Finds LinkedIn Profiles using natural language

{
  "id": "UsBaGY83vnyZjRoB",
  "meta": {
    "instanceId": "d4e74e27d8d0aa53cd4bdff26f47c18bb91437db0b63a6ba8ec9f78df0e0234f",
    "templateId": "2808",
    "templateCredsSetupCompleted": true
  },
  "name": "TopSourcer - Finds LinkedIn Profiles using natural language",
  "tags": [],
  "nodes": [
    {
      "id": "16a5f4a2-6e00-40f5-bab7-35526550eacd",
      "name": "Wait",
      "type": "n8n-nodes-base.wait",
      "position": [
        3240,
        -280
      ],
      "webhookId": "88c6a5cc-4b33-438c-ba85-2e075a276a78",
      "parameters": {},
      "typeVersion": 1.1
    },
    {
      "id": "f9ff2e4f-176b-453d-8743-cab4d9fd408d",
      "name": "When chat message received",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        1040,
        -180
      ],
      "webhookId": "475042df-7c36-4658-ab1c-ff55c237621f",
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1
    },
    {
      "id": "b988c049-2400-4a3a-b615-f4048832bd8d",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        980,
        -340
      ],
      "parameters": {
        "content": "Click \"Open Chat\" after activating the workflow.

Here, paste in a job description or describe your ideal candidate."
      },
      "typeVersion": 1
    },
    {
      "id": "74cec892-07d6-4e7d-9c6f-becfb51241c8",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1300,
        -300
      ],
      "parameters": {
        "width": 300,
        "content": "Under \"Credential to connect with\" add your openAI API key. Find at: https://platform.openai.com/settings/organization/api-keys
"
      },
      "typeVersion": 1
    },
    {
      "id": "940373af-ca88-44f1-b3c3-fb125ab6daf9",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        2800,
        -360
      ],
      "parameters": {
        "width": 300,
        "content": "For the first condition: {{ $json.start }} is less than 50, so change \"50\" to your desired number of results. 

Each loop fetches the next page, returning 10 results per iteration."
      },
      "typeVersion": 1
    },
    {
      "id": "c2bc0757-753b-4fee-b42b-65e5a0ff4750",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        3160,
        -440
      ],
      "parameters": {
        "color": 5,
        "width": 200,
        "content": "Waits 5 seconds to avoid rate limiting by Google. While it's unlikely you'll be rate-limited since you're authenticated with your cookie, this is just a precaution."
      },
      "typeVersion": 1
    },
    {
      "id": "9007b42b-1a79-4b98-9d75-71894d660c1d",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        3400,
        -600
      ],
      "parameters": {
        "color": 4,
        "width": 380,
        "height": 280,
        "content": "Get this Cookie-Editor. https://chromewebstore.google.com/detail/cookie-editor/hlkenndednhfkekhgcdicdfddnkalmdm

Do a google search --> click this extension --> Export --> Header string.

Then, open this node --> under Header Auth --> edit --> and under cookie value paste in your header string.  

