Community / Mass Importer / Bay Area Zipcode 95433

We utilize this data source to train our price prediction model so as to identify undervalued real estates that were listed for sale.

Domain: zillow.com , Associated categories: Real Estate

Harvested on CSV JSON HTML

Data source unique ID

n3432_dd7d14efc0f6d6da937e06efe8601833eses

Privacy

Public

Last ran status

COMPLETED

Last ran

2016-11-09 17:16:23 UTC

Crawl Frequency

Not scheduled

Urls to Crawl

Provide your own list of URLs you want to get data from

http://www.zillow.com/browse/homes/pr/vega-alta-county/95433/

{
    "engine": "sinatra",
    "origin_url": "http://www.zillow.com/browse/homes/pr/vega-alta-county/48205/",
    "columns": [
        {
            "col_name": "street",
            "dom_query": ".browse-content .zsg-lg-1-2:nth-child(1) li a"
        },
        {
            "col_name": "street page",
            "dom_query": ".browse-content .zsg-lg-1-2:nth-child(1) li a",
            "required_attribute": "href",
            "options": {
                "columns": [
                    {
                        "col_name": "apartment name",
                        "dom_query": ".browse-content .zsg-lg-1-2:nth-child(1) li a"
                    },
                    {
                        "col_name": "apartment page",
                        "dom_query": ".browse-content .zsg-lg-1-2:nth-child(1) li a",
                        "required_attribute": "href",
                        "options": {
                            "columns": [
                                {
                                    "col_name": "address",
                                    "dom_query": "header h1"
                                },
                                {
                                    "col_name": "neighborhood",
                                    "dom_query": "h2:contains('Neighborhood')",
                                    "regex_pattern": "Neighborhood: (.*)",
                                    "regex_group": 1
                                },
                                {
                                    "col_name": "configuration",
                                    "dom_query": ".zsg-content-header.addr h3"
                                },
                                {
                                    "col_name": "bedrooms",
                                    "dom_query": ".zsg-content-header.addr h3 .addr_bbs:nth-child(2)"
                                },
                                {
                                    "col_name": "bathrooms",
                                    "dom_query": ".zsg-content-header.addr h3 .addr_bbs:nth-child(4)"
                                },
                                {
                                    "col_name": "size",
                                    "dom_query": ".zsg-content-header.addr h3 .addr_bbs:nth-child(6)"
                                },
                                {
                                    "col_name": "price",
                                    "dom_query": ".main-row.home-summary-row",
                                    "regex_pattern": "[0-9,]+"
                                },
                                {
                                    "col_name": "parking",
                                    "dom_query": "h3:contains('Facts') + .zsg-list_square li:contains('Parking:'):first",
                                    "regex_pattern": "Parking: (.*)",
                                    "regex_group": 1
                                },
                                {
                                    "col_name": "year built",
                                    "dom_query": "p:contains('built in')",
                                    "regex_pattern": "built in ([0-9]+)",
                                    "regex_group": 1
                                },
                                {
                                    "col_name": "transaction_type",
                                    "dom_query": ".status-icon-row"
                                },
                                {
                                    "col_name": "bmr",
                                    "dom_query": ".notranslate:contains('Fair Housing Opportunity'), .notranslate:contains('BMR'):first"
                                },
                                {
                                    "col_name": "ccrc",
                                    "dom_query": ".notranslate:contains('retirement community'), .notranslate:contains('CCRC'):first"
                                },
                                {
                                    "col_name": "home_type",
                                    "dom_query": ".zsg-list_square li:contains('Single Family'):first, .zsg-list_square li:contains('Apartment'):first, .zsg-list_square li:contains('Townhouse'):first, .zsg-list_square li:contains('Manufactured'):first"
                                },
                                {
                                    "col_name": "sfh",
                                    "dom_query": ".zsg-list_square li:contains('Single Family'):first"
                                },
                                {
                                    "col_name": "mfh",
                                    "dom_query": ".zsg-list_square li:contains('Apartment'):first"
                                },
                                {
                                    "col_name": "pool",
                                    "dom_query": "li:contains('Pool'):first"
                                },
                                {
                                    "col_name": "manufactured",
                                    "dom_query": "li:contains('Manufactured'):first"
                                },
                                {
                                    "col_name": "hoa_fees",
                                    "dom_query": "li:contains('HOA Fee:'):first",
                                    "regex_pattern": "[0-9,]+"
                                },
                                {
                                    "col_name": "ajax_render",
                                    "dom_query": "script:contains('z-hdp-price-history')",
                                    "regex_pattern": "(AjaxRender[^\"]+rhost=1)\",jsModule:\"z-hdp-price-history",
