Last active
December 12, 2015 00:18
-
-
Save bmpvieira/4683065 to your computer and use it in GitHub Desktop.
This script fetches all the sequences links from a MycorWeb Blast result.
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
| # getMycorLinks.coffee | |
| # This script fetches all the sequences links from a MycorWeb Blast result. | |
| # | |
| # sequences can be fetched from these links with getMycorSequences.coffee: | |
| # https://gist.github.com/4683075 | |
| # results can be splitted into multiple files to run multiple instances of | |
| # getMycorSequences.coffee | |
| # | |
| # Dependencies: casperjs | |
| # Usage: casperjs getMycorLinks.coffee numberOutputFiles URL | |
| # Example: casperjs getMycorLinks.coffee 2 'http://mycor.nancy.inra.fr/IMGC/TuberGenome/database.php?table=gene_seq&start=0&search=&order=Name' | |
| # Author: Bruno Vieira (mail@bmpvieira.com) | |
| # License: MIT | |
| fs = require 'fs' | |
| casper = require('casper').create() | |
| numOutputFiles = casper.cli.args[0] | |
| parsedUrl = casper.cli.args[1].split('/database') | |
| rootUrl = parsedUrl[0] | |
| firstPage = "/database#{parsedUrl[1]}" | |
| getLinks = -> | |
| links = document.querySelectorAll "td>a" | |
| Array::map.call links, (e) -> e.getAttribute "href" | |
| sequencesLinks = [] | |
| pages = [] | |
| casper.start "#{rootUrl}/#{firstPage}", -> | |
| firstPageLinks = @evaluate getLinks | |
| for link in firstPageLinks | |
| pages.push link if link.match 'database' | |
| pageSequencesLinks = firstPageLinks.slice(pages.length) | |
| sequencesLinks = sequencesLinks.concat pageSequencesLinks | |
| for page in pages | |
| @thenOpen "#{rootUrl}/#{page}", => | |
| pageSequencesLinks = @evaluate(getLinks).slice(pages.length) | |
| sequencesLinks = sequencesLinks.concat pageSequencesLinks | |
| casper.then -> | |
| numSequencesPerFile = Math.floor(sequencesLinks.length / numOutputFiles) | |
| for start in [0..sequencesLinks.length] by numSequencesPerFile | |
| end = start + numSequencesPerFile | |
| if end > sequencesLinks.length | |
| end = sequencesLinks.length | |
| filename = "sequencesLinks:#{start}-#{end}.txt" | |
| for sequenceLink in sequencesLinks.slice start, end | |
| fs.write filename, "#{rootUrl}/#{sequenceLink}\n", 'a' | |
| casper.run() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment