66 lines
1.9 KiB
Python
66 lines
1.9 KiB
Python
|
"""
|
||
|
|
PDF Text Extractor
|
||
|
|
"""
|
||
|
|
import pdfplumber
|
||
|
|
from typing import Dict, List, Optional
|
||
|
|
|
||
|
|
|
||
|
|
class PDFProcessor:
|
||
|
|
"""Extract text from PDF files"""
|
||
|
|
|
||
|
|
def extract_text(self, file_path: str) -> str:
|
||
|
|
"""Extract all text from PDF"""
|
||
|
|
text_parts = []
|
||
|
|
|
||
|
|
with pdfplumber.open(file_path) as pdf:
|
||
|
|
for page_num, page in enumerate(pdf.pages, 1):
|
||
|
|
text = page.extract_text()
|
||
|
|
if text:
|
||
|
|
text_parts.append(f"--- Page {page_num} ---\n{text}")
|
||
|
|
|
||
|
|
return "\n\n".join(text_parts)
|
||
|
|
|
||
|
|
def extract_pages(self, file_path: str) -> List[Dict]:
|
||
|
|
"""Extract text page by page with metadata"""
|
||
|
|
pages = []
|
||
|
|
|
||
|
|
with pdfplumber.open(file_path) as pdf:
|
||
|
|
for page_num, page in enumerate(pdf.pages, 1):
|
||
|
|
text = page.extract_text()
|
||
|
|
if text:
|
||
|
|
pages.append({
|
||
|
|
"page_number": page_num,
|
||
|
|
"text": text.strip(),
|
||
|
|
"word_count": len(text.split())
|
||
|
|
})
|
||
|
|
|
||
|
|
return pages
|
||
|
|
|
||
|
|
def extract_with_metadata(self, file_path: str) -> Dict:
|
||
|
|
"""Extract text with PDF metadata"""
|
||
|
|
result = {
|
||
|
|
"text": "",
|
||
|
|
"pages": [],
|
||
|
|
"metadata": {}
|
||
|
|
}
|
||
|
|
|
||
|
|
with pdfplumber.open(file_path) as pdf:
|
||
|
|
# Get metadata
|
||
|
|
result["metadata"] = {
|
||
|
|
"page_count": len(pdf.pages),
|
||
|
|
"metadata": pdf.metadata
|
||
|
|
}
|
||
|
|
|
||
|
|
# Extract pages
|
||
|
|
pages = self.extract_pages(file_path)
|
||
|
|
result["pages"] = pages
|
||
|
|
result["text"] = "\n\n".join([p["text"] for p in pages])
|
||
|
|
|
||
|
|
return result
|
||
|
|
|
||
|
|
|
||
|
|
def process_pdf(file_path: str) -> str:
|
||
|
|
"""Process PDF file and return text"""
|
||
|
|
processor = PDFProcessor()
|
||
|
|
return processor.extract_with_metadata(file_path)["text"]
|