diff options
| -rw-r--r-- | fuzzycat/__main__.py | 2 | ||||
| -rw-r--r-- | fuzzycat/utils.py | 11 |
2 files changed, 7 insertions, 6 deletions
diff --git a/fuzzycat/__main__.py b/fuzzycat/__main__.py index 89e3a12..8ff20f5 100644 --- a/fuzzycat/__main__.py +++ b/fuzzycat/__main__.py @@ -26,7 +26,7 @@ import requests from fuzzycat.cluster import (Cluster, release_key_title, release_key_title_ngram, release_key_title_normalized, release_key_title_nysiis, release_key_title_sandcrawler) -from fuzzycat.utils import random_word +from fuzzycat.utils import random_idents_from_query, random_word from fuzzycat.verify import GroupVerifier, verify logging.getLogger("requests").setLevel(logging.WARNING) diff --git a/fuzzycat/utils.py b/fuzzycat/utils.py index cf74220..9aa3a4c 100644 --- a/fuzzycat/utils.py +++ b/fuzzycat/utils.py @@ -6,6 +6,7 @@ import random import re import string +import requests from glom import PathAccessError, glom printable_no_punct = string.digits + string.ascii_letters + string.whitespace @@ -164,11 +165,11 @@ def random_idents_from_query(query="*", Return a number of random idents from a search query. """ for _ in range(max_retries): - r = requests.get(es, params={"q": query}) - if r.status_code != 200: + resp = requests.get(es, params={"q": query}) + if resp.status_code != 200: raise RuntimeError('could not query {} for random item: {}'.format(es, r.url)) - resp = r.json() - if resp["hits"]["total"] < 2: + payload = resp.json() + if payload["hits"]["total"] < 2: continue - idents = [doc["_source"]["ident"] for doc in resp["hits"]["hits"]] + idents = [doc["_source"]["ident"] for doc in payload["hits"]["hits"]] return random.sample(idents, r) |