Clean up botched WARC imports from 2025-02-01 to 2025-02-04

[Mr0grog]

An early version of the WARC import script did a poor job handling revisits and wound up recording some redirects as the final response instead of following through to the actual final response and recording that. This has since been fixed in the import script, but it looks like we have some versions that need remediation from crawls on 2025-02-01 and 2025-02-04.

A good example is the left-hand side of this comparison: https://monitoring.envirodatagov.org/page/8b6cbc6d-ee2b-45af-8f8c-c005d997e800/f731df95-f9f5-44ce-9b24-a43a53166634..daf1d7c7-7739-491c-b346-b67de202af20

See the API for this version: https://api.monitoring.envirodatagov.org/api/v0/versions/f731df95-f9f5-44ce-9b24-a43a53166634

{
    "links": {
        "page": "https://api.monitoring.envirodatagov.org/api/v0/pages/8b6cbc6d-ee2b-45af-8f8c-c005d997e800",
        "previous": "https://api.monitoring.envirodatagov.org/api/v0/versions/1592d114-2588-41cf-a90d-91c497990409",
        "next": "https://api.monitoring.envirodatagov.org/api/v0/versions/e6703420-0776-4eb0-8efa-461a39f2a545"
    },
    "data": {
        "uuid": "f731df95-f9f5-44ce-9b24-a43a53166634",
        "page_uuid": "8b6cbc6d-ee2b-45af-8f8c-c005d997e800",
        "capture_time": "2025-02-02T07:57:47.456Z",
        "body_url": "https://edgi-wm-archive.s3.amazonaws.com/e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
        "body_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
        "source_type": "edgi_crawl_v0",
        "source_metadata": {
            "warc_name": "rec-8dfe9ae16db6-20250202010120189-0.warc.gz",
            "user_agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.1.73.104 Safari/537.36",
            "warc_page_id": "bbe297af-cd28-4dfd-b4ac-f6d8cdb01a09",
            "warc_record_ids": [
                "<urn:uuid:43a510da-54ef-43d5-9740-541250a4199d>",
                "<urn:uuid:47bab6e8-c1da-46de-910f-87df746f8885>"
            ],
            "warc_record_meta": {
                "cert": {
                    "ctc": "1",
                    "issuer": "GeoTrust RSA CA 2018"
                },
                "ipType": "Public"
            }
        },
        "created_at": "2025-02-04T08:58:11.544Z",
        "updated_at": "2025-02-04T08:58:11.544Z",
        "title": "",
        "url": "https://www.transportation.gov/careers/dot-deia-strategic-plan",
        "different": true,
        "status": 301,  // <------------------------------------------------ BAD!
        "content_length": 0,
        "media_type": "text/html",
        "headers": {
            "date": "Sun, 02 Feb 2025 07:57:47 GMT",
            "etag": "\"1738483067\"",
            "x-age": "0",
            "server": "nginx",
            "expires": "Sun, 02 Feb 2025 08:57:47 GMT",
            "location": "https://www.transportation.gov/",
            "x-generator": "Drupal 10 (https://www.drupal.org)",
            "content-type": "text/html; charset=utf-8",
            "x-request-id": "v-646efb1e-e13b-11ef-8a0d-7b5e4a4e7615",
            "cache-control": "public, max-age=3600",
            "last-modified": "Sun, 02 Feb 2025 07:57:47 GMT",
            "x-redirect-id": "155591",
            "content-length": "370",
            "x-frame-options": "SAMEORIGIN",
            "content-language": "en",
            "x-ah-environment": "prod",
            "x-content-type-options": "nosniff",
            "strict-transport-security": "max-age=31536000 ; includeSubDomains ; preload"
        },
        "network_error": null
    }
}