PDF

from pypdf import PdfReader, PdfWriter

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

# 提取文本
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"标题: {meta.title}")
print(f"作者: {meta.author}")
print(f"主题: {meta.subject}")
print(f"创建者: {meta.creator}")

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

page = reader.pages[0]
page.rotate(90)  # 顺时针旋转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} 页的表格 {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:  # 检查表格是否为空
                df = pd.DataFrame(table[1:], columns=table[0])
                all_tables.append(df)

# 合并所有表格
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

# 添加文本
c.drawString(100, height - 100, "Hello World!")
c.drawString(100, height - 120, "这是用 reportlab 创建的 PDF")

# 添加线条
c.line(100, height - 140, 400, height - 140)

# 保存
c.save()

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 = []

# 添加内容
title = Paragraph("报告标题", styles['Title'])
story.append(title)
story.append(Spacer(1, 12))

body = Paragraph("这是报告的正文内容。" * 20, styles['Normal'])
story.append(body)
story.append(PageBreak())

# 第2页
story.append(Paragraph("第2页", styles['Heading1']))
story.append(Paragraph("第2页的内容", styles['Normal']))

# 构建 PDF
doc.build(story)

# 提取文本
pdftotext input.pdf output.txt

# 提取文本并保留布局
pdftotext -layout input.pdf output.txt

# 提取指定页面
pdftotext -f 1 -l 5 input.pdf output.txt  # 第1-5页

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

# 拆分页面
qpdf input.pdf --pages . 1-5 -- pages1-5.pdf
qpdf input.pdf --pages . 6-10 -- pages6-10.pdf

# 旋转页面
qpdf input.pdf output.pdf --rotate=+90:1  # 将第1页旋转90度

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

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

# 拆分
pdftk input.pdf burst

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

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

# 将 PDF 转换为图像
images = convert_from_path('scanned.pdf')

# 对每一页进行 OCR 识别
text = ""
for i, image in enumerate(images):
    text += f"第 {i+1} 页:\n"
    text += pytesseract.image_to_string(image)
    text += "\n\n"

print(text)

from pypdf import PdfReader, PdfWriter

# 创建水印（或加载现有的）
watermark = PdfReader("watermark.pdf").pages[0]

# 应用到所有页面
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

# 这会将所有图像提取为 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)

# 添加密码
writer.encrypt("userpassword", "ownerpassword")

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