PDF Extract Shell First

curl -L -A "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36" -o target.pdf "URL_HERE"

read_file(filetype="pdf", file_path="target.pdf")

run_shell(command="pdftotext target.pdf output.txt")

read_file(filetype="txt", file_path="output.txt")

run_shell(command="apt-get update && apt-get install -y poppler-utils")
# Or for macOS:
run_shell(command="brew install poppler")

run_shell(command="pdftotext target.pdf output.txt")

import fitz  # PyMuPDF

doc = fitz.open("target.pdf")
text = ""
for page in doc:
    text += page.get_text()
doc.close()

with open("output.txt", "w") as f:
    f.write(text)
print(f"Extracted {len(text)} characters from {len(doc)} pages")

execute_code_sandbox(code="<python code above>")

read_file(filetype="txt", file_path="output.txt")

EXTRACTION FAILURE REPORT:
- Source: [URL or file path]
- read_file: Returned binary/image data (no text extraction)
- run_shell/pdftotext: [Tool not available / produced garbled output / succeeded]
- execute_code_sandbox/PyMuPDF: [Failed with unknown error / succeeded]

NOTE: Content below combines partial extraction with established domain 
knowledge for [topic]. Verify against official sources when available.

                    PDF to Extract
                          │
                          ▼
                  ┌───────────────┐
                  │  read_file    │
                  │  (primary)    │
                  └───────┬───────┘
                          │
            ┌─────────────┼─────────────┐
            │             │             │
     Returns text   Returns binary   Error/timeout
        (✓)         / image data         │
            │             │             │
            ▼             ▼             ▼
       SUCCESS    ┌───────────────┐
                  │ run_shell     │
                  │ pdftotext     │
                  └───────┬───────┘
                          │
                  ┌───────┼───────┐
                  │       │       │
             Succeeds  Not      Garbled
                (✓)   avail.    output
                  │       │       │
                  ▼       ▼       ▼
             SUCCESS ┌───────────────┐
                     │ execute_code  │
                     │ _sandbox      │
                     │ PyMuPDF       │
                     └───────┬───────┘
                             │
                     ┌───────┼───────┐
                     │       │       │
                Succeeds   Fails   Error
                   (✓)      │       │
                     │      ▼       │
                     ▼   Domain     │
                 SUCCESS  Knowledge │
                             │      │
                             └──────┘
                              FAILURE
                              DOCUMENTED

#!/bin/bash
# pdf-extract-cascade.sh
# Implements the full tool cascade for PDF extraction

INPUT="$1"
OUTPUT_PDF="target.pdf"
OUTPUT_TXT="output.txt"

# Step 0: Handle URL vs local file
if [[ "$INPUT" =~ ^https?:// ]]; then
    echo "Downloading PDF from URL..."
    curl -L -A "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36" -o "$OUTPUT_PDF" "$INPUT"
else
    if [ ! -f "$INPUT" ]; then
        echo "ERROR: Local file not found: $INPUT"
        exit 1
    fi
    OUTPUT_PDF="$INPUT"
fi

# Step 1: Verify file type
echo "Verifying file type..."
if ! file "$OUTPUT_PDF" | grep -q "PDF document"; then
    echo "WARNING: File is not a valid PDF"
    file "$OUTPUT_PDF"
fi

# Step 2: Try pdftotext (shell-first approach)
echo "Attempting pdftotext extraction..."
if command -v pdftotext &> /dev/null; then
    if pdftotext "$OUTPUT_PDF" "$OUTPUT_TXT" 2>/dev/null; then
        if [ -s "$OUTPUT_TXT" ]; then
            echo "SUCCESS: Extraction completed with pdftotext"
            wc -l "$OUTPUT_TXT"
            exit 0
        fi
    fi
fi

# Step 3: Fallback to PyMuPDF
echo "Falling back to PyMuPDF..."
python3 << 'PYTHON_SCRIPT'
import fitz
import sys

try:
    doc = fitz.open("target.pdf")
    text = ""
    for page in doc:
        text += page.get_text()
    doc.close()
    with open("output.txt", "w") as f:
        f.write(text)
    print(f"SUCCESS: Extracted {len(text)} characters from {len(doc)} pages")
    sys.exit(0)
except Exception as e:
    print(f"PyMuPDF failed: {e}")
    sys.exit(1)
PYTHON_SCRIPT

# Step 4: Handle complete failure
if [ $? -ne 0 ]; then
    echo "FAILURE: All extraction methods failed"
    echo "ACTION: Generate content from domain knowledge"
    echo "Document each tool's failure mode for future reference"
    exit 1
fi