diff options
| author | Bryan Newbold <bnewbold@robocracy.org> | 2021-11-09 14:17:31 -0800 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@robocracy.org> | 2021-11-09 14:17:35 -0800 |
| commit | 86e6850e70617e1609b79e0ee4bfe2a26f7f992e (patch) | |
| tree | deb5724e1c611e9b6aa0a020d5c0ead34e74853b /notes | |
| parent | ad050445ac4f3e218ec101790bbf187731646361 (diff) | |
| download | fatcat-86e6850e70617e1609b79e0ee4bfe2a26f7f992e.tar.gz fatcat-86e6850e70617e1609b79e0ee4bfe2a26f7f992e.zip | |
cleanups: tweaks to wayback CDX cleanup scripts
Diffstat (limited to 'notes')
| -rw-r--r-- | notes/cleanups/scripts/fetch_full_cdx_ts.py | 9 |
1 files changed, 8 insertions, 1 deletions
diff --git a/notes/cleanups/scripts/fetch_full_cdx_ts.py b/notes/cleanups/scripts/fetch_full_cdx_ts.py index 6c6817ab..6f67c7e1 100644 --- a/notes/cleanups/scripts/fetch_full_cdx_ts.py +++ b/notes/cleanups/scripts/fetch_full_cdx_ts.py @@ -157,7 +157,14 @@ def process_file(fe, session) -> dict: if short in full_urls: continue - cdx_record = get_api_cdx(original_url, partial_dt=ts, http_session=session) + cdx_record = None + try: + cdx_record = get_api_cdx(original_url, partial_dt=ts, http_session=session) + except requests.exceptions.HTTPError as e: + if e.response.status_code == 403: + return dict(file_entity=fe, full_urls=full_urls, status="fail-cdx-403") + else: + raise if cdx_record: if cdx_record['sha1hex'] == fe['sha1'] and cdx_record['url'] == original_url and cdx_record['datetime'].startswith(ts): assert len(cdx_record['datetime']) == 14 and cdx_record['datetime'].isdigit() |