"
            },
            {
              "key": "html_lang",
              "attribute": "lang",
              "cssSelector": "html",
              "returnValue": "attribute"
            },
            {
              "key": "canonical",
              "attribute": "href",
              "cssSelector": "link[rel=\"canonical\"]",
              "returnValue": "attribute"
            },
            {
              "key": "hreflang",
              "attribute": "hreflang",
              "cssSelector": "link[rel=\"alternate\"][hreflang]",
              "returnArray": true,
              "returnValue": "attribute"
            },
            {
              "key": "hreflang_url",
              "attribute": "href",
              "cssSelector": "link[rel=\"alternate\"][hreflang]",
              "returnArray": true,
              "returnValue": "attribute"
            },
            {
              "key": "og_title",
              "attribute": "content",
              "cssSelector": "meta[property=\"og:title\"]",
              "returnValue": "attribute"
            },
            {
              "key": "og_description",
              "attribute": "content",
              "cssSelector": "meta[property=\"og:description\"]",
              "returnValue": "attribute"
            },
            {
              "key": "og_url",
              "attribute": "content",
              "cssSelector": "meta[property=\"og:url\"]",
              "returnValue": "attribute"
            },
            {
              "key": "og_type",
              "attribute": "content",
              "cssSelector": "meta[property=\"og:type\"]",
              "returnValue": "attribute"
            },
            {
              "key": "og_site_name",
              "attribute": "content",
              "cssSelector": "meta[property=\"og:site_name\"]",
              "returnValue": "attribute"
            },
            {
              "key": "og_locale",
              "attribute": "content",
              "cssSelector": "meta[property=\"og:locale\"]",
              "returnValue": "attribute"
            },
            {
              "key": "og_image",
              "attribute": "content",
              "cssSelector": "meta[property=\"og:image\"]",
              "returnValue": "attribute"
            },
            {
              "key": "og_image_alt",
              "attribute": "content",
              "cssSelector": "meta[property=\"og:image:alt\"]",
              "returnValue": "attribute"
            },
            {
              "key": "og_image_width",
              "attribute": "content",
              "cssSelector": "meta[property=\"og:image:width\"]",
              "returnValue": "attribute"
            },
            {
              "key": "og_image_height",
              "attribute": "content",
              "cssSelector": "meta[property=\"og:image:height\"]",
              "returnValue": "attribute"
            },
            {
              "key": "twitter_card",
              "attribute": "content",
              "cssSelector": "meta[name=\"twitter:card\"]",
              "returnValue": "attribute"
            },
            {
              "key": "twitter_title",
              "attribute": "content",
              "cssSelector": "meta[name=\"twitter:title\"]",
              "returnValue": "attribute"
            },
            {
              "key": "twitter_description",
              "attribute": "content",
              "cssSelector": "meta[name=\"twitter:description\"]",
              "returnValue": "attribute"
            },
            {
              "key": "twitter_image",
              "attribute": "content",
              "cssSelector": "meta[name=\"twitter:image\"]",
              "returnValue": "attribute"
            },
            {
              "key": "twitter_site",
              "attribute": "content",
              "cssSelector": "meta[name=\"twitter:site\"]",
              "returnValue": "attribute"
            },
            {
              "key": "twitter_creator",
              "attribute": "content",
              "cssSelector": "meta[name=\"twitter:creator\"]",
              "returnValue": "attribute"
            },
            {
              "key": "h1",
              "cssSelector": "h1",
              "returnArray": true
            },
            {
              "key": "h2",
              "cssSelector": "h2",
              "returnArray": true
            }
          ]
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "187984ae-d4cc-4519-9395-83d5903100e1",
      "name": "Sticky Note6",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        2448,
        352
      ],
      "parameters": {
        "width": 592,
        "height": 256,
        "content": "\n\n\n\n\n\n\n\n\n\n\n\nManages single-batch iterations for HTTP GET requests to prevent rate-limit blocks and server timeouts during bulk URL fetching."
      },
      "typeVersion": 1
    },
    {
      "id": "84ab50e6-d13b-45bc-8691-fcaa33ea7c8b",
      "name": "Sticky Note7",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        3536,
        320
      ],
      "parameters": {
        "width": 1232,
        "height": 576,
        "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n**Response Routing & Error Mapping**\nEvaluates HTTP status codes and HTML DOM structure to filter bot-protection walls. Routes and maps failed requests."
      },
      "typeVersion": 1
    },
    {
      "id": "e7467fd2-3725-4dcc-9436-50efe2e91562",
      "name": "Sticky Note8",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        3152,
        -192
      ],
      "parameters": {
        "width": 752,
        "height": 368,
        "content": "**DOM Extraction & Data Aggregation**\nIterates over valid HTML payloads to parse CSS selectors, maps preserved HTTP headers, and aggregates items."
      },
      "typeVersion": 1
    }
  ],
  "connections": {
    "Send Error URL": {
      "main": [
        [
          {
            "node": "Map Compliance Error Data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract SEO Tags": {
      "main": [
        [
          {
            "node": "Aggregate Loop Data",
            "type": "main",
            "index": 1
          }
        ]
      ]
    },
    "Send Fetch Error": {
      "main": [
        [
          {
            "node": "Map Failed Request Data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Upload to Server": {
      "main": [
        [
          {
            "node": "Extract Download URL",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Generate CSV File": {
      "main": [
        [
          {
            "node": "Upload to Server",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Aggregate Loop Data": {
      "main": [
        [
          {
            "node": "Loop Tag Extraction",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Header Data": {
      "main": [
        [
          {
            "node": "Aggregate Loop Data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Loop Tag Extraction": {
      "main": [
        [
          {
            "node": "Format Final Dataset",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Extract Header Data",
            "type": "main",
            "index": 0
          },
          {
            "node": "Extract SEO Tags",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Check Empty URL List": {
      "main": [
        [
          {
            "node": "Send Empty Input Error",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Check For Skipped Inputs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Download URL": {
      "main": [
        [
          {
            "node": "Send Download Link",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Format Final Dataset": {
      "main": [
        [
          {
            "node": "Generate CSV File",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Send Progress Update": {
      "main": [
        [
          {
            "node": "Verify Processed URLs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Map Status Error Data": {
      "main": [
        [
          {
            "node": "Loop Through URL Batches",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Verify Processed URLs": {
      "main": [
        [
          {
            "node": "Loop Tag Extraction",
            "type": "main",
            "index": 0
          }
        ],
        []
      ]
    },
    "Format Valid Page Data": {
      "main": [
        [
          {
            "node": "Send Success URL Notification",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Send Status Code Error": {
      "main": [
        [
          {
            "node": "Map Status Error Data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Verify HTTP 200 Status": {
      "main": [
        [
          {
            "node": "Inspect HTML Content Structure",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Send Status Code Error",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Fetch Page HTML Payload": {
      "main": [
        [
          {
            "node": "Verify HTTP 200 Status",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Send Fetch Error",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Format URL JSON Objects": {
      "main": [
        [
          {
            "node": "Split Into Individual Items",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Map Failed Request Data": {
      "main": [
        [
          {
            "node": "Loop Through URL Batches",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Check For Skipped Inputs": {
      "main": [
        [
          {
            "node": "Send Skipped Input Warning",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Loop Through URL Batches": {
      "main": [
        [
          {
            "node": "Remove Duplicate Records",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Fetch Page HTML Payload",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Remove Duplicate Records": {
      "main": [
        [
          {
            "node": "Send Progress Update",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Verify Maximum URL Limit": {
      "main": [
        [
          {
            "node": "Format URL JSON Objects",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Send Maximum Limit Error",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Map Compliance Error Data": {
      "main": [
        [
          {
            "node": "Loop Through URL Batches",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract and Normalize URLs": {
      "main": [
        [
          {
            "node": "Check Empty URL List",
            "type": "main",
            "index": 0
          },
          {
            "node": "Verify Maximum URL Limit",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Receive Chat Message Input": {
      "main": [
        [
          {
            "node": "Extract and Normalize URLs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Split Into Individual Items": {
      "main": [
        [
          {
            "node": "Loop Through URL Batches",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Send Success URL Notification": {
      "main": [
        [
          {
            "node": "Loop Through URL Batches",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Inspect HTML Content Structure": {
      "main": [
        [
          {
            "node": "Validate HTML Compliance Status",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Validate HTML Compliance Status": {
      "main": [
        [
          {
            "node": "Format Valid Page Data",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Send Error URL",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}

About this workflow

Analyze up to 100 URLs in one run and export key on-page SEO data to CSV automatically.

Source: https://n8n.io/workflows/15756/ — 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.