skills.rest
EdwardSalkeld
EdwardSalkeldCOMMUNITY
Explore all skills by this author →
GitHub

liff-catalog-pdf-extraction

Extract structured per-film JSON data from LIFF catalog PDFs.

Updated Oct 15, 2025
Search Tags:#automation#pdf#catalog#json#extraction#film data
One-click install
npx skills add https://github.com/EdwardSalkeld/liff-archive --skill liff-catalog-pdf-extraction
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: liff-catalog-pdf-extraction
Source: https://github.com/EdwardSalkeld/liff-archive/tree/main/skills/liff-catalog-pdf-extraction
Command: npx skills add https://github.com/EdwardSalkeld/liff-archive --skill liff-catalog-pdf-extraction

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates the extraction of structured film data from PDF catalog pages, which often contain a mix of film entries and other non-film content.

Core Features & Use Cases

  • Multi-pass Extraction: Handles complex PDFs by performing text extraction, page classification, film block segmentation, and JSON normalization.
  • Selective Extraction: Skips non-film pages (like introductions, indexes, adverts) and logs the reasons.
  • Structured Output: Generates one JSON file per film with detailed metadata, or logs skipped pages.
  • Use Case: Process a batch of LIFF catalog PDFs to automatically create a structured database of all films featured in the catalog, including details like title, director, runtime, and description.

Quick Start

Use the liff-catalog-pdf-extraction skill to extract film data from the file 'page-10.pdf'.

Frequently Asked Questions about liff-catalog-pdf-extraction

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract structured film data from a PDF catalog?▼

Extracting structured film data from a PDF catalog requires a multi-pass workflow that performs text extraction, classifies film pages versus non-film content, segments film blocks, and normalizes the output into per-film JSON files. Pages without film content are logged and skipped.

What's the best way to parse mixed content types in catalog PDFs?▼

Parsing mixed content types in catalog PDFs is handled by a selective extraction workflow that classifies each page independently, skipping non-film content like indexes and adverts while segmenting actual film blocks for structured JSON normalization.

Do I need external tools to convert PDF pages to JSON?▼

Converting PDF pages to JSON relies on external tools like pdftotext and jq, with optional Python package support via a local tooling environment to facilitate the multi-pass extraction and normalization workflow.

Why does PDF text extraction skip certain pages in a film catalog?▼

PDF text extraction skips certain pages in a film catalog to filter out non-film content. The workflow classifies pages independently, logs the reasons for skipping introductions or adverts, and processes only valid film blocks to ensure clean JSON output.

How are sanity checks performed during PDF data extraction?▼

Sanity checks are performed during PDF data extraction after segmenting film blocks and normalizing JSON output. These checks validate the structured per-film data, ensuring the extracted metadata meets expected quality standards before generating the final JSON files.

Related Skills

Explore More Content & Communication Skills→
Xinm123Xinm123

pdf

Extract text and tables from PDFs using Python tools.

Community
Intermediate
cri-matthewcri-matthew

legislative-flattener

Flatten hierarchical legislative DOCX text into numbered requirements with classifications.

Community
Intermediate
babywormbabyworm
43

rtl-p4-rapid-impl-policy

Enforce lint, CDC, smoke, and block sanity gates for P4 modules.

Community
Intermediate
EthanAlgoXEthanAlgoX
65

sentiment-analysis

Extract and quantify market sentiment from unstructured text into normalized scores.

Community
Intermediate