Python利用PyPDF2库处理PDF文件的基本操作

pip install PyPDF2

import PyPDF2

pdf1 = open("file1.pdf", "rb")
pdf2 = open("file2.pdf", "rb")
output = open("merged.pdf", "wb")

pdf_reader1 = PyPDF2.PdfFileReader(pdf1)
pdf_reader2 = PyPDF2.PdfFileReader(pdf2)
pdf_writer = PyPDF2.PdfFileWriter()

for page_num in range(pdf_reader1.numPages):
    page = pdf_reader1.getPage(page_num)
    pdf_writer.addPage(page)

for page_num in range(pdf_reader2.numPages):
    page = pdf_reader2.getPage(page_num)
    pdf_writer.addPage(page)

pdf_writer.write(output)

pdf1.close()
pdf2.close()
output.close()

import PyPDF2

pdf = open("source.pdf", "rb")
pdf_reader = PyPDF2.PdfFileReader(pdf)

for page_num in range(pdf_reader.numPages):
    pdf_writer = PyPDF2.PdfFileWriter()
    pdf_writer.addPage(pdf_reader.getPage(page_num))
    output = open(f"page_{page_num + 1}.pdf", "wb")
    pdf_writer.write(output)
    output.close()

pdf.close()

import PyPDF2

pdf = open("file.pdf", "rb")
pdf_reader = PyPDF2.PdfFileReader(pdf)
pdf_writer = PyPDF2.PdfFileWriter()

for page_num in range(pdf_reader.numPages):
    page = pdf_reader.getPage(page_num)
    page.rotateClockwise(90)  # 旋转90度
    pdf_writer.addPage(page)

output = open("rotated.pdf", "wb")
pdf_writer.write(output)

pdf.close()
output.close()

import PyPDF2

pdf = open("file.pdf", "rb")
pdf_reader = PyPDF2.PdfFileReader(pdf)

text = ""
for page_num in range(pdf_reader.numPages):
    page = pdf_reader.getPage(page_num)
    text += page.extractText()

print(text)

import PyPDF2

pdf = open("file.pdf", "rb")
pdf_reader = PyPDF2.PdfFileReader(pdf)
pdf_writer = PyPDF2.PdfFileWriter()

watermark = PyPDF2.PdfFileReader(open("watermark.pdf", "rb"))

for page_num in range(pdf_reader.numPages):
    page = pdf_reader.getPage(page_num)
    page.mergePage(watermark.getPage(0))
    pdf_writer.addPage(page)

output = open("watermarked.pdf", "wb")
pdf_writer.write(output)

pdf.close()
output.close()

import PyPDF2

pdf = open("file.pdf", "rb")
pdf_reader = PyPDF2.PdfFileReader(pdf)
pdf_writer = PyPDF2.PdfFileWriter()

for page_num in range(pdf_reader.numPages):
    page = pdf_reader.getPage(page_num)
    pdf_writer.addPage(page)

pdf_writer.encrypt("password", "owner_password")
output = open("encrypted.pdf", "wb")
pdf_writer.write(output)

pdf.close()
output.close()

import PyPDF2

pdf = open("file.pdf", "rb")
pdf_reader = PyPDF2.PdfFileReader(pdf)

for page_num in range(pdf_reader.numPages):
    page = pdf_reader.getPage(page_num)
    xObject = page['/Resources']['/XObject'].get_object()
    for obj in xObject:
        if xObject[obj]['/Subtype'] == '/Image':
            img = xObject[obj]
            data = img.get_data()
            with open(f"image_{page_num + 1}.jpg", "wb") as f:
                f.write(data)

pdf.close()