From c31835f787f3ae36e26bad0a1803f8557f8084e7 Mon Sep 17 00:00:00 2001 From: Pjotr Prins Date: Wed, 6 Jan 2021 02:33:35 -0600 Subject: Pubseq fetch: sometimes a request times out. So repeat with intervals. --- workflows/tools/pubseq-fetch-data.py | 33 +++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 14 deletions(-) diff --git a/workflows/tools/pubseq-fetch-data.py b/workflows/tools/pubseq-fetch-data.py index 2119fdf..ef4edde 100755 --- a/workflows/tools/pubseq-fetch-data.py +++ b/workflows/tools/pubseq-fetch-data.py @@ -5,6 +5,7 @@ import json import os import requests import sys +import time parser = argparse.ArgumentParser(description=""" @@ -33,18 +34,22 @@ for id in ids: print(id) jsonfn = dir+"/"+id+".json" if not os.path.exists(jsonfn): + count = 0 r = requests.get(f"http://covid19.genenetwork.org/api/sample/{id}.json") - if r: - m_url = r.json()[0]['metadata'] - mr = requests.get(m_url) - with open(dir+"/"+id+".json","w") as outf: - outf.write(mr.text) - if args.fasta: - fastafn = dir+"/"+id+".fa" - if os.path.exists(fastafn): continue - fa_url = r.json()[0]['fasta'] - fr = requests.get(fa_url) - with open(fastafn,"w") as outf: - outf.write(fr.text) - else: - raise Exception(f"Can not find record for {id}") + while not r: + count += 1 + if count>10: raise Exception(f"Can not find record for {id}") + time.sleep(15) + r = requests.get(f"http://covid19.genenetwork.org/api/sample/{id}.json") + m_url = r.json()[0]['metadata'] + mr = requests.get(m_url) + with open(dir+"/"+id+".json","w") as outf: + outf.write(mr.text) + if args.fasta: + fastafn = dir+"/"+id+".fa" + if os.path.exists(fastafn): continue + fa_url = r.json()[0]['fasta'] + fr = requests.get(fa_url) + with open(fastafn,"w") as outf: + outf.write(fr.text) + -- cgit v1.2.3