This is to perform an authenticated google search.
"
      },
      "typeVersion": 1
    },
    {
      "id": "b1d2f9dd-227d-4372-89f8-e6d54e94f2fc",
      "name": "Sticky Note5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1680,
        -320
      ],
      "parameters": {
        "content": "Connect your google sheets account and create a document."
      },
      "typeVersion": 1
    },
    {
      "id": "df0fb397-55d0-41ec-a9df-2c39019ad68e",
      "name": "Create a new sheet",
      "type": "n8n-nodes-base.googleSheets",
      "position": [
        1740,
        -180
      ],
      "parameters": {
        "title": "={{ $('Generate a Boolean Search String').item.json.choices[0].message.content.sheet_name + ' ' + $now }}
",
        "options": {},
        "operation": "create",
        "documentId": {
          "__rl": true,
          "mode": "list",
          "value": "1M9UUgw1wPZIBSoPiGTvNIgA19ERgOo5KmD9wx__Y8ZY",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1M9UUgw1wPZIBSoPiGTvNIgA19ERgOo5KmD9wx__Y8ZY/edit?usp=drivesdk",
          "cachedResultName": "Candidates"
        }
      },
      "credentials": {
        "googleSheetsOAuth2Api": {
          "id": "6wBRjmD77d71tAqP",
          "name": "Google Sheets account"
        }
      },
      "typeVersion": 4.5
    },
    {
      "id": "678a0b65-de67-41f0-ada6-23cef1226228",
      "name": "Add columns to new sheet",
      "type": "n8n-nodes-base.googleSheets",
      "position": [
        2220,
        -180
      ],
      "parameters": {
        "columns": {
          "value": {},
          "schema": [
            {
              "id": "linkedin_url",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "linkedin_url",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "autoMapInputData",
          "matchingColumns": [],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        },
        "options": {},
        "operation": "append",
        "sheetName": {
          "__rl": true,
          "mode": "id",
          "value": "={{ $('Create a new sheet').item.json.sheetId }}"
        },
        "documentId": {
          "__rl": true,
          "mode": "list",
          "value": "1M9UUgw1wPZIBSoPiGTvNIgA19ERgOo5KmD9wx__Y8ZY",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1M9UUgw1wPZIBSoPiGTvNIgA19ERgOo5KmD9wx__Y8ZY/edit?usp=drivesdk",
          "cachedResultName": "Candidates"
        }
      },
      "credentials": {
        "googleSheetsOAuth2Api": {
          "id": "6wBRjmD77d71tAqP",
          "name": "Google Sheets account"
        }
      },
      "typeVersion": 4.5
    },
    {
      "id": "767491ab-f7dd-4e23-816b-840bc24e5268",
      "name": "set page number for google search",
      "type": "n8n-nodes-base.code",
      "position": [
        2480,
        -180
      ],
      "parameters": {
        "jsCode": "return [{ json: { start: 0 } }];
"
      },
      "typeVersion": 2
    },
    {
      "id": "f76f28a5-8444-4ff9-b62c-0d94a07c6447",
      "name": "Extracts all linkedin urls from the google http response",
      "type": "n8n-nodes-base.code",
      "position": [
        3740,
        -280
      ],
      "parameters": {
        "jsCode": "// Extract LinkedIn profile URLs from HTML
function extractLinkedInUrls(html) {
    // First decode any encoded HTML entities
    html = html.replace(/&/g, '&')
               .replace(/\\u003d/g, '=')
               .replace(/\\x22/g, '\"')
               .replace(/\\x26/g, '&')
               .replace(/\\x3e/g, '>')
               .replace(/\\x3c/g, '<');

    const patterns = [
        // Standard LinkedIn URLs in href
        /(?:https?:)?\/\/(?:[a-z]{2,}\.)?linkedin\.com\/in\/[a-zA-Z0-9._-]+(?:\/[a-z]{2})?/gi,
        // URLs in encoded strings
        /(?:\"url\"|url=)(?:[^\"&]*?)(?:https?:)?\/\/(?:[a-z]{2,}\.)?linkedin\.com\/in\/[a-zA-Z0-9._-]+(?:\/[a-z]{2})?/gi,
        // URLs in JSON strings
        /\"(?:https?:)?\/\/(?:[a-z]{2,}\.)?linkedin\.com\/in\/[a-zA-Z0-9._-]+(?:\/[a-z]{2})?\"/gi
    ];

    const urls = new Set();
    
    patterns.forEach(pattern => {
        const matches = html.matchAll(pattern);
        for (const match of matches) {
            let url = match[0];
            
            // Clean up the URL
            url = url.replace(/^\"url\"|^url=|\"$/g, '') // Remove url= prefix and quotes
                    .replace(/^[\"']|[\"']$/g, '')      // Remove surrounding quotes
                    .replace(/\\+/g, '')              // Remove backslashes
                    .trim();
            
            // Ensure URL has protocol
            if (!url.startsWith('http')) {
                url = 'https://' + url.replace(/^\/\//, '');
            }
            
            // Only include if it's a LinkedIn profile URL
            if (url.includes('linkedin.com/in/')) {
                // Clean the URL: remove tracking parameters and fragments
                url = url.split(/[?#&]/)[0];
                
                // Remove any trailing slashes
                url = url.replace(/\/$/, '');
                
                // Add to Set to remove duplicates
                urls.add(url);
            }
        }
    });

    return Array.from(urls);
}

// Get the HTML from input
const html = $input.first().json.data;

// Extract URLs and create array of objects
const linkedInProfiles = extractLinkedInUrls(html)
    .filter(url => !url.includes('google.com')) // Extra safety check to remove any Google URLs
    .map(url => ({
        linkedin_url: url
    }));

// Return the array of objects directly
return linkedInProfiles;"
      },
      "typeVersion": 2
    },
    {
      "id": "5a93c8f2-f55b-4d0e-92f8-0d86147f8d13",
      "name": "Google Boolean Search",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        3500,
        -300
      ],
      "parameters": {
        "url": "https://www.google.com/search",
        "options": {},
        "sendQuery": true,
        "sendHeaders": true,
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "queryParameters": {
          "parameters": [
            {
              "name": "q",
              "value": "={{ $('Generate a Boolean Search String').first().json.choices[0].message.content.search_string }}
"
            },
            {
              "name": "start",
              "value": "={{ $json.start }}"
            }
          ]
        },
        "headerParameters": {
          "parameters": [
            {
              "name": "User-Agent",
              "value": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/132.0.0.0 Safari/537.36"
            }
          ]
        }
      },
      "credentials": {
        "httpHeaderAuth": {
          "id": "5T6POWjsPfV558Ta",
          "name": "Header Auth account"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "37b4f264-34f0-47bb-9b1b-fa53beafb2a9",
      "name": "Generate a Boolean Search String",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "position": [
        1320,
        -180
      ],
      "parameters": {
        "modelId": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o-mini",
          "cachedResultName": "GPT-4O-MINI"
        },
        "options": {},
        "messages": {
          "values": [
            {
              "role": "system",
              "content": "You are an expert in Boolean search techniques for Google. When the user send a job description, generate a search string specifically for finding LinkedIn profiles. Your response must always follow this exact format:
site:linkedin.com/in [Boolean search string]
Create the Boolean search string using precise operators (AND, OR, \"\", *, -) to match the job requirements. Focus only on generating the search string - provide no additional commentary or explanations unless specifically requested.

Also return sheet_name (less than 100 char)"
            },
            {
              "content": "={{ $json.chatInput }}"
            }
          ]
        },
        "simplify": false,
        "jsonOutput": true
      },
      "credentials": {
        "openAiApi": {
          "id": "EX7mky4RGLDD6udW",
          "name": "OpenAi account"
        }
      },
      "retryOnFail": false,
      "typeVersion": 1.8
    },
    {
      "id": "99041eff-f094-4c2a-a75a-4b01faf33d1b",
      "name": "If desired results not reached",
      "type": "n8n-nodes-base.if",
      "position": [
        2920,
        -200
      ],
      "parameters": {
        "options": {},
        "conditions": {
          "options": {
            "version": 2,
            "leftValue": "",
            "caseSensitive": true,
            "typeValidation": "strict"
          },
          "combinator": "and",
          "conditions": [
            {
              "id": "da9f8de0-1e75-4ff3-9f81-8e911251416b",
              "operator": {
                "type": "number",
                "operation": "lt"
              },
              "leftValue": "={{ $json.start }}",
              "rightValue": 50
            },
            {
              "id": "a891c085-7f49-4523-8610-40577b3ffd3b",
              "operator": {
                "name": "filter.operator.equals",
                "type": "string",
                "operation": "equals"
              },
              "leftValue": "",
              "rightValue": ""
            }
          ]
        }
      },
      "typeVersion": 2.2
    },
    {
      "id": "d218a1e8-2959-4b7c-a84d-f8e0df82c5e7",
      "name": "Appends the results to the sheet",
      "type": "n8n-nodes-base.googleSheets",
      "position": [
        4040,
        -280
      ],
      "parameters": {
        "columns": {
          "value": {
            "linkedin_url": "={{ $json.linkedin_url }}"
          },
          "schema": [
            {
              "id": "linkedin_url",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "linkedin_url",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Full Name",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Full Name",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "First Name",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "First Name",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Headline",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Headline",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Candidate Summary",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Candidate Summary",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Experiences Summary",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "Experiences Summary",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Education Summary",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "Education Summary",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Skills",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Skills",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "City",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "City",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Country",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "Country",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Criteria_Assessment",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "Criteria_Assessment",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "overall_fit_score",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "overall_fit_score",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "score_justification",
              "type": "string",
              "display": true,
              "removed": false,
              "required": false,
              "displayName": "score_justification",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Company",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Company",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Company Industry",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Company Industry",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Company Size",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Company Size",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Company LinkedIn URL",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Company LinkedIn URL",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Company Website",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Company Website",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Current Company Join Date",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Current Company Join Date",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Certifications",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Certifications",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Courses Taken",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Courses Taken",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Email",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Email",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Phone",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Phone",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Connections Count",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Connections Count",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Followers Count",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Followers Count",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Languages Spoken",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Languages Spoken",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Projects",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Projects",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            },
            {
              "id": "Date Created",
              "type": "string",
              "display": true,
              "required": false,
              "displayName": "Date Created",
              "defaultMatch": false,
              "canBeUsedToMatch": true
            }
          ],
          "mappingMode": "defineBelow",
          "matchingColumns": [],
          "attemptToConvertTypes": false,
          "convertFieldsToString": false
        },
        "options": {},
        "operation": "append",
        "sheetName": {
          "__rl": true,
          "mode": "id",
          "value": "={{ $('Create a new sheet').first().json.sheetId }}"
        },
        "documentId": {
          "__rl": true,
          "mode": "list",
          "value": "1M9UUgw1wPZIBSoPiGTvNIgA19ERgOo5KmD9wx__Y8ZY",
          "cachedResultUrl": "https://docs.google.com/spreadsheets/d/1M9UUgw1wPZIBSoPiGTvNIgA19ERgOo5KmD9wx__Y8ZY/edit?usp=drivesdk",
          "cachedResultName": "Candidates"
        }
      },
      "credentials": {
        "googleSheetsOAuth2Api": {
          "id": "6wBRjmD77d71tAqP",
          "name": "Google Sheets account"
        }
      },
      "typeVersion": 4.5
    },
    {
      "id": "7a56e7d7-31f8-4115-b993-227bd7221c07",
      "name": "Adds 10 to start - Go to next page",
      "type": "n8n-nodes-base.code",
      "position": [
        4340,
        -220
      ],
      "parameters": {
        "jsCode": "// Get the start value from 'Edit Fields2' node
const startValue =$('If desired results not reached').first().json.start;

// Add 10 to the start value
const start = startValue + 10;

// Return the new value
return [{ json: { start } }];
"
      },
      "typeVersion": 2
    },
    {
      "id": "afe22fc0-c9c1-4aab-a11d-d91740f812bb",
      "name": "Columns to add",
      "type": "n8n-nodes-base.code",
      "position": [
        1980,
        -180
      ],
      "parameters": {
        "jsCode": "return [{
  json: {
    \"linkedin_url\": \"\"
  }
}];
"
      },
      "typeVersion": 2
    }
  ],
  "active": true,
  "pinData": {},
  "settings": {},
  "versionId": "ce389fd9-7697-4e36-8346-6be9414aecf2",
  "connections": {
    "Wait": {
      "main": [
        [
          {
            "node": "Google Boolean Search",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Columns to add": {
      "main": [
        [
          {
            "node": "Add columns to new sheet",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Create a new sheet": {
      "main": [
        [
          {
            "node": "Columns to add",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Google Boolean Search": {
      "main": [
        [
          {
            "node": "Extracts all linkedin urls from the google http response",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Add columns to new sheet": {
      "main": [
        [
          {
            "node": "set page number for google search",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When chat message received": {
      "main": [
        [
          {
            "node": "Generate a Boolean Search String",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "If desired results not reached": {
      "main": [
        [
          {
            "node": "Wait",
            "type": "main",
            "index": 0
          }
        ],
        []
      ]
    },
    "Appends the results to the sheet": {
      "main": [
        [
          {
            "node": "Adds 10 to start - Go to next page",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Generate a Boolean Search String": {
      "main": [
        [
          {
            "node": "Create a new sheet",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "set page number for google search": {
      "main": [
        [
          {
            "node": "If desired results not reached",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Adds 10 to start - Go to next page": {
      "main": [
        [
          {
            "node": "If desired results not reached",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extracts all linkedin urls from the google http response": {
      "main": [
        [
          {
            "node": "Appends the results to the sheet",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}