Created
March 29, 2019 02:17
-
-
Save bioinformatist/18a804056cb7108d7cce7a54c9934350 to your computer and use it in GitHub Desktop.
Get latest complete genome URLs from IMG XML file
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
| #!/usr/bin/env python | |
| from datetime import datetime | |
| import argparse | |
| import xml.etree.ElementTree as ET | |
| parser = argparse.ArgumentParser('Get latest complete genome URLs from IMG XML file') | |
| parser.add_argument("file", help = 'A XML file downloaded from IMG') | |
| args = parser.parse_args() | |
| name_time_url = {} | |
| def latest_complete(file): | |
| tree = ET.parse(file) | |
| root = tree.getroot() | |
| for child in root.iter('file'): | |
| filename = child.get('filename') | |
| if 'assembly.fasta' in filename or 'assembled.fna' in filename: | |
| label = child.get('label') | |
| timestamp = child.get('timestamp').replace('PDT ', "").replace('PST', '') | |
| dt = datetime.strptime(timestamp, "%c") | |
| name_time_url.setdefault(label, {}) | |
| name_time_url[label][dt] = child.get('url') | |
| for name in name_time_url: | |
| latest = max(name_time_url[name].keys()) | |
| print("https://genome.jgi.doe.gov{}".format(name_time_url[name][latest])) | |
| if __name__ == "__main__": | |
| latest_complete(args.file) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment