Last active
December 23, 2015 02:59
-
-
Save gornostal/6570516 to your computer and use it in GitHub Desktop.
Scrape audible search results
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
/** | |
* To run use http://nrabinowitz.github.com/pjscrape/ | |
* 1. $ phantomjs pjscrape.js audible.js | |
* 2. Register on mongolab.com | |
* 3. $ mongoimport -h ds0466148.mongolab.com:45598 -d <dbname> -c <collection> -u <user> -p <password> --file audible.json --jsonArray | |
* 4. Install greasemonkey (Firefox) or tempermonkey (Chrome) | |
* 5. Add this userscript https://gist.github.com/gornostal/6570526 | |
* 6. Open https://mongolab.com/databases/audible/collections/fiction_books or whatever you have | |
*/ | |
pjs.config({ | |
log: 'stdout', | |
format: 'json', | |
writer: 'file', | |
outFile: 'audible.json' | |
}); | |
pjs.addSuite({ | |
url: 'http://www.audible.com/search/ref=sr_pg__1?field_subjectbin=2226688011&searchSize=50', | |
moreUrls: '.adbl-page-next a:first:contains("Next")', | |
maxDepth: 30, | |
scraper: function() { | |
return $('li.adbl-result-item').map(function() { | |
var link = $('.adbl-prod-title a:first', this), | |
name = link.text(), | |
url = _pjs.toFullUrl(link.attr('href')), | |
image = $('a img.adbl-prod-image', this), | |
imageUrl = _pjs.toFullUrl(image.attr('src')), | |
author = $('.adbl-prod-author a:first', this).text(), | |
releaseDate = $('.adbl-label:contains("Release Date")', this).next().text(), | |
ratingEl = $('.boldrating', this), | |
rating = parseFloat(ratingEl.text().trim()), | |
ratingsMatch = ratingEl.parent().text().match(/\((\d+) ratings\)/); | |
ratings = parseInt((ratingsMatch && ratingsMatch[1]) || 0, 10); | |
return { | |
name: name, | |
link: url, | |
image: imageUrl, | |
releaseDate: releaseDate, | |
author: author, | |
rating: rating, | |
ratings: ratings | |
}; | |
}).toArray(); | |
} | |
}); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment