pip install PyPDF2

from PyPDF2 import PdfFileReader, PdfFileWriter  
  
# 創(chuàng)建PDF寫入對(duì)象  
output = PdfFileWriter()  
  
# 讀取第一個(gè)PDF文件  
input1 = PdfFileReader(open("file1.pdf", "rb"))  
  
# 讀取第二個(gè)PDF文件  
input2 = PdfFileReader(open("file2.pdf", "rb"))  
  
# 將第一個(gè)PDF文件的所有頁面添加到輸出文件中  
for i in range(input1.getNumPages()):  
    output.addPage(input1.getPage(i))  
  
# 將第二個(gè)PDF文件的所有頁面添加到輸出文件中  
for i in range(input2.getNumPages()):  
    output.addPage(input2.getPage(i))  
  
# 將合并后的PDF文件寫入到新的文件中  
with open("output.pdf", "wb") as outputStream:  
    output.write(outputStream)

from PyPDF2 import PdfFileReader, PdfFileWriter  
  
# 定義要插入的起始頁碼  
insert_start_page = 3  # 假設(shè)要在第一個(gè)PDF文件的第3頁后插入第二個(gè)PDF文件的內(nèi)容  
  
# 創(chuàng)建PDF寫入對(duì)象  
output = PdfFileWriter()  
  
# 讀取第一個(gè)PDF文件  
input1 = PdfFileReader(open("file1.pdf", "rb"))  
  
# 讀取第二個(gè)PDF文件  
input2 = PdfFileReader(open("file2.pdf", "rb"))  
  
# 將第一個(gè)PDF文件的前insert_start_page-1頁添加到輸出文件中  
for i in range(insert_start_page - 1):  
    output.addPage(input1.getPage(i))  
  
# 將第二個(gè)PDF文件的所有頁面添加到輸出文件中  
for i in range(input2.getNumPages()):  
    output.addPage(input2.getPage(i))  
  
# 將第一個(gè)PDF文件的剩余頁面添加到輸出文件中  
for i in range(insert_start_page - 1, input1.getNumPages()):  
    output.addPage(input1.getPage(i))  
  
# 將合并后的PDF文件寫入到新的文件中  
with open("output.pdf", "wb") as outputStream:  
    output.write(outputStream)

# author:mlnt
# createdate:2022/8/16
import PyPDF2    # 導(dǎo)入PyPDF2模塊

# 官方文檔：https://pypi.org/project/PyPDF2/
# 1.打開PDF文件
pdf = open(file='test.pdf', mode='rb')  # 以二進(jìn)制方式打開

# 2.獲取PDF文件的頁數(shù)
# 打開PDF文件成功后，可使用PdfFileReader()方法讀取PDF內