From a70841cb971bf681ae1215ba4a6ed372833e0617 Mon Sep 17 00:00:00 2001
From: Benoit Favre <benoit.favre@lis-lab.fr>
Date: Fri, 12 Jun 2020 13:59:46 +0200
Subject: [PATCH] fix problems with pubmed servers disconnecting
---
bibliovid_add_abstract.py | 26 +++++++++++++++++---------
1 file changed, 17 insertions(+), 9 deletions(-)
diff --git a/bibliovid_add_abstract.py b/bibliovid_add_abstract.py
index df59b60..c418f23 100644
--- a/bibliovid_add_abstract.py
+++ b/bibliovid_add_abstract.py
@@ -5,6 +5,8 @@ import sys, json, re, collections
from pymed import PubMed
from datetime import datetime, date
+import requests
+import time
pubmed = PubMed(tool="https://covid19.lis-lab.fr", email="benoit.favre@univ-amu.fr")
@@ -32,16 +34,22 @@ for article in articles['results']:
found = False
for query in ['(%s[Title] AND (%s[Author])' % (preprocess(title), preprocess(authors)), '%s[Title]' % preprocess(title), preprocess(title)]:
- results = pubmed.query(query, max_results=30)
- for result in results:
- entry = result.toDict()
- if normalize(title) == normalize(entry['title']):
- found = True
- for field in ['pubmed_id', 'doi', 'abstract']:
- if field in entry:
- article[field] = entry[field]
- stats[field] += 1
+ for retries in range(10):
+ try:
+ results = pubmed.query(query, max_results=30)
+ for result in results:
+ entry = result.toDict()
+ if normalize(title) == normalize(entry['title']):
+ found = True
+ for field in ['pubmed_id', 'doi', 'abstract']:
+ if field in entry:
+ article[field] = entry[field]
+ stats[field] += 1
+ break
break
+ except requests.exceptions.HTTPError as e:
+ print(e, file=sys.stderr)
+ time.sleep(5)
if found:
break
if not found:
--
GitLab