Teknium
c49fa88b80
* refactor(skills): shipped-set slim — 15 skills to optional, github six-way merge, pdf absorbs OCR+nano-pdf, channel-gated teams pipeline
Maintainer-directed shipped-skills curation (skills index 1,900 -> ~1,400
tok/call on desktop; every session pays the index, so this is a per-call
diet on all installs):
- optional-skills moves (installable via skills hub, history preserved):
creative comfyui/ascii-art/excalidraw/pretext/sketch/touchdesigner-mcp;
ALL of mlops (huggingface-hub, llama-cpp, serving-llms-vllm,
weights-and-biases, evaluating-llms-harness — subcategory structure
kept); research-paper-writing (55 supporting files, 17.3K-tok load);
openhue; blogwatcher (first taught the cronjob monitor-field watch
pattern + web_extract instead of pre-cron manual workflows)
- DELETED session-librarian (Aug-12 'inspired by Perplexity Computer'
port, never maintainer-intended; session_search covers discovery)
- github: six skills (auth, issues, pr-workflow, issue-to-pr,
code-review, repo-management) merged into ONE software-development/
github skill — routing body + complete per-workflow references;
benbarclay authorship credited; codebase-inspection rides along;
discipline pins from test_github_issue_to_pr_skill.py preserved
against the reference body in the new test_github_skill.py
- pdf absorbs ocr-and-documents + nano-pdf as references/ + scripts
(extract_pymupdf, extract_marker converted to the argparse house
standard its contract test enforces)
- NEW session_platforms frontmatter gate (metadata.hermes): hides a
skill from the index on gateway channels it is not for; fail-open on
unknown platform; teams-meeting-pipeline gated to [teams, cron]
- blocked-page-recovery: research -> new web category; trigger-first
description ('Use when a fetch fails: 403/429, paywall, WAF, bot
wall.') so the model actually reaches for it on blocked fetches
- docs regenerated via generate-skill-docs.py (195 pages); related_skills
swept repo-wide; tests: 1672 passed (2 openclaw failures pre-existing
on clean main, Windows-local)
* chore: ignore .skills_prompt_snapshot.json (local index cache, accidentally committed)
102 lines
3.6 KiB
Python
102 lines
3.6 KiB
Python
#!/usr/bin/env python3
|
|
"""Extract text from documents using pymupdf. Lightweight (~25MB), no models.
|
|
|
|
Usage:
|
|
python extract_pymupdf.py document.pdf
|
|
python extract_pymupdf.py document.pdf --markdown
|
|
python extract_pymupdf.py document.pdf --pages 0-4
|
|
python extract_pymupdf.py document.pdf --images output_dir/
|
|
python extract_pymupdf.py document.pdf --tables
|
|
python extract_pymupdf.py document.pdf --metadata
|
|
"""
|
|
import sys
|
|
import json
|
|
|
|
def extract_text(path, pages=None):
|
|
import pymupdf
|
|
doc = pymupdf.open(path)
|
|
page_range = range(len(doc)) if pages is None else pages
|
|
for i in page_range:
|
|
if i < len(doc):
|
|
print(f"\n--- Page {i+1}/{len(doc)} ---\n")
|
|
print(doc[i].get_text())
|
|
|
|
def extract_markdown(path, pages=None):
|
|
import pymupdf4llm
|
|
md = pymupdf4llm.to_markdown(path, pages=pages)
|
|
print(md)
|
|
|
|
def extract_tables(path):
|
|
import pymupdf
|
|
doc = pymupdf.open(path)
|
|
for i, page in enumerate(doc):
|
|
tables = page.find_tables()
|
|
for j, table in enumerate(tables.tables):
|
|
print(f"\n--- Page {i+1}, Table {j+1} ---\n")
|
|
df = table.to_pandas()
|
|
print(df.to_markdown(index=False))
|
|
|
|
def extract_images(path, output_dir):
|
|
import pymupdf
|
|
from pathlib import Path
|
|
Path(output_dir).mkdir(parents=True, exist_ok=True)
|
|
doc = pymupdf.open(path)
|
|
count = 0
|
|
for i, page in enumerate(doc):
|
|
for img_idx, img in enumerate(page.get_images(full=True)):
|
|
xref = img[0]
|
|
pix = pymupdf.Pixmap(doc, xref)
|
|
if pix.n >= 5:
|
|
pix = pymupdf.Pixmap(pymupdf.csRGB, pix)
|
|
out_path = f"{output_dir}/page{i+1}_img{img_idx+1}.png"
|
|
pix.save(out_path)
|
|
count += 1
|
|
print(f"Extracted {count} images to {output_dir}/")
|
|
|
|
def show_metadata(path):
|
|
import pymupdf
|
|
doc = pymupdf.open(path)
|
|
print(json.dumps({
|
|
"pages": len(doc),
|
|
"title": doc.metadata.get("title", ""),
|
|
"author": doc.metadata.get("author", ""),
|
|
"subject": doc.metadata.get("subject", ""),
|
|
"creator": doc.metadata.get("creator", ""),
|
|
"producer": doc.metadata.get("producer", ""),
|
|
"format": doc.metadata.get("format", ""),
|
|
}, indent=2))
|
|
|
|
if __name__ == "__main__":
|
|
import argparse
|
|
|
|
parser = argparse.ArgumentParser(
|
|
description="Extract text/tables/images/metadata from documents using pymupdf (lightweight, no models)."
|
|
)
|
|
parser.add_argument("path", help="Document to read")
|
|
parser.add_argument("--pages", help="Page selection: N or START-END (0-indexed)")
|
|
parser.add_argument("--markdown", action="store_true", help="Markdown output via pymupdf4llm")
|
|
parser.add_argument("--tables", action="store_true", help="Extract tables as markdown")
|
|
parser.add_argument("--images", nargs="?", const="./images", metavar="OUTPUT_DIR",
|
|
help="Extract embedded images to OUTPUT_DIR (default ./images)")
|
|
parser.add_argument("--metadata", action="store_true", help="Show document metadata as JSON")
|
|
args = parser.parse_args()
|
|
|
|
pages = None
|
|
if args.pages:
|
|
if "-" in args.pages:
|
|
start, end = args.pages.split("-")
|
|
pages = list(range(int(start), int(end) + 1))
|
|
else:
|
|
pages = [int(args.pages)]
|
|
|
|
if args.metadata:
|
|
show_metadata(args.path)
|
|
elif args.tables:
|
|
extract_tables(args.path)
|
|
elif args.images is not None:
|
|
extract_images(args.path, args.images)
|
|
elif args.markdown:
|
|
extract_markdown(args.path, pages=pages)
|
|
else:
|
|
extract_text(args.path, pages=pages)
|