Last active
December 21, 2015 07:28
-
-
Save alanshaw/6270911 to your computer and use it in GitHub Desktop.
Scrape polestarglobal.com [where to buy page](http://web.polestarglobal.com/about/where-to-buy) for import into django
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
var Browser = require("zombie") | |
, defaults = require("defaults") | |
var regionMap = { | |
"Africa": 1, | |
"Asia/Pacific": 2, | |
"Europe": 3, | |
"Middle East": 4, | |
"North America": 5, | |
"South America": 6 | |
} | |
var prodMap = { | |
"Fleet Management": "fleet_management", | |
"Marine Asset Tracker": "marine_asset_tracker", | |
"Ship Security (SSAS & SSRS)": "ship_security", | |
"LRIT Conformance": "lrit_conformance", | |
"Fisheries Vessel Monitoring": "fisheries_vessel_monitoring", | |
"Approved Service Centres": "approved_service_centre" | |
} | |
var defaultDist = { | |
"fleet_management": false, | |
"marine_asset_tracker": false, | |
"ship_security": false, | |
"lrit_conformance": false, | |
"fisheries_vessel_monitoring": false, | |
"approved_service_centre": false | |
} | |
var browser = new Browser() | |
browser.visit("http://web.polestarglobal.com/about/where-to-buy", {debug: true}, function (er) { | |
if (er) return console.error(er) | |
var distributors = [] | |
, pk = 0 | |
var distItems = browser.queryAll("#retailers > li") | |
console.log("Found", distItems.length, "distributors") | |
distItems.forEach(function (dist) { | |
var fields = defaults({}, defaultDist) | |
fields.name = browser.text(".org", dist) | |
fields.country = browser.text(".country-name", dist) | |
fields.region = regionMap[dist.getAttribute("data-region")] | |
dist.getAttribute("data-products").split(",").forEach(function (prod) { | |
fields[prodMap[prod]] = true | |
}) | |
fields.rep = browser.text(".fn", dist) || null | |
fields.street = browser.html(".street-address > *", dist) || null | |
if (fields.street) { | |
fields.street = fields.street | |
.replace(/<div>/g, "") | |
.replace(/<\/div>/g, "\n") | |
.replace(/\\t/g, "") | |
.trim() | |
} | |
fields.city = browser.text(".locality", dist) || null | |
fields.county = browser.text(".region", dist) || null | |
fields.postcode = browser.text(".postal-code", dist) || null | |
var tels = browser.queryAll(".tel", dist) | |
if (tels[0]) { | |
fields.tel = browser.text(tels[0]) || null | |
} else { | |
fields.tel = null | |
} | |
if (tels[1]) { | |
fields.fax = browser.text(tels[1]) || null | |
} else { | |
fields.fax = null | |
} | |
fields.email = browser.text(".email", dist) || null | |
fields.website = browser.text(".url", dist) || null | |
var map = browser.query("img", dist) | |
if (map) { | |
var matches = (/color:red%7C([0-9-.]+),([0-9-.]+)&/g).exec(map.src) | |
if (matches) { | |
fields.latitude = matches[1] | |
fields.longitude = matches[2] | |
} | |
} | |
distributors.push({ | |
pk: ++pk, | |
model: "content.distributor", | |
fields: fields | |
}) | |
}) | |
console.log(JSON.stringify(distributors, null, 2)) | |
}) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment