Skip to content

Instantly share code, notes, and snippets.

@bioinformatist

bioinformatist/getLatestCompleteIMG.py

Created March 29, 2019 02:17
Show Gist options
  • Save bioinformatist/18a804056cb7108d7cce7a54c9934350 to your computer and use it in GitHub Desktop.
Save bioinformatist/18a804056cb7108d7cce7a54c9934350 to your computer and use it in GitHub Desktop.
Download ZIP

Revisions

  1. Yu Sun created this gist Mar 29, 2019.
    30 changes: 30 additions & 0 deletions getLatestCompleteIMG.py
    View file
    Original file line number Diff line number Diff line change
    @@ -0,0 +1,30 @@
    #!/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)