{
  "version": "1.0.0",
  "exported_at": "2026-05-31T00:00:00.000Z",
  "project": {
    "name": "Zillow Scraper",
    "description": "Best-effort Zillow property listing scraper inferred from the Octoparse Zillow collection. Starts from a concrete Zillow location results URL and extracts Zillow listing-card data: address, price, beds, baths, sqft, status/type text, brokerage, listing URL, ZPID, image URL, days-on-Zillow text, and full card text. Pagination strategy: after each extraction, check for an enabled Zillow Next page link and click through until no next page exists, appending all pages to zillow-scraper.csv. Zillow frequently uses bot protection, CAPTCHA, geoblocking, and dynamic React-rendered markup; if blocked, the flow ends without extraction and the Navigate URL should be replaced with a valid Zillow search URL from a browser session.",
    "color": "bg-[#4589ff]",
    "template_id": "ai-generated"
  },
  "blocks": [
    {
      "block_id": "set-window-size-1",
      "block_type": "process",
      "title": "Set Window Size",
      "description": "Set browser window dimensions",
      "position_x": 120,
      "position_y": 220,
      "config": {
        "width": 1920,
        "height": 1080,
        "color": "bg-[#4589ff]"
      }
    },
    {
      "block_id": "navigate-1",
      "block_type": "process",
      "title": "Navigate",
      "description": "Go to a URL",
      "position_x": 456,
      "position_y": 220,
      "config": {
        "url": "https://www.zillow.com/san-francisco-ca/",
        "color": "bg-[#4589ff]"
      }
    },
    {
      "block_id": "wait-for-page-load-1",
      "block_type": "process",
      "title": "Wait for Page Load",
      "description": "Wait for page to finish loading",
      "position_x": 792,
      "position_y": 220,
      "config": {
        "timeout": 45,
        "color": "bg-[#08bdba]"
      }
    },
    {
      "block_id": "sleep-1",
      "block_type": "process",
      "title": "Sleep",
      "description": "Wait for specified time",
      "position_x": 1128,
      "position_y": 220,
      "config": {
        "duration": 5,
        "color": "bg-[#08bdba]"
      }
    },
    {
      "block_id": "element-exists-1",
      "block_type": "process",
      "title": "Element Exists",
      "description": "Check if element exists",
      "position_x": 1464,
      "position_y": 220,
      "config": {
        "selector": "//button[contains(normalize-space(.), \"Accept\") or contains(normalize-space(.), \"I Accept\") or contains(normalize-space(.), \"Agree\") or contains(normalize-space(.), \"Continue\")]",
        "color": "bg-[#ff832b]"
      }
    },
    {
      "block_id": "click-1",
      "block_type": "process",
      "title": "Click",
      "description": "Click on element",
      "position_x": 1800,
      "position_y": 520,
      "config": {
        "selector": "//button[contains(normalize-space(.), \"Accept\") or contains(normalize-space(.), \"I Accept\") or contains(normalize-space(.), \"Agree\") or contains(normalize-space(.), \"Continue\")]",
        "timeout": 10,
        "color": "bg-[#a56eff]"
      }
    },
    {
      "block_id": "sleep-2",
      "block_type": "process",
      "title": "Sleep",
      "description": "Wait for specified time",
      "position_x": 2136,
      "position_y": 520,
      "config": {
        "duration": 3,
        "color": "bg-[#a56eff]"
      }
    },
    {
      "block_id": "inject-javascript-1",
      "block_type": "process",
      "title": "Inject JavaScript",
      "description": "Execute custom JavaScript",
      "position_x": 2472,
      "position_y": 520,
      "config": {
        "jsCode": "window.scrollTo(0, Math.min(document.body.scrollHeight, 1800));",
        "waitForCompletion": true,
        "timeout": 10,
        "color": "bg-[#a56eff]"
      }
    },
    {
      "block_id": "sleep-3",
      "block_type": "process",
      "title": "Sleep",
      "description": "Wait for specified time",
      "position_x": 2808,
      "position_y": 520,
      "config": {
        "duration": 4,
        "color": "bg-[#08bdba]"
      }
    },
    {
      "block_id": "element-exists-2",
      "block_type": "process",
      "title": "Element Exists",
      "description": "Check if element exists",
      "position_x": 3144,
      "position_y": 520,
      "config": {
        "selector": "article[data-test=\"property-card\"], [data-test=\"property-card\"], [data-testid=\"property-card\"], [data-testid=\"card-container\"], #grid-search-results article, ul.photo-cards li article",
        "color": "bg-[#ff832b]"
      }
    },
    {
      "block_id": "structured-export-1",
      "block_type": "process",
      "title": "Structured Export",
      "description": "Export data with custom columns",
      "position_x": 3480,
      "position_y": 520,
      "config": {
        "rowSelector": "article[data-test=\"property-card\"], [data-test=\"property-card\"], [data-testid=\"property-card\"], [data-testid=\"card-container\"], #grid-search-results article, ul.photo-cards li article",
        "fileName": "zillow-scraper.csv",
        "saveLocation": "C:\\Users\\theskd\\Documents\\UScraper\\templates",
        "includeHeaders": true,
        "fileMode": "append",
        "color": "bg-[#42be65]",
        "columns": [
          {
            "name": "address",
            "selector": "[data-test=\"property-card-addr\"], [data-testid=\"property-card-addr\"], address",
            "attribute": "text"
          },
          {
            "name": "price",
            "selector": "[data-test=\"property-card-price\"], [data-testid=\"property-card-price\"], span[data-test=\"property-card-price\"]",
            "attribute": "text"
          },
          {
            "name": "beds",
            "selector": "(ROW.innerText.match(/(\\d+(?:\\.\\d+)?)\\s*(?:bd|bed|beds)/i)||[])[1]||\"\"",
            "attribute": "text",
            "isJs": true
          },
          {
            "name": "baths",
            "selector": "(ROW.innerText.match(/(\\d+(?:\\.\\d+)?)\\s*(?:ba|bath|baths)/i)||[])[1]||\"\"",
            "attribute": "text",
            "isJs": true
          },
          {
            "name": "living_area_sqft",
            "selector": "((ROW.innerText.match(/([\\d,]+)\\s*(?:sqft|sq ft)/i)||[])[1]||\"\").replace(/,/g,\"\")",
            "attribute": "text",
            "isJs": true
          },
          {
            "name": "status_or_home_type",
            "selector": "Array.from(new Set(ROW.innerText.split(\"\\n\").map(s=>s.trim()).filter(s=>/(for sale|house|condo|townhome|multi-family|lot|land|auction|rent|apartment|new construction|open house)/i.test(s)))).join(\" | \")",
            "attribute": "text",
            "isJs": true
          },
          {
            "name": "brokerage",
            "selector": "[data-test=\"property-card-brokerage\"], [data-testid=\"property-card-brokerage\"]",
            "attribute": "text"
          },
          {
            "name": "listing_url",
            "selector": "a[data-test=\"property-card-link\"], a[data-testid=\"property-card-link\"], a[href*=\"/homedetails/\"], a[href*=\"_zpid\"]",
            "attribute": "href"
          },
          {
            "name": "zpid",
            "selector": "((ROW.querySelector('a[data-test=\"property-card-link\"], a[data-testid=\"property-card-link\"], a[href*=\"/homedetails/\"], a[href*=\"_zpid\"]')?.href || ROW.querySelector('a')?.href || '').match(/\\/(\\d+)_zpid|zpid=(\\d+)/)||[]).filter(Boolean).pop()||\"\"",
            "attribute": "text",
            "isJs": true
          },
          {
            "name": "image_url",
            "selector": "img",
            "attribute": "src"
          },
          {
            "name": "days_on_zillow_text",
            "selector": "(ROW.innerText.match(/\\b\\d+\\s+days?\\s+on\\s+Zillow\\b/i)||[])[0]||\"\"",
            "attribute": "text",
            "isJs": true
          },
          {
            "name": "card_text",
            "selector": "ROW.innerText.trim().replace(/\\s+/g,\" \")",
            "attribute": "text",
            "isJs": true
          }
        ]
      }
    },
    {
      "block_id": "element-exists-3",
      "block_type": "process",
      "title": "Element Exists",
      "description": "Check if element exists",
      "position_x": 3816,
      "position_y": 520,
      "config": {
        "selector": "a[title=\"Next page\"]:not([aria-disabled=\"true\"]), a[rel=\"next\"]:not([aria-disabled=\"true\"]), a[aria-label=\"Next page\"]:not([aria-disabled=\"true\"]), button[title=\"Next page\"]:not([disabled]), button[aria-label=\"Next page\"]:not([disabled])",
        "color": "bg-[#ff832b]"
      }
    },
    {
      "block_id": "click-2",
      "block_type": "process",
      "title": "Click",
      "description": "Click on element",
      "position_x": 4152,
      "position_y": 520,
      "config": {
        "selector": "a[title=\"Next page\"]:not([aria-disabled=\"true\"]), a[rel=\"next\"]:not([aria-disabled=\"true\"]), a[aria-label=\"Next page\"]:not([aria-disabled=\"true\"]), button[title=\"Next page\"]:not([disabled]), button[aria-label=\"Next page\"]:not([disabled])",
        "timeout": 15,
        "color": "bg-[#ff832b]"
      }
    },
    {
      "block_id": "wait-for-page-load-2",
      "block_type": "process",
      "title": "Wait for Page Load",
      "description": "Wait for page to finish loading",
      "position_x": 4488,
      "position_y": 520,
      "config": {
        "timeout": 45,
        "color": "bg-[#08bdba]"
      }
    },
    {
      "block_id": "sleep-4",
      "block_type": "process",
      "title": "Sleep",
      "description": "Wait for specified time",
      "position_x": 4824,
      "position_y": 520,
      "config": {
        "duration": 5,
        "color": "bg-[#ff832b]"
      }
    },
    {
      "block_id": "inject-javascript-2",
      "block_type": "process",
      "title": "Inject JavaScript",
      "description": "Execute custom JavaScript",
      "position_x": 5160,
      "position_y": 520,
      "config": {
        "jsCode": "window.scrollTo(0, Math.min(document.body.scrollHeight, 1800));",
        "waitForCompletion": true,
        "timeout": 10,
        "color": "bg-[#a56eff]"
      }
    },
    {
      "block_id": "sleep-5",
      "block_type": "process",
      "title": "Sleep",
      "description": "Wait for specified time",
      "position_x": 5496,
      "position_y": 758,
      "config": {
        "duration": 3,
        "color": "bg-[#08bdba]"
      }
    },
    {
      "block_id": "end-1",
      "block_type": "output",
      "title": "End",
      "description": "Terminate execution flow",
      "position_x": 3144,
      "position_y": 520,
      "config": {
        "color": "bg-[#8d8d8d]"
      }
    },
    {
      "block_id": "end-2",
      "block_type": "output",
      "title": "End",
      "description": "Terminate execution flow",
      "position_x": 3816,
      "position_y": 520,
      "config": {
        "color": "bg-[#8d8d8d]"
      }
    }
  ],
  "connections": [
    {
      "from_block_id": "set-window-size-1",
      "from_connector_id": "right",
      "to_block_id": "navigate-1",
      "to_connector_id": "left"
    },
    {
      "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": "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": "inject-javascript-1",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "click-1",
      "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"
    },
    {
      "from_block_id": "inject-javascript-1",
      "from_connector_id": "right",
      "to_block_id": "sleep-3",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "sleep-3",
      "from_connector_id": "right",
      "to_block_id": "element-exists-2",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "element-exists-2",
      "from_connector_id": "true",
      "to_block_id": "structured-export-1",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "element-exists-2",
      "from_connector_id": "false",
      "to_block_id": "end-1",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "structured-export-1",
      "from_connector_id": "right",
      "to_block_id": "element-exists-3",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "element-exists-3",
      "from_connector_id": "true",
      "to_block_id": "click-2",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "element-exists-3",
      "from_connector_id": "false",
      "to_block_id": "end-2",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "click-2",
      "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-4",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "sleep-4",
      "from_connector_id": "right",
      "to_block_id": "inject-javascript-2",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "inject-javascript-2",
      "from_connector_id": "right",
      "to_block_id": "sleep-5",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "sleep-5",
      "from_connector_id": "right",
      "to_block_id": "element-exists-2",
      "to_connector_id": "left"
    }
  ],
  "canvas_elements": [
    {
      "id": "group-entry",
      "element_type": "group",
      "title": "Entry & Setup",
      "color": "#4589ff",
      "position_x": 48,
      "position_y": 116,
      "width": 380,
      "height": 296,
      "z_index": 20,
      "data": {
        "memberBlockIds": [
          "set-window-size-1"
        ]
      }
    },
    {
      "id": "group-load",
      "element_type": "group",
      "title": "Page Load",
      "color": "#08bdba",
      "position_x": 384,
      "position_y": 116,
      "width": 5360,
      "height": 834,
      "z_index": 20,
      "data": {
        "memberBlockIds": [
          "navigate-1",
          "wait-for-page-load-1",
          "sleep-1",
          "sleep-2",
          "sleep-3",
          "wait-for-page-load-2",
          "sleep-4",
          "sleep-5"
        ]
      }
    },
    {
      "id": "group-pagination",
      "element_type": "group",
      "title": "Pagination Loop",
      "color": "#ff832b",
      "position_x": 1392,
      "position_y": 116,
      "width": 3008,
      "height": 596,
      "z_index": 20,
      "data": {
        "memberBlockIds": [
          "element-exists-1",
          "click-1",
          "element-exists-2",
          "element-exists-3",
          "click-2"
        ]
      }
    },
    {
      "id": "group-interaction",
      "element_type": "group",
      "title": "Interaction",
      "color": "#a56eff",
      "position_x": 2400,
      "position_y": 416,
      "width": 3008,
      "height": 296,
      "z_index": 20,
      "data": {
        "memberBlockIds": [
          "inject-javascript-1",
          "inject-javascript-2"
        ]
      }
    },
    {
      "id": "group-extract",
      "element_type": "group",
      "title": "Data Extraction",
      "color": "#42be65",
      "position_x": 3408,
      "position_y": 416,
      "width": 380,
      "height": 296,
      "z_index": 20,
      "data": {
        "memberBlockIds": [
          "structured-export-1"
        ]
      }
    },
    {
      "id": "group-control",
      "element_type": "group",
      "title": "Control Flow",
      "color": "#8d8d8d",
      "position_x": 3072,
      "position_y": 416,
      "width": 992,
      "height": 296,
      "z_index": 20,
      "data": {
        "memberBlockIds": [
          "end-1",
          "end-2"
        ]
      }
    },
    {
      "id": "note-overview",
      "element_type": "note",
      "title": "Overview",
      "content": "Best-effort Zillow property listing scraper inferred from the Octoparse Zillow collection. Starts from a concrete Zillow location results URL and extracts Zillow listing-card data: address, price, beds, baths, sqft, status/type text, brokerage, listing URL, ZPID, image URL, days-on-Zillow text, and full card text. Pagination strategy: after each extraction, check for an enabled Zillow Next page link and click through until no next page exists, appending all pages to zillow-scraper.csv. Zillow frequently uses bot protection, CAPTCHA, geoblocking, and dynamic React-rendered markup; if blocked, the flow ends without extraction and the Navigate URL should be replaced with a valid Zillow search URL from a browser session.",
      "color": "#f1c21b",
      "position_x": 80,
      "position_y": 20,
      "width": 480,
      "height": 160,
      "z_index": 22,
      "data": {}
    },
    {
      "id": "note-block-element-exists-1",
      "element_type": "note",
      "title": "Note: Element Exists",
      "content": "Condition block: checks `//button[contains(normalize-space(.), \"Accept\") or contains(normalize-space(.), \"I Accept\") or contains(normalize-space(`. True / False branches control which path runs next. Keep enough space between branches so both connector lines are visible.",
      "color": "#ee5396",
      "position_x": 1664,
      "position_y": 200,
      "width": 340,
      "height": 170,
      "z_index": 22,
      "data": {
        "block_id": "element-exists-1"
      }
    },
    {
      "id": "note-block-inject-javascript-1",
      "element_type": "note",
      "title": "Note: Inject JavaScript",
      "content": "Runs custom JavaScript in the page: `window.scrollTo(0, Math.min(document.body.scrollHeight, 1800));...` Verify in browser if results are empty.",
      "color": "#ee5396",
      "position_x": 2672,
      "position_y": 500,
      "width": 340,
      "height": 128,
      "z_index": 22,
      "data": {
        "block_id": "inject-javascript-1"
      }
    },
    {
      "id": "note-block-element-exists-2",
      "element_type": "note",
      "title": "Note: Element Exists",
      "content": "Condition block: checks `article[data-test=\"property-card\"], [data-test=\"property-card\"], [data-testid=\"property-card\"], [data-testid=\"card-conta`. True / False branches control which path runs next. Keep enough space between branches so both connector lines are visible.",
      "color": "#ee5396",
      "position_x": 3344,
      "position_y": 500,
      "width": 340,
      "height": 170,
      "z_index": 22,
      "data": {
        "block_id": "element-exists-2"
      }
    },
    {
      "id": "note-block-structured-export-1",
      "element_type": "note",
      "title": "Note: Structured Export",
      "content": "Structured export with JS columns (beds, baths, living_area_sqft, status_or_home_type, zpid). These selectors are fragile — update if the site layout changes.",
      "color": "#ee5396",
      "position_x": 3680,
      "position_y": 500,
      "width": 340,
      "height": 132,
      "z_index": 22,
      "data": {
        "block_id": "structured-export-1"
      }
    },
    {
      "id": "note-block-element-exists-3",
      "element_type": "note",
      "title": "Note: Element Exists",
      "content": "Condition block: checks `a[title=\"Next page\"]:not([aria-disabled=\"true\"]), a[rel=\"next\"]:not([aria-disabled=\"true\"]), a[aria-label=\"Next page\"]:n`. True / False branches control which path runs next. Keep enough space between branches so both connector lines are visible.",
      "color": "#ee5396",
      "position_x": 4016,
      "position_y": 500,
      "width": 340,
      "height": 170,
      "z_index": 22,
      "data": {
        "block_id": "element-exists-3"
      }
    },
    {
      "id": "note-block-click-2",
      "element_type": "note",
      "title": "Note: Click",
      "content": "Pagination click — add waits after this block; the page reloads asynchronously.",
      "color": "#ee5396",
      "position_x": 4352,
      "position_y": 500,
      "width": 316,
      "height": 106,
      "z_index": 22,
      "data": {
        "block_id": "click-2"
      }
    }
  ]
}