python PDF常用的10个脚本

📝 面试求职： 「面试试题小程序」 ，内容涵盖 测试基础、Linux操作系统、MySQL数据库、Web功能测试、接口测试、APPium移动端测试、Python知识、Selenium自动化测试相关、性能测试、性能测试、计算机网络知识、Jmeter、HR面试，命中率杠杠的。（大家刷起来…）

📝 职场经验干货：

软件测试工程师简历上如何编写个人信息（一周8个面试）

软件测试工程师简历上如何编写专业技能（一周8个面试）

软件测试工程师简历上如何编写项目经验（一周8个面试）

软件测试工程师简历上如何编写个人荣誉（一周8个面试）

软件测试行情分享（这些都不了解就别贸然冲了.）

软件测试面试重点，搞清楚这些轻松拿到年薪30W+

软件测试面试刷题小程序免费使用（永久使用）

---

合并多个PDF文件

from PyPDF2 import PdfMerger

def merge_pdfs(paths, output):

    merger = PdfMerger()

    for pdf in paths:

        merger.append(pdf)

    merger.write(output)

    merger.close()

paths = ['/path/to/file1.pdf', '/path/to/file2.pdf']

output = '/path/to/merged.pdf'

merge_pdfs(paths, output)‍

拆分PDF文件

from PyPDF2 import PdfReader, PdfWriter

def split_pdf(input_path, start_page, end_page, output_path):

    with open(input_path, 'rb') as file:

        pdf = PdfReader(file)

        writer = PdfWriter()

        for i in range(start_page - 1, end_page):

            writer.add_page(pdf.pages[i])

        with open(output_path, 'wb') as output:

            writer.write(output)

input_path = '/path/to/input.pdf'

start_page = 1

end_page = 5

output_path = '/path/to/output.pdf'

split_pdf(input_path, start_page, end_page, output_path)‍

加密PDF文件

from PyPDF2 import PdfWriter, PdfReader

def encrypt_pdf(input_path, output_path, password):

    with open(input_path, 'rb') as file:

        pdf = PdfReader(file)

        writer = PdfWriter()

        for page in pdf.pages:

            writer.add_page(page)

        writer.encrypt(password)

        with open(output_path, 'wb') as output:

            writer.write(output)

input_path = '/path/to/input.pdf'

output_path = '/path/to/encrypted.pdf'

password = 'mysecretpassword'

encrypt_pdf(input_path, output_path, password)‍

解密PDF文件

from PyPDF2 import PdfReader, PdfWriter

def decrypt_pdf(input_path, output_path, password):

    with open(input_path, 'rb') as file:

        pdf = PdfReader(file)

        if not pdf.is_encrypted or pdf.decrypt(password) == 0:

            raise ValueError("Password incorrect or file not encrypted.")

        writer = PdfWriter()

        for page in pdf.pages:

            writer.add_page(page)

        with open(output_path, 'wb') as output:

            writer.write(output)

input_path = '/path/to/encrypted.pdf'

output_path = '/path/to/decrypted.pdf'

password = 'mysecretpassword'

decrypt_pdf(input_path, output_path, password)‍

提取PDF中的文本

from PyPDF2 import PdfReader

def extract_text_from_pdf(pdf_path):

    with open(pdf_path, 'rb') as file:

        pdf = PdfReader(file)

        text = ''

        for page in pdf.pages:

            text += page.extract_text()

    return text

pdf_path = '/path/to/input.pdf'

text = extract_text_from_pdf(pdf_path)

print(text)‍

将文本添加到PDF页面

from PyPDF2 import PdfWriter, PdfReader

from reportlab.lib.pagesizes import letter

from reportlab.pdfgen import canvas

def add_text_to_pdf(pdf_path, output_path, text, x, y):

    packet = io.BytesIO()

    can = canvas.Canvas(packet, pagesize=letter)

    can.drawString(x, y, text)

    can.save()

    packet.seek(0)

    new_pdf = PdfReader(packet)

    existing_pdf = PdfReader(open(pdf_path, "rb"))

    output = PdfWriter()

    page = existing_pdf.pages[0]

    page.merge_page(new_pdf.pages[0])

    output.add_page(page)

    outputStream = open(output_path, "wb")

    output.write(outputStream)

    outputStream.close()

pdf_path = '/path/to/input.pdf'

output_path = '/path/to/output_with_text.pdf'

text = 'This is some text.'

x = 50

y = 750

add_text_to_pdf(pdf_path, output_path, text, x, y)‍

添加水印到PDF

from PyPDF2 import PdfReader, PdfWriter

from reportlab.pdfgen import canvas

from reportlab.lib.pagesizes import letter

def add_watermark(input_pdf, output_pdf, watermark_text):

    watermark = canvas.Canvas("/tmp/watermark.pdf", pagesize=letter)

    watermark.saveState()

    watermark.setFont("Helvetica", 80)

    watermark.rotate(45)

    watermark.setFillAlpha(0.1)

    watermark.drawString(150, 300, watermark_text)

    watermark.restoreState()

    watermark.save()

    watermark_pdf = PdfReader(open("/tmp/watermark.pdf", "rb"))

    input_pdf = PdfReader(open(input_pdf, "rb"))

    output_pdf = PdfWriter()

    watermark_page = watermark_pdf.pages[0]

    for page in input_pdf.pages:

        page.merge_page(watermark_page)

        output_pdf.add_page(page)

    outputStream = open(output_pdf, "wb")

    output_pdf.write(outputStream)

    outputStream.close()

input_pdf = '/path/to/input.pdf'

output_pdf = '/path/to/output_with_watermark.pdf'

watermark_text = 'Confidential'

add_watermark(input_pdf, output_pdf, watermark_text)‍

删除PDF页面

from PyPDF2 import PdfReader, PdfWriter

def remove_pages(input_pdf, output_pdf, page_numbers):

    input_pdf = PdfReader(open(input_pdf, "rb"))

    output_pdf = PdfWriter()

    for i, page in enumerate(input_pdf.pages):

        if i + 1 not in page_numbers:

            output_pdf.add_page(page)

    outputStream = open(output_pdf, "wb")

    output_pdf.write(outputStream)

    outputStream.close()

input_pdf = '/path/to/input.pdf'

output_pdf = '/path/to/output_without_pages.pdf'

page_numbers = [1, 3]  # Pages to remove

remove_pages(input_pdf, output_pdf, page_numbers)‍

PDF页面旋转

from PyPDF2 import PdfReader, PdfWriter

def rotate_pages(input_pdf, output_pdf, page_numbers, angle):

    input_pdf = PdfReader(open(input_pdf, "rb"))

    output_pdf = PdfWriter()

    for i, page in enumerate(input_pdf.pages):

        if i + 1 in page_numbers:

            page.rotate(angle)

        output_pdf.add_page(page)

    outputStream = open(output_pdf, "wb")

    output_pdf.write(outputStream)

    outputStream.close()

input_pdf = '/path/to/input.pdf'

output_pdf = '/path/to/output_rotated.pdf'

page_numbers = [2, 4]  # Pages to rotate

angle = 90  # Rotation angle (90, 180, 270)

rotate_pages(input_pdf, output_pdf, page_numbers, angle)‍

将HTML转换为PDF

from weasyprint import HTML

def html_to_pdf(html_path, output_path):

    HTML(html_path).write_pdf(output_path)

html_path = '/path/to/input.html'

output_path = '/path/to/output.pdf'

html_to_pdf(html_path, output_path)‍

最后： 下方这份完整的软件测试视频教程已经整理上传完成，需要的朋友们可以自行领取【保证100%免费】
​​​​
​​​​