                                    "regex_group": 1,
                                    "options": {
                                        "method": "post",
                                        "set_post_cookies": true,
                                        "post_data": {
                                            "origin_url": "http://www.zillow.com/@@ajax_render@@",
                                            "method": "get",
                                            "attribute": "html"
                                        },
                                        "origin_url": "http://localhost:9807/json_attribute_raw",
                                        "columns": [
                                            {
                                                "col_name": "event_date",
                                                "dom_query": "tbody tr td:nth-child(1)"
                                            },
                                            {
                                                "col_name": "event_name",
                                                "dom_query": "tbody tr td:nth-child(2)"
                                            },
                                            {
                                                "col_name": "event_price",
                                                "dom_query": "tbody tr td:nth-child(3)"
                                            }
                                        ]
                                    }
                                }
                            ]
                        }
                    }
                ]
            }
        }
    ],
    "cookies": [
        {
            "domain": ".getdata.io",
            "expirationDate": 1510725089,
            "hostOnly": false,
            "httpOnly": false,
            "name": "__utma",
            "path": "/",
            "secure": false,
            "session": false,
            "storeId": "0",
            "value": "55957693.119617150.1438097241.1447550662.1447652610.99",
            "id": 1
        },
        {
            "domain": ".getdata.io",
            "expirationDate": 1447654889,
            "hostOnly": false,
            "httpOnly": false,
            "name": "__utmb",
            "path": "/",
            "secure": false,
            "session": false,
            "storeId": "0",
            "value": "55957693.9.10.1447652610",
            "id": 2
        },
        {
            "domain": ".getdata.io",
            "hostOnly": false,
            "httpOnly": false,
            "name": "__utmc",
            "path": "/",
            "secure": false,
            "session": true,
            "storeId": "0",
            "value": "55957693",
            "id": 3
        },
        {
            "domain": ".getdata.io",
            "expirationDate": 1447653209,
            "hostOnly": false,
            "httpOnly": false,
            "name": "__utmt",
            "path": "/",
            "secure": false,
            "session": false,
            "storeId": "0",
            "value": "1",
            "id": 4
        },
        {
            "domain": ".getdata.io",
            "expirationDate": 1463421089,
            "hostOnly": false,
            "httpOnly": false,
            "name": "__utmz",
            "path": "/",
            "secure": false,
            "session": false,
            "storeId": "0",
            "value": "55957693.1447532605.96.15.utmcsr=api.getdata.io|utmccn=(referral)|utmcmd=referral|utmcct=/",
            "id": 5
        },
        {
            "domain": ".getdata.io",
            "expirationDate": 1465553362,
            "hostOnly": false,
            "httpOnly": false,
            "name": "mp_4b366188fc149ce99e5011bda07fa12c_mixpanel",
            "path": "/",
            "secure": false,
            "session": false,
            "storeId": "0",
            "value": "%7B%22distinct_id%22%3A%20%22a4ca8c520d82d44846159b04f86dd066%22%2C%22%24initial_referrer%22%3A%20%22%24direct%22%2C%22%24initial_referring_domain%22%3A%20%22%24direct%22%7D",
            "id": 6
        },
        {
            "domain": ".getdata.io",
            "expirationDate": 1479189089,
            "hostOnly": false,
            "httpOnly": false,
            "name": "mp_6739c9644606bc42c8ac134c22e1d691_mixpanel",
            "path": "/",
            "secure": false,
            "session": false,
            "storeId": "0",
            "value": "%7B%22distinct_id%22%3A%20%22a4ca8c520d82d44846159b04f86dd066%22%2C%22%24initial_referrer%22%3A%20%22%24direct%22%2C%22%24initial_referring_domain%22%3A%20%22%24direct%22%2C%22%24search_engine%22%3A%20%22google%22%7D",
            "id": 7
        },
        {
            "domain": "getdata.io",
            "hostOnly": true,
            "httpOnly": true,
            "name": "_mbd_dev_session",
            "path": "/",
            "secure": false,
            "session": true,
            "storeId": "0",
            "value": "BAh7CEkiD3Nlc3Npb25faWQGOgZFVEkiJWQwN2FmNDkzOTNkMzVjNmMwYjlhZmQxZmZmMDhlN2I0BjsAVEkiG3dhcmRlbi51c2VyLm1lbWJlci5rZXkGOwBUWwdbBmkQSSIiJDJhJDEwJGZuM1A3WG5EeU55T2JDUlZEUU1kUU8GOwBUSSIQX2NzcmZfdG9rZW4GOwBGSSIxTFJ0bWVnS1pOZUdpUzEvTjFiUkZWN1JaWHJaYzU0d0x5cUdHbG93S29rYz0GOwBG--93c06bbb0df7e116ab8483bcad77b3d0c2c0cc70",
            "id": 8
        },
        {
            "domain": "getdata.io",
            "expirationDate": 1475909155,
            "hostOnly": true,
            "httpOnly": false,
            "name": "closed_ins",
            "path": "/",
            "secure": false,
            "session": false,
            "storeId": "0",
            "value": "1",
            "id": 9
        },
        {
            "domain": "getdata.io",
            "expirationDate": 1469895337,
            "hostOnly": true,
            "httpOnly": false,
            "name": "closed_ins",
            "path": "/krakes",
            "secure": false,
            "session": false,
            "storeId": "0",
            "value": "1",
            "id": 10
        },
        {
            "domain": "getdata.io",
            "expirationDate": 1460784277.365656,
            "hostOnly": true,
            "httpOnly": false,
            "name": "muuid",
            "path": "/",
            "secure": false,
            "session": false,
            "storeId": "0",
            "value": "a4ca8c520d82d44846159b04f86dd066",
            "id": 11
        }
    ]
}