Python으로 PDF 파일 다루기

Python PDF 처리:

# 1. PyPDF2 — 기본 텍스트 추출
from PyPDF2 import PdfReader

reader = PdfReader("document.pdf")
for page in reader.pages:
    print(page.extract_text())

# 2. pdfplumber — 테이블 추출에 강함
import pdfplumber
with pdfplumber.open("document.pdf") as pdf:
    for page in pdf.pages:
        print(page.extract_text())
        tables = page.extract_tables()

# 3. PDF 생성 — reportlab
from reportlab.pdfgen import canvas
c = canvas.Canvas("output.pdf")
c.drawString(100, 750, "Hello, PDF!")
c.save()

# 4. PDF 병합
from PyPDF2 import PdfMerger
merger = PdfMerger()
merger.append("file1.pdf")
merger.append("file2.pdf")
merger.write("merged.pdf")