Note :- Please review the HTML file and Report file
And i have different folders for all the
raw data i have extracted from the PDF
# 📄 Advanced PDF Analysis Tool
An intelligent PDF analysis system that extracts text, tables, images, and
performs advanced linguistic analysis
including readability metrics, sentiment analysis, and generates interactive dashboards.
## ✨ Features
### 📊 Core Analysis
- **Text Extraction**: Extract all text content with page-level
granularity
- **Word Statistics**: Total words, unique words,
character count, reading time estimation
- **Spelling & Grammar**: Automatic spell-checking
with suggestions and frequency tracking
- **Smart Summarization**: Extractive summarization using TF-IDF-like
scoring
### 📈 Advanced Analytics (NEW!)
- **Readability Metrics**:
- Flesch Reading Ease score
- Gunning Fog Index
- Grade level estimation
- Average sentence length and syllable counts
- Per-page readability tracking
- **Sentiment Analysis**:
- Page-by-page sentiment scoring
- Overall document tone (positive/negative/neutral)
- Polarity and subjectivity measurements
- Sentiment trend visualization
- **Named Entity Recognition (NER)**: ⭐ NEW!
- Automatic identification and classification of entities
- Recognizes people, organizations, locations, dates, and more
- Entity frequency analysis and top entity rankings
- Category-wise entity breakdown
- Helps quickly identify key topics and subjects in documents
### 📊 Data Extraction
- **Tables**: Multi-method extraction (PyMuPDF, pdfplumber, text-based fallback)
- Automatic header detection and promotion
- Export to CSV with full metadata
- Smart table synopsis generation
- **Images**: Complete image extraction with metadata
- Size classification (small/medium/large)
- Color space and depth analysis
- Duplicate detection
- Context-aware extraction (nearby text)
- **References**: Automatic citation and URL extraction
- DOI detection
- arXiv paper links
- Web URLs and citations
### 📋 Output Formats
1. **Interactive HTML Dashboard** ⭐ NEW!
- Beautiful, modern design with dark gradient theme
- Interactive Plotly charts:
- Word frequency visualization
- Page complexity analysis
- Sentiment trends across pages
- Named Entity Recognition section with:
- Total entity count and category breakdown
- Top entities table with counts
- Entity type classification (PERSON, ORG, GPE, DATE, etc.)
- Responsive grid layout
- Key metrics cards
- Searchable tables
- One-click PDF export
2. **PDF Report**
- Professional formatted report
- Embedded tables with proper rendering
- Image thumbnails
- Comprehensive metrics summary
