# Download ENA records so that we can discover newly uploaded data
# 2025-04-12
# Hui

import os
import sys
import time
import shutil
from configure import TEMP_DIR, UPDATE_NETWORK_LOG_FILE
from log import write_log_file
from configure import INFO_DIR

accession = 3702 # arabidopsis
types = ['read_run', 'read_experiment', 'sample', 'study']
for t in types:
    url = f'https://www.ebi.ac.uk/ena/browser/api/xml/links/taxon?accession={accession}&result={t}'
    print(url)
    if not os.path.exists(TEMP_DIR):
        sys.exit()
    cmd = 'wget "%s" -O %s' % (url, os.path.join(TEMP_DIR, 'ena_'+t+'.xml')) # save XML data to file
    os.system(cmd)
    time.sleep(5)

for t in types:
    fname = os.path.join(TEMP_DIR, 'ena_'+t+'.xml')
    if os.path.exists(fname):
        print(f'Move {fname} to {INFO_DIR}')
        shutil.move(fname, INFO_DIR)
    time.sleep(5)

write_log_file('[download_ena_records.py] ENA records updated. Check folder %s' % (INFO_DIR), UPDATE_NETWORK_LOG_FILE)

#https://www.ebi.ac.uk/ena/browser/api/xml/links/taxon?accession=3702&result=read_run
#https://www.ebi.ac.uk/ena/browser/api/xml/links/taxon?accession=3702&result=read_experiment
#https://www.ebi.ac.uk/ena/browser/api/xml/links/taxon?accession=3702&result=sample
#https://www.ebi.ac.uk/ena/browser/api/xml/links/taxon?accession=3702&result=study