把中文 PDF 课件提炼为结构化 Markdown 学习笔记的 Agent Skill，含零截断图例裁剪脚本（pdfplumber + pypdfium2 + Pillow）
-
Updated
Sep 20, 2026 - Python
#
pypdfium2
Here are 13 public repositories matching this topic...
python ocr ai vision structured-output multimodal document-extraction pydantic fastapi tool-use document-ai pypdfium2
-
Updated
May 19, 2026 - Python
High-fidelity PDF to DOCX with editable layout, Google Docs support, and render-back verification.
python pdf document-conversion docx google-docs ooxml layout-analysis pdfium pdf-to-word pypdfium2 pdf-to-docx
-
Updated
Sep 11, 2026 - Python
PDF tables, word boxes, form fields & page render for DuckDB (Python, pdfplumber)
python pdf sql vgi table-extraction document-processing apache-arrow pdf-tables pdfplumber duckdb document-parsing duckdb-extension pypdfium2 query-farm
-
Updated
Aug 28, 2026 - Python
Preflight checks for document extraction pipelines — validate, render, and screen PDFs before they reach your LLM. Pure-Python wheel, in-memory only.
python pdf python-library pdf-to-image pdf-processing invoice-processing document-ai ocr-preprocessing pypdfium2 llm-preprocessing blank-detection
-
Updated
Apr 13, 2026 - Python
Mi herramienta de escritorio para comprimir archivos PDF
-
Updated
Jun 15, 2026 - Python
Preprocessing pipeline for Colombian legal documents that cleans and structures PDF/HTML content for RAG systems, preserving legal formatting while removing UI noise and metadata.
-
Updated
Mar 22, 2026 - Python
Turn invoices, receipts and scanned documents into a balanced, audit-ready ledger — automatically.
async jinja2 pytest ruff pytesseract uvicorn structlog instructor pdfplumber fastapi-docker pydantic-v2 pypdfium2
-
Updated
Sep 23, 2026 - Python
PDF layout-surgery engine on a fully permissive stack - read, erase, and redraw text and vector art by coordinate.
-
Updated
Sep 27, 2026 - Python
A Python tool for extracting highlighted text from PDF files while preserving formatting attributes (headers, bold, italic) and removing unwanted line breaks and page breaks. Perfect for integrating with content management systems.
pdf opencv automation numpy documentation-tool crm pillow python3 scrapping pymupdf pdf-document-processor pypdfium2
-
Updated
May 15, 2025 - Python
20 PDF classifiers, one verdict matrix: should this PDF go through fast text extraction, or do we need OCR?
python pdf benchmark ocr text-extraction evaluation-framework pdfminer claude pikepdf pypdfium2 ai-collaboration pdf-classification
-
Updated
May 25, 2026 - Python
Le couteau suisse PDF 100% offline - 0 tracker - CircaFrax - Astra
-
Updated
Sep 29, 2026
Add this topic to your repo
To associate your repository with the pypdfium2 topic, visit your repo's landing page and select "manage topics."