aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2020-05-21 19:51:23 -0700
committerBryan Newbold <bnewbold@archive.org>2020-05-21 19:51:23 -0700
commit55bb09006e984da217cbfdf4145aaad16b0b5cac (patch)
tree73084a62056ed25424585348dced6b52c74ec296
parent0063be61247aa4ea697568ce9741f6857b80d595 (diff)
downloadfatcat-scholar-55bb09006e984da217cbfdf4145aaad16b0b5cac.tar.gz
fatcat-scholar-55bb09006e984da217cbfdf4145aaad16b0b5cac.zip
helpers to fetch small-ish data samples
-rw-r--r--Makefile8
1 files changed, 8 insertions, 0 deletions
diff --git a/Makefile b/Makefile
index c269576..61e9a4b 100644
--- a/Makefile
+++ b/Makefile
@@ -21,6 +21,14 @@ dev: ## Run web service locally, with reloading
run: ## Run web service under gunicorn
pipenv run gunicorn fatcat_scholar.web:app -w 4 -k uvicorn.workers.UvicornWorker
+.PHONY: fetch-works
+fetch-works: ## Fetches some works from any release .json in the data dir
+ cat data/release_*.json | jq . -c | pipenv run python -m fatcat_scholar.work_pipeline run_releases | pv -l > data/work_intermediate.json
+
+.PHONY: fetch-sim
+fetch-sim: ## Fetches some SIM pages
+ pipenv run python -m fatcat_scholar.sim_pipeline run_issue_db --limit 500 | pv -l > data/sim_intermediate.json
+
.PHONY: dev-index
dev-index: ## Delete/Create DEV elasticsearch fulltext index locally
http delete ":9200/dev_scholar_fulltext_v01" && true