feat(scrape): vision OCR of image-only doc pages (support matrices) (#5)

Co-authored-by: claude <[email protected]>
This commit was merged in pull request #5.
This commit is contained in:
2026-07-23 09:48:38 -04:00
committed by claude
parent caf562b7c3
commit 698196bd63
10 changed files with 407 additions and 6 deletions
+7
View File
@@ -95,6 +95,13 @@ BUNDLES: list[BundleSpec] = [
BundleSpec("morpheus_quickspecs", "a50009231enw", "HPE Morpheus Enterprise Software QuickSpecs",
"v1", "QuickSpecs", "html-file",
source_url="https://www.hpe.com/psnow/doc/a50009231enw"),
# Release schedule / support-lifecycle matrix. This `sf` solution article
# is a single page whose table (which version ships when; when a stream
# hits Maintenance/EOL) lives ENTIRELY inside a JPEG. Scraped as `single`;
# the matrix text comes from the VISION_OCR pass (see scrape/vision.py).
# version=None — it spans all major streams, not one release.
BundleSpec("morpheus_release_schedule", "sf000111242en_us", "HPE Morpheus Software Release Schedule",
None, "Release Schedule", "single"),
]