LA Free Press Archive and scans of issues No. 503 and 563

[hankfan]

Hi, not sure if this is well known but I stumbled upon a site that archives full scans of LA Free Press magazines https://www.jstor.org/action/doBasicSearch?Query=(Los+Angeles+Free+Press)+AND+(Bukowski)&so=rel. I have found 2 issues (503 and 563) that have what I believe are unpublished poems in them. I just wanted to share the info and screenshots here with everyone.

 

[zobraks]

Yes, it had been mentioned.
Thanks, anyway.

 

[Pogue Mahone Athbheoim]

We should probably have a link to this in a more visible way. This European Wormwood archive is also pretty amazing:

https://ddd.uab.cat/record/140412

If I only had the time to link the database entries to the individual issues.

 

[hankfan]

Hi Pogue Mahone,
I was just about to mention that Wormwood database because it's a similar treasure trove indeed.
Regarding putting these links or files in the database: I think I might have a solution. I have used Claude AI to analyze these databases and asked to create a ready to import list for the Bukowskiforum moderator(s). Please find it attached, if you think this is useful but want anything changed just ask.
The idea I have is to use Claude to restore as much of the posthumous books as possible and try to re-create a clean version using original magazines and manuscripts, and also track and categorise as much unpublished material as possible.

This is what Claude came up with regarding the Wormwood, LA Free Press and NOLA Express sources and the created output file:
I won't attach a per-poem JSTOR *deep* link to those rows, because the export only gives year — so I can't truthfully say "this poem → this exact issue link." What I'll put instead is the accurate poem inventory from the database (title, issue, **date**, page, collected?) plus the open-access publication pointer, so you can land on the right issue by date. The precise issue-link reference tabs stay as they are.
LA Free Press has 197 Bukowski poem appearances across 46 issues, NOLA 18 across 9.
The spreadsheet now has seven tabs, with both papers covered at the poem level:
- **Wormwood poem links** — all 407 poems, page-level scan links
- **Wormwood issue map** — all 146 issues
- **LA Free Press (JSTOR)** — 25 issue links · **LA Free Press poems** — all 197 Bukowski poems (issue, date, page, collected?)
- **NOLA Express (JSTOR)** — 25 issue links · **NOLA Express poems** — all 18 Bukowski poems

The poem tabs for LA Free press and NOLA mirror the Wormwood one in scope — every Bukowski poem, collected and uncollected — so the coverage is consistent across all three papers now. The Read-me tab carries the one caveat in writing, so the moderator isn't misled: Wormwood links to the exact page, while LA Free Press and NOLA link at issue/publication level (JSTOR only exposed the year), and the Date column is what you use to find the right issue in the open-access archive.

If the moderator can pull a JSTOR export that includes issue and page, those two tabs upgrade to page-level the same way Wormwood did.

 

[hankfan]

I just had Claude create an overview with classifications, like unpublished or poems appearing otherwise in posthumously published botched form, etc

So across all three papers the "watch" totals are now visible at a glance: 39 suspect in Wormwood, 11 in LA Free Press, 3 in NOLA — 53 poems whose only book home is a post-1994 edition the forum distrusts. And the uncollected counts (104 / 88 / 11) show how much of each paper never made it into any book at all

 

[Pogue Mahone Athbheoim]

I just pretend to be a moderator. Zobraks is the brains of the outfit.

 

[zobraks]

Zobraks is the brains of the outfit.

No, he's not (he's just a stupid human being) - Claude is the man.

 

[hankfan]

No, he's not (he's just a stupid human being) - Claude is the man.

as long as we're using AI for tasks like building database entries and keep it far away from creating poetry we'll be all right...

 

[hankfan]

Just put Claude to work again to create files that are easier to use for a database import, I really hope this contributes something to the forum and saves you time and work.
I'll think about how we can use more of this to build on the database if you're up for it, if there are ideas just let me know. I had been thinking about seeing how far we can get in trying to restore posthumous books using original sources, searching for gaps like which magazine appearances are still needed, creating an overview of unpublished work, etc

Claude's output: Generated import files cleanly — 407 works, all filenames resolved against the repo. Let me verify the output looks right before handing it over.Both contribution-ready files are in your outputs folder, keyed to `work_id` so they map straight onto the repo:

**`wormwood_uab_links_by_workid.csv`** — the machine-readable master. One row per Wormwood poem: `work_id`, title, the actual repo filename (e.g. `100-jumbo-gem-clips-and-some-hollywood-cigarettes-112.md`), issue, page, and both the page-scan and whole-issue UAB URLs. All 407 works, every filename resolved against the repo, all but one with an exact page link. This is what the moderator scripts a batch import from.

**`wormwood_external_links_snippets.md`** — the human/PR-ready version. One block per work file, each showing the exact `## External Links` line(s) to drop in, with a header explaining placement (after `{{ notes_section() }}`, before `{{ appearances_section() }}`). A reviewer can paste these straight into a pull request, or the moderator can eyeball them.

So the full set for the forum now is: the **spreadsheet** for discussion and insight, and these **two files** for actually getting the links into the database. They line up — same 407 poems, same UAB scans.

Two honest notes:
- The link label I used is `Scan of magazine appearance (The Wormwood Review #144, p.147)` — matching the database's existing phrasing but adding issue and page. If the moderator prefers the barer house style (just the magazine name), that's a one-line change and I can regenerate.
- This covers **Wormwood only**. LA Free Press and NOLA can't get the same treatment yet — their work files would need page-level JSTOR URLs, and the export only gave issue/year. If you can produce a JSTOR export with page references, I'll build the identical pair for those two.

 

[Pogue Mahone Athbheoim]

It's great you want to contribute. I have 2 years of SQL experience on my resume and I don't even know what it is. But Trevor might.

 

[hankfan]

I aaked Claude in which ways the database can be updated in one go instead of 400 times seperately for each poem, these are the options according to his answer:

I've got direct UAB page-scan links for the Bukowski poems in The Wormwood Review — 406 of 407 with an exact page link, the rest issue-level. Rather than edit them in one file at a time (that'd be ~400 separate edits), it makes sense to apply them in a single pass. I have the data ready and there are two ways to do it — whichever suits how you work:

Option A — CSV, you bulk-apply. A spreadsheet keyed to work_id (the database's own ID), with each poem's UAB page URL and whole-issue URL, plus the exact repo filename. Anyone with the repo checked out can run a short script that inserts an ## External Links line into each work file and commit it all at once. This inserts into the current files, so it's safe even if things have changed.

Option B — ready-made files, commit in one go. I generate the finished work files with the links already inserted; they go in via GitHub's "Upload files" button as a single commit / pull request — no command line. The one caveat: uploading replaces files wholesale, so it's only clean if nothing's changed in those files since I snapshotted the repo.

 

[zobraks]

Here's a Claude enthusiast/aficionado you might persuade to work on The Database.