added a simple caching of the requests to make it

much quicker to fail and restart
This commit is contained in:
Karma Riuk
2025-04-01 10:14:45 +02:00
parent a24ffa00fc
commit a362aba344
2 changed files with 13 additions and 1 deletions

1
optional-requirments.txt Normal file
View File

@ -0,0 +1 @@
requests_cache

View File

@ -9,7 +9,7 @@ import pandas as pd
from github import Github, GithubException from github import Github, GithubException
from pandas.io.common import tarfile from pandas.io.common import tarfile
from tqdm import tqdm from tqdm import tqdm
from datetime import datetime from datetime import datetime, timedelta
from dataset import ( from dataset import (
Comment, Comment,
@ -474,8 +474,19 @@ if __name__ == "__main__":
type=str, type=str,
help="Run the script on a single repo (format: 'owner/name'). If not set, all repos in '--repos' CSV are processed.", help="Run the script on a single repo (format: 'owner/name'). If not set, all repos in '--repos' CSV are processed.",
) )
parser.add_argument(
"--cache-requests",
action="store_true",
help="Cache GitHub API requests in a SQLite file using 'requests_cache' (in optional-requirements.txt). Speeds up reruns but may serve stale data.",
)
args = parser.parse_args() args = parser.parse_args()
if args.cache_requests:
import requests_cache
requests_cache.install_cache('github_cache', expire_after=timedelta(weeks=2))
g = Github(os.environ["GITHUB_AUTH_TOKEN_CRAB"]) g = Github(os.environ["GITHUB_AUTH_TOKEN_CRAB"])
docker_client = docker.from_env() docker_client = docker.from_env()
move_github_logging_to_file() move_github_logging_to_file()