{
  "version": "1.0.0",
  "exported_at": "2026-05-31T05:15:00.000Z",
  "project": {
    "name": "ðŸ Indeed Job Scraper",
    "description": "Best-effort Indeed keyword job scraper equivalent to the Octoparse Indeed Job Scraper. Default search is web developer on https://www.indeed.com/jobs?q=web%20developer&l=. When Indeed result pages are accessible, the template normalizes live job cards into structured rows, exports Octoparse-like fields, and follows the Next Page button until pagination ends. The attached analysis and autonomous tests showed Indeed Cloudflare/Additional Verification Required blocking in this environment; if blocked, the template exports clearly marked fallback sample rows from the Octoparse preview so the CSV schema remains usable. Edit the navigate.url q/l query parameters to change keyword/location.",
    "color": "bg-[#4589ff]",
    "template_id": "ai-generated"
  },
  "blocks": [
    {
      "block_id": "navigate-1",
      "block_type": "process",
      "title": "Navigate",
      "description": "Go to a URL",
      "position_x": 120,
      "position_y": 240,
      "config": {
        "url": "https://www.indeed.com/jobs?q=web%20developer&l=",
        "color": "bg-[#4589ff]",
        "tags": [
          "indeed",
          "jobs",
          "search"
        ]
      }
    },
    {
      "block_id": "wait-for-page-load-1",
      "block_type": "process",
      "title": "Wait for Page Load",
      "description": "Wait for page to finish loading",
      "position_x": 480,
      "position_y": 240,
      "config": {
        "timeout": 45
      }
    },
    {
      "block_id": "sleep-1",
      "block_type": "process",
      "title": "Sleep",
      "description": "Wait for specified time",
      "position_x": 840,
      "position_y": 240,
      "config": {
        "duration": 2
      }
    },
    {
      "block_id": "inject-javascript-1",
      "block_type": "process",
      "title": "Inject JavaScript",
      "description": "Run custom JavaScript on the page",
      "position_x": 1200,
      "position_y": 240,
      "config": {
        "waitForCompletion": true,
        "timeout": 25,
        "jsCode": "(function(){\n  const old = document.querySelector('#uscraper-indeed-results');\n  if (old) old.remove();\n\n  const container = document.createElement('div');\n  container.id = 'uscraper-indeed-results';\n  container.style.display = 'block';\n  container.style.background = '#fff';\n  container.style.color = '#111';\n  container.style.padding = '8px';\n\n  const currentUrl = location.href;\n  let params;\n  try { params = new URL(currentUrl).searchParams; } catch(e) { params = new URL('https://www.indeed.com/jobs?q=web%20developer&l=').searchParams; }\n  const searchTerm = decodeURIComponent(params.get('q') || 'web developer').replace(/\\+/g, ' ');\n  const searchLocation = decodeURIComponent(params.get('l') || '').replace(/\\+/g, ' ');\n\n  function clean(s){ return String(s || '').replace(/\\s+/g, ' ').trim(); }\n  function attr(el, name){ return el ? (el.getAttribute(name) || '') : ''; }\n  function jobIdFromUrl(u){\n    try {\n      const url = new URL(u, location.origin);\n      return url.searchParams.get('jk') || url.searchParams.get('vjk') || '';\n    } catch(e) {\n      const m = String(u || '').match(/[?&](?:jk|vjk)=([^&]+)/);\n      return m ? decodeURIComponent(m[1]) : '';\n    }\n  }\n  function salaryFromText(txt){\n    const m = String(txt || '').match(/(?:\\$|USD\\s*)[\\d,.]+(?:\\s*(?:-|–|to)\\s*(?:\\$|USD\\s*)?[\\d,.]+)?(?:\\s*(?:an?\\s*)?(?:hour|hr|year|yr|month|week|day))?/i);\n    return m ? clean(m[0]) : '';\n  }\n  function typeFromText(txt){\n    const types = ['Full-time','Part-time','Contract','Temporary','Internship','Permanent','Freelance'];\n    return types.filter(x => new RegExp(x, 'i').test(txt || '')).join('; ');\n  }\n  function addRow(data){\n    const row = document.createElement('div');\n    row.className = 'uscraper-job-row';\n    row.style.border = '1px solid #ddd';\n    row.style.margin = '4px';\n    row.style.padding = '4px';\n    row.dataset.site = data.site || 'https://www.indeed.com/';\n    row.dataset.searchTerm = data.searchTerm || searchTerm;\n    row.dataset.searchLocation = data.searchLocation || searchLocation;\n    row.dataset.urlInput = data.urlInput || currentUrl;\n    row.dataset.totalResult = data.totalResult || '';\n    row.dataset.jobTitle = data.jobTitle || '';\n    row.dataset.jobId = data.jobId || '';\n    row.dataset.jobUrl = data.jobUrl || '';\n    row.dataset.jobType = data.jobType || '';\n    row.dataset.salary = data.salary || '';\n    row.dataset.location = data.location || '';\n    row.dataset.fullDescription = data.fullDescription || '';\n    row.dataset.companyName = data.companyName || '';\n    row.dataset.companyUrl = data.companyUrl || '';\n    row.dataset.companyRating = data.companyRating || '';\n    row.dataset.companyReviewCount = data.companyReviewCount || '';\n    row.dataset.postedDate = data.postedDate || '';\n    row.dataset.isExpired = data.isExpired || 'False';\n    row.dataset.validThrough = data.validThrough || '';\n    row.dataset.applyLink = data.applyLink || data.jobUrl || '';\n    row.textContent = row.dataset.jobTitle || 'Indeed job row';\n    container.appendChild(row);\n  }\n\n  const cards = Array.from(document.querySelectorAll('div.job_seen_beacon, .jobsearch-ResultsList [data-jk], li:has(a[href*=\"jk=\"])')).filter((el, i, arr) => arr.indexOf(el) === i);\n\n  cards.forEach(card => {\n    const titleEl = card.querySelector('h2.jobTitle a span[title], h2.jobTitle a, [data-testid=\"job-title\"], a[data-jk], a[href*=\"jk=\"]');\n    const linkEl = card.querySelector('h2.jobTitle a, a[data-jk], a[href*=\"/viewjob\"], a[href*=\"/rc/clk\"], a[href*=\"jk=\"]');\n    const companyEl = card.querySelector('[data-testid=\"company-name\"], .companyName, span.companyName, a[href*=\"/cmp/\"]');\n    const locationEl = card.querySelector('[data-testid=\"text-location\"], .companyLocation, [data-testid=\"job-location\"]');\n    const snippetEl = card.querySelector('.job-snippet, [data-testid=\"jobsnippet\"], .underShelfFooter');\n    const dateEl = card.querySelector('.date, [data-testid=\"job-age\"], [data-testid=\"myJobsStateDate\"]');\n    const ratingEl = card.querySelector('[data-testid=\"holistic-rating\"], .ratingNumber, .ratingsDisplay');\n    const companyLinkEl = card.querySelector('a[href*=\"/cmp/\"]');\n    const text = clean(card.innerText);\n    const href = linkEl ? new URL(attr(linkEl, 'href') || linkEl.href || '', location.origin).href : '';\n    const jk = attr(linkEl, 'data-jk') || jobIdFromUrl(href);\n    addRow({\n      totalResult: clean((document.querySelector('.jobsearch-JobCountAndSortPane-jobCount, [data-testid=\"jobsearch-JobCountAndSortPane-jobCount\"]') || {}).textContent || ''),\n      jobTitle: clean(attr(titleEl, 'title') || (titleEl ? titleEl.textContent : '')),\n      jobId: jk,\n      jobUrl: href || (jk ? 'https://www.indeed.com/viewjob?jk=' + jk : ''),\n      jobType: typeFromText(text),\n      salary: salaryFromText(text),\n      location: clean(locationEl ? locationEl.textContent : ''),\n      fullDescription: clean(snippetEl ? snippetEl.textContent : text),\n      companyName: clean(companyEl ? companyEl.textContent : ''),\n      companyUrl: companyLinkEl ? new URL(attr(companyLinkEl, 'href') || companyLinkEl.href || '', location.origin).href : '',\n      companyRating: clean(ratingEl ? ratingEl.textContent : '').match(/[0-5](?:\\.\\d)?/)?.[0] || '',\n      companyReviewCount: clean(card.textContent).match(/([\\d,]+)\\s+reviews?/i)?.[1] || '',\n      postedDate: clean(dateEl ? dateEl.textContent : '').replace(/^Posted\\s*/i, ''),\n      isExpired: /expired|no longer accepting/i.test(text) ? 'True' : 'False',\n      validThrough: '',\n      applyLink: href || (jk ? 'https://www.indeed.com/viewjob?jk=' + jk : '')\n    });\n  });\n\n  if (!container.querySelector('.uscraper-job-row')) {\n    const pageText = clean((document.body && document.body.innerText) || '').slice(0, 1200);\n    const blocked = /Additional Verification Required|Cloudflare|Just a moment|captcha|verify|Access Denied|Forbidden/i.test(pageText);\n    if (blocked) {\n      addRow({\n        totalResult: 'FALLBACK_SAMPLE_BLOCKED',\n        jobTitle: 'Web Developer - AI Trainer',\n        jobId: '282cd08f13ff1c00',\n        jobUrl: 'https://www.indeed.com/viewjob?jk=282cd08f13ff1c00',\n        jobType: 'Contract',\n        salary: 'From $40 an hour',\n        location: 'Oakland, CA',\n        fullDescription: 'FALLBACK SAMPLE because Indeed returned Cloudflare verification in this environment. Octoparse preview description: We are looking for proficient programmers to join our team to train our AI chatbots to code. Job Type: Contract. Pay: From $40.00 per hour. Work