10 Commits

Author	SHA1	Message	Date
eulaly	1ea696d818	added texts and fixes for mojibake	2026-05-07 17:22:16 -04:00
eulaly	28d6d222bd	added create_csv.py	2026-05-07 17:22:00 -04:00
eulaly	f5d679808e	completed openai batch work	2026-05-07 07:24:11 -04:00
eulaly	64a7a18721	openai batch refactor	2026-05-06 13:53:50 -04:00
eulaly	e1ad4432a7	refactor/batch-openai prep	2026-05-06 13:29:59 -04:00
eulaly	f3abbefac7	add gpt4o batch analysis	2026-05-05 16:50:10 -04:00
eulaly	683bfb324f	remove hyphen for underscore in nomenclature, remove dependency	2026-05-05 16:47:11 -04:00
eulaly	d834d18c81	added 4o initial manual analysis and test	2026-05-05 15:00:34 -04:00
eulaly	e7df0b24a1	1.1 cleanup	2026-05-05 13:50:04 -04:00
eulaly	beb5cf461b	t1.1: scrape one forum via ViewComments.cfm POST pagination ... Spider fetches ViewComments.cfm?GdocForumID=N with vPerPage=500, generates all page requests from page-1 metadata, and parses each div.Cbox for comment_id, author, date, title, text, reg_title, reg_desc. Handles span-wrapped comment text. Fixes UTF-8/windows-1251 meta-tag encoding mismatch. 9083 items, 15 empty-text (0.17%). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-05-05 12:28:07 -04:00