-def http_to_keep(api, project_uuid, url, utcnow=datetime.datetime.utcnow):
- r = api.collections().list(filters=[["properties", "exists", url]]).execute()
+
+def http_to_keep(api, project_uuid, url, utcnow=datetime.datetime.utcnow, varying_url_params=""):
+ varying_params = [s.strip() for s in varying_url_params.split(",")]
+
+ parsed = urllib.parse.urlparse(url)
+ query = [q for q in urllib.parse.parse_qsl(parsed.query)
+ if q[0] not in varying_params]
+ clean_url = urllib.parse.urlunparse((parsed.scheme, parsed.netloc, parsed.path, parsed.params,
+ urllib.parse.urlencode(query), parsed.fragment))
+
+ r = api.collections().list(filters=[["properties", "exists", clean_url]]).execute()