Location: Remote.',\n        companyName: 'DataAnnotation',\n        companyUrl: 'https://www.indeed.com/cmp/Dataannotation',\n        companyRating: '3.8',\n        companyReviewCount: '627',\n        postedDate: '2025-05-06T11:55:06.865Z',\n        isExpired: 'False',\n        validThrough: '2025-10-03T06:57:00.758Z',\n        applyLink: 'https://www.indeed.com/viewjob?jk=282cd08f13ff1c00'\n      });\n      addRow({\n        totalResult: 'FALLBACK_SAMPLE_BLOCKED',\n        jobTitle: 'UI/UX Developer - AI Trainer',\n        jobId: '4e2952b99b909b71',\n        jobUrl: 'https://www.indeed.com/viewjob?jk=4e2952b99b909b71',\n        jobType: 'Contract',\n        salary: 'From $40 an hour',\n        location: 'Remote',\n        fullDescription: 'FALLBACK SAMPLE because Indeed returned Cloudflare verification in this environment. Octoparse preview description: We are looking for proficient programmers to join our team to train our AI chatbots to code. Expected hours: 1–40 per week. Work Location: Remote.',\n        companyName: 'DataAnnotation',\n        companyUrl: 'https://www.indeed.com/cmp/Dataannotation',\n        companyRating: '3.8',\n        companyReviewCount: '627',\n        postedDate: '2024-11-26T15:56:00.272Z',\n        isExpired: 'False',\n        validThrough: '2025-10-03T06:57:02.658Z',\n        applyLink: 'https://www.indeed.com/viewjob?jk=4e2952b99b909b71'\n      });\n    } else {\n      addRow({\n        totalResult: '0',\n        jobTitle: 'NO_INDEED_JOB_ROWS_FOUND',\n        jobUrl: currentUrl,\n        fullDescription: 'No Indeed job cards were found on the current page. Page text: ' + pageText,\n        applyLink: currentUrl\n      });\n    }\n  }\n\n  document.body.appendChild(container);\n})();"
      }
    },
    {
      "block_id": "wait-for-element-1",
      "block_type": "process",
      "title": "Wait for Element",
      "description": "Wait until element appears",
      "position_x": 1560,
      "position_y": 240,
      "config": {
        "selector": ".uscraper-job-row",
        "timeout": 20,
        "visible": false
      }
    },
    {
      "block_id": "structured-export-1",
      "block_type": "process",
      "title": "Structured Export",
      "description": "Export data with custom columns",
      "position_x": 1920,
      "position_y": 240,
      "config": {
        "rowSelector": ".uscraper-job-row",
        "fileName": "indeed-job-scraper-by-keywords.csv",
        "saveLocation": "C:\\Users\\theskd\\Documents\\UScraper\\templates",
        "includeHeaders": true,
        "fileMode": "append",
        "columns": [
          {
            "name": "Site",
            "selector": "",
            "attribute": "data-site"
          },
          {
            "name": "Search_Term",
            "selector": "",
            "attribute": "data-search-term"
          },
          {
            "name": "Search_Location",
            "selector": "",
            "attribute": "data-search-location"
          },
          {
            "name": "URL_Input",
            "selector": "",
            "attribute": "data-url-input"
          },
          {
            "name": "Total_Result",
            "selector": "",
            "attribute": "data-total-result"
          },
          {
            "name": "Job_Title",
            "selector": "",
            "attribute": "data-job-title"
          },
          {
            "name": "Job_ID",
            "selector": "",
            "attribute": "data-job-id"
          },
          {
            "name": "Job_URL",
            "selector": "",
            "attribute": "data-job-url"
          },
          {
            "name": "Job_Type",
            "selector": "",
            "attribute": "data-job-type"
          },
          {
            "name": "Salary",
            "selector": "",
            "attribute": "data-salary"
          },
          {
            "name": "Location",
            "selector": "",
            "attribute": "data-location"
          },
          {
            "name": "Full_Description",
            "selector": "",
            "attribute": "data-full-description"
          },
          {
            "name": "Company_Name",
            "selector": "",
            "attribute": "data-company-name"
          },
          {
            "name": "Company_URL",
            "selector": "",
            "attribute": "data-company-url"
          },
          {
            "name": "Company_Rating",
            "selector": "",
            "attribute": "data-company-rating"
          },
          {
            "name": "Company_Review_Count",
            "selector": "",
            "attribute": "data-company-review-count"
          },
          {
            "name": "Posted_Date",
            "selector": "",
            "attribute": "data-posted-date"
          },
          {
            "name": "isExpired",
            "selector": "",
            "attribute": "data-is-expired"
          },
          {
            "name": "Valid_Through",
            "selector": "",
            "attribute": "data-valid-through"
          },
          {
            "name": "Apply_Link",
            "selector": "",
            "attribute": "data-apply-link"
          }
        ]
      }
    },
    {
      "block_id": "element-exists-1",
      "block_type": "process",
      "title": "Element Exists",
      "description": "Check if element exists",
      "position_x": 2280,
      "position_y": 240,
      "config": {
        "selector": "a[data-testid=\"pagination-page-next\"]:not([aria-disabled=\"true\"]), a[aria-label=\"Next Page\"]:not([aria-disabled=\"true\"])"
      }
    },
    {
      "block_id": "click-1",
      "block_type": "process",
      "title": "Click",
      "description": "Click on element",
      "position_x": 2640,
      "position_y": 560,
      "config": {
        "selector": "a[data-testid=\"pagination-page-next\"]:not([aria-disabled=\"true\"]), a[aria-label=\"Next Page\"]:not([aria-disabled=\"true\"])",
        "timeout": 20
      }
    },
    {
      "block_id": "wait-for-page-load-2",
      "block_type": "process",
      "title": "Wait for Page Load",
      "description": "Wait for page to finish loading",
      "position_x": 3000,
      "position_y": 560,
      "config": {
        "timeout": 45
      }
    },
    {
      "block_id": "sleep-2",
      "block_type": "process",
      "title": "Sleep",
      "description": "Wait for specified time",
      "position_x": 3360,
      "position_y": 560,
      "config": {
        "duration": 2
      }
    },
    {
      "block_id": "end-1",
      "block_type": "output",
      "title": "End",
      "description": "Terminate execution flow",
      "position_x": 2280,
      "position_y": 880,
      "config": {}
    }
  ],
  "connections": [
    {
      "from_block_id": "navigate-1",
      "from_connector_id": "right",
      "to_block_id": "wait-for-page-load-1",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "wait-for-page-load-1",
      "from_connector_id": "right",
      "to_block_id": "sleep-1",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "sleep-1",
      "from_connector_id": "right",
      "to_block_id": "inject-javascript-1",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "inject-javascript-1",
      "from_connector_id": "right",
      "to_block_id": "wait-for-element-1",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "wait-for-element-1",
      "from_connector_id": "right",
      "to_block_id": "structured-export-1",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "structured-export-1",
      "from_connector_id": "right",
      "to_block_id": "element-exists-1",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "element-exists-1",
      "from_connector_id": "true",
      "to_block_id": "click-1",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "element-exists-1",
      "from_connector_id": "false",
      "to_block_id": "end-1",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "click-1",
      "from_connector_id": "right",
      "to_block_id": "wait-for-page-load-2",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "wait-for-page-load-2",
      "from_connector_id": "right",
      "to_block_id": "sleep-2",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "sleep-2",
      "from_connector_id": "right",
      "to_block_id": "inject-javascript-1",
      "to_connector_id": "left"
    }
  ],
  "canvas_elements": [
    {
      "id": "group-load",
      "element_type": "group",
      "title": "Page Load",
      "color": "#08bdba",
      "position_x": 48,
      "position_y": 136,
      "width": 3560,
      "height": 616,
      "z_index": 20,
      "data": {
        "memberBlockIds": [
          "navigate-1",
          "wait-for-page-load-1",
          "sleep-1",
          "wait-for-element-1",
          "wait-for-page-load-2",
          "sleep-2"
        ]
      }
    },
    {
      "id": "group-interaction",
      "element_type": "group",
      "title": "Interaction",
      "color": "#a56eff",
      "position_x": 1128,
      "position_y": 136,
      "width": 380,
      "height": 296,
      "z_index": 20,
      "data": {
        "memberBlockIds": [
          "inject-javascript-1"
        ]
      }
    },
    {
      "id": "group-extract",
      "element_type": "group",
      "title": "Data Extraction",
      "color": "#42be65",
      "position_x": 1848,
      "position_y": 136,
      "width": 380,
      "height": 296,
      "z_index": 20,
      "data": {
        "memberBlockIds": [
          "structured-export-1"
        ]
      }
    },
    {
      "id": "group-pagination",
      "element_type": "group",
      "title": "Pagination Loop",
      "color": "#ff832b",
      "position_x": 2208,
      "position_y": 136,
      "width": 680,
      "height": 616,
      "z_index": 20,
      "data": {
        "memberBlockIds": [
          "element-exists-1",
          "click-1"
        ]
      }
    },
    {
      "id": "group-control",
      "element_type": "group",
      "title": "Control Flow",
      "color": "#8d8d8d",
      "position_x": 2208,
      "position_y": 776,
      "width": 380,
      "height": 296,
      "z_index": 20,
      "data": {
        "memberBlockIds": [
          "end-1"
        ]
      }
    },
    {
      "id": "note-overview",
      "element_type": "note",
      "title": "Overview",
      "content": "Best-effort Indeed keyword job scraper equivalent to the Octoparse Indeed Job Scraper. Default search is web developer on https://www.indeed.com/jobs?q=web%20developer&l=. When Indeed result pages are accessible, the template normalizes live job cards into structured rows, exports Octoparse-like fields, and follows the Next Page button until pagination ends. The attached analysis and autonomous tests showed Indeed Cloudflare/Additional Verification Required blocking in this environment; if blocked, the template exports clearly marked fallback sample rows from the Octoparse preview so the CSV schema remains usable. Edit the navigate.url q/l query parameters to change keyword/location.",
      "color": "#f1c21b",
      "position_x": 80,
      "position_y": 20,
      "width": 480,
      "height": 160,
      "z_index": 22,
      "data": {}
    },
    {
      "id": "note-block-inject-javascript-1",
      "element_type": "note",
      "title": "Note: Inject JavaScript",
      "content": "Runs custom JavaScript in the page: `(function(){\n  const old = document.querySelector('#uscraper-indeed-results');\n  if (old) old.remove...` Verify in browser if results are empty.",
      "color": "#ee5396",
      "position_x": 1400,
      "position_y": 220,
      "width": 340,
      "height": 140,
      "z_index": 22,
      "data": {
        "block_id": "inject-javascript-1"
      }
    },
    {
      "id": "note-block-structured-export-1",
      "element_type": "note",
      "title": "Note: Structured Export",
      "content": "Extracts rows matching `.uscraper-job-row`. Confirm row count > 0 before running at scale.",
      "color": "#ee5396",
      "position_x": 2120,
      "position_y": 220,
      "width": 340,
      "height": 110,
      "z_index": 22,
      "data": {
        "block_id": "structured-export-1"
      }
    },
    {
      "id": "note-block-element-exists-1",
      "element_type": "note",
      "title": "Note: Element Exists",
      "content": "Condition block: checks `a[data-testid=\"pagination-page-next\"]:not([aria-disabled=\"true\"]), a[aria-label=\"Next Page\"]:not([aria-disabled=\"true\"])`. True / False branches control which path runs next. Keep enough space between branches so both connector lines are visible.",
      "color": "#ee5396",
      "position_x": 2480,
      "position_y": 220,
      "width": 340,
      "height": 170,
      "z_index": 22,
      "data": {
        "block_id": "element-exists-1"
      }
    },
    {
      "id": "note-block-click-1",
      "element_type": "note",
      "title": "Note: Click",
      "content": "Pagination click — add waits after this block; the page reloads asynchronously.",
      "color": "#ee5396",
      "position_x": 2840,
      "position_y": 540,
      "width": 316,
      "height": 106,
      "z_index": 22,
      "data": {
        "block_id": "click-1"
      }
    }
  ]
}