from pypdf import PdfReader, PdfWriter

# 讀取 PDF
reader = PdfReader("document.pdf")
print(f"頁數: {len(reader.pages)}")

# 擷取文字
text = ""
for page in reader.pages:
    text += page.extract_text()

from pypdf import PdfWriter, PdfReader

writer = PdfWriter()
for pdf_file in ["doc1.pdf", "doc2.pdf", "doc3.pdf"]:
    reader = PdfReader(pdf_file)
    for page in reader.pages:
        writer.add_page(page)

with open("merged.pdf", "wb") as output:
    writer.write(output)

reader = PdfReader("input.pdf")
for i, page in enumerate(reader.pages):
    writer = PdfWriter()
    writer.add_page(page)
    with open(f"page_{i+1}.pdf", "wb") as output:
        writer.write(output)

reader = PdfReader("document.pdf")
meta = reader.metadata
print(f"標題: {meta.title}")
print(f"作者: {meta.author}")
print(f"主題: {meta.subject}")
print(f"建立者: {meta.creator}")

reader = PdfReader("input.pdf")
writer = PdfWriter()

page = reader.pages[0]
page.rotate(90)  # 順時針旋轉 90 度
writer.add_page(page)

with open("rotated.pdf", "wb") as output:
    writer.write(output)

import pdfplumber

with pdfplumber.open("document.pdf") as pdf:
    for page in pdf.pages:
        text = page.extract_text()
        print(text)

with pdfplumber.open("document.pdf") as pdf:
    for i, page in enumerate(pdf.pages):
        tables = page.extract_tables()
        for j, table in enumerate(tables):
            print(f"第 {i+1} 頁的表格 {j+1}:")
            for row in table:
                print(row)

import pandas as pd

with pdfplumber.open("document.pdf") as pdf:
    all_tables = []
    for page in pdf.pages:
        tables = page.extract_tables()
        for table in tables:
            if table:  # 檢查表格是否不為空
                df = pd.DataFrame(table[1:], columns=table[0])
                all_tables.append(df)

# 合併所有表格
if all_tables:
    combined_df = pd.concat(all_tables, ignore_index=True)
    combined_df.to_excel("extracted_tables.xlsx", index=False)

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

c = canvas.Canvas("hello.pdf", pagesize=letter)
width, height = letter

# 新增文字
c.drawString(100, height - 100, "Hello World!")
c.drawString(100, height - 120, "這是使用 reportlab 建立的 PDF")

# 新增線條
c.line(100, height - 140, 400, height - 140)

# 儲存
c.save()

from reportlab.lib.pagesizes import A4
from reportlab.platypus import SimpleDocTemplate, Paragraph, Table, TableStyle
from reportlab.lib.styles import ParagraphStyle
from reportlab.lib import colors
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.ttfonts import TTFont

# 註冊中文字型（Windows）
pdfmetrics.registerFont(TTFont('MicrosoftJhengHei', 'C:/Windows/Fonts/msjh.ttc'))

# 建立樣式
cell_style = ParagraphStyle('Cell_CN', fontName='MicrosoftJhengHei', fontSize=9, leading=14)
header_style = ParagraphStyle('Header_CN', fontName='MicrosoftJhengHei', fontSize=9, leading=14, textColor=colors.white)

# 包裝函式 - 關鍵！
def wrap(text, style=cell_style):
    return Paragraph(text, style)

# 表格資料 - 使用 Paragraph 包裝才能自動換行
data = [
    [wrap('標題1', header_style), wrap('標題2', header_style)],
    [wrap('短文字'), wrap('這是一段很長的文字，會根據欄寬自動換行顯示')],
]

# 建立表格並設定欄寬
table = Table(data, colWidths=[100, 200])
table.setStyle(TableStyle([
    ('BACKGROUND', (0, 0), (-1, 0), colors.HexColor('#4472C4')),
    ('GRID', (0, 0), (-1, -1), 1, colors.HexColor('#DDDDDD')),
    ('VALIGN', (0, 0), (-1, -1), 'MIDDLE'),
    ('TOPPADDING', (0, 0), (-1, -1), 8),
    ('BOTTOMPADDING', (0, 0), (-1, -1), 8),
]))

from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak
from reportlab.lib.styles import getSampleStyleSheet

doc = SimpleDocTemplate("report.pdf", pagesize=letter)
styles = getSampleStyleSheet()
story = []

# 新增內容
title = Paragraph("報告標題", styles['Title'])
story.append(title)
story.append(Spacer(1, 12))

body = Paragraph("這是報告的內文。" * 20, styles['Normal'])
story.append(body)
story.append(PageBreak())

# 第 2 頁
story.append(Paragraph("第 2 頁", styles['Heading1']))
story.append(Paragraph("第 2 頁的內容", styles['Normal']))

# 建置 PDF
doc.build(story)

# 擷取文字
pdftotext input.pdf output.txt

# 擷取文字並保留版面配置
pdftotext -layout input.pdf output.txt

# 擷取特定頁面
pdftotext -f 1 -l 5 input.pdf output.txt  # 第 1-5 頁

# 合併 PDF
qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf

# 分割頁面
qpdf input.pdf --pages . 1-5 -- pages1-5.pdf
qpdf input.pdf --pages . 6-10 -- pages6-10.pdf

# 旋轉頁面
qpdf input.pdf output.pdf --rotate=+90:1  # 將第 1 頁旋轉 90 度

# 移除密碼
qpdf --password=mypassword --decrypt encrypted.pdf decrypted.pdf

# 合併
pdftk file1.pdf file2.pdf cat output merged.pdf

# 分割
pdftk input.pdf burst

# 旋轉
pdftk input.pdf rotate 1east output rotated.pdf

# 需要：pip install pytesseract pdf2image
import pytesseract
from pdf2image import convert_from_path

# 將 PDF 轉換為圖片
images = convert_from_path('scanned.pdf')

# 對每頁進行 OCR
text = ""
for i, image in enumerate(images):
    text += f"第 {i+1} 頁:\n"
    text += pytesseract.image_to_string(image)
    text += "\n\n"

print(text)

from pypdf import PdfReader, PdfWriter

# 建立浮水印（或載入現有的）
watermark = PdfReader("watermark.pdf").pages[0]

# 套用到所有頁面
reader = PdfReader("document.pdf")
writer = PdfWriter()

for page in reader.pages:
    page.merge_page(watermark)
    writer.add_page(page)

with open("watermarked.pdf", "wb") as output:
    writer.write(output)

# 使用 pdfimages (poppler-utils)
pdfimages -j input.pdf output_prefix

# 這會將所有圖片擷取為 output_prefix-000.jpg、output_prefix-001.jpg 等

from pypdf import PdfReader, PdfWriter

reader = PdfReader("input.pdf")
writer = PdfWriter()

for page in reader.pages:
    writer.add_page(page)

# 新增密碼
writer.encrypt("userpassword", "ownerpassword")

with open("encrypted.pdf", "wb") as output:
    writer.write(output)