Created
September 3, 2019 12:54
-
-
Save meelash/b65c12777c8abcfa71866c3d41be73dd to your computer and use it in GitHub Desktop.
This file contains 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
const Apify = require('apify'); | |
(async () => { | |
const rootAddress = new URL('https://stores.cosmoprofbeauty.com'); | |
const requestQueue = await Apify.openRequestQueue(); | |
await requestQueue.addRequest({ | |
url: rootAddress.href, | |
userData: {requestType:'listPage'} | |
}) | |
const enqueueListItems = ($, requestType) =>{ | |
return Promise.all(Array.prototype.map.call($('.mapListItemWrap a').get(), elem => { | |
return requestQueue.addRequest({ | |
url: (new URL($(elem).attr('href'), rootAddress)).href, | |
userData: {requestType} | |
}); | |
})); | |
} | |
const crawler = new Apify.CheerioCrawler({ | |
requestQueue, | |
handlePageFunction: async ({ request, response, html, $ }) => { | |
switch (request.userData.requestType) { | |
case 'listPage': | |
return await enqueueListItems($, 'statePage'); | |
case 'statePage': | |
return await enqueueListItems($, 'cityPage'); | |
case 'cityPage': | |
// console.log(`Pre-promise visited page: ${request.url} ${request.retryCount} times, because ${request.errorMessages}`); | |
return Promise.all(Array.prototype.map.call($('.rio-list-links a').first().get(), elem => { | |
// console.log(`visited page: ${request.url} ${request.retryCount} times, because ${request.errorMessages}`); | |
// console.log(`Request with id: ${(new URL($(elem).attr('href'), rootAddress)).href} added`); | |
return requestQueue.addRequest({ | |
url: (new URL($(elem).attr('href'), rootAddress)).href, | |
userData: {requestType: 'detailsPage'} | |
}).then(({wasAlreadyPresent, request}) => { | |
if (wasAlreadyPresent) { | |
// console.log(`The request with id: ${request.url} was already present`); | |
} | |
}); | |
})); | |
case 'detailsPage': | |
const poi = { | |
store_number: $('#rio-store-id').text(), | |
debug: { url: request.url, id: request.id, uniqueKey: request.uniqueKey, all: JSON.stringify(request)}, | |
}; | |
await Apify.pushData([poi]); | |
break | |
default: | |
throw 'ERROR: Unhandled Page!' | |
break; | |
} | |
}, | |
}); | |
await crawler.run(); | |
})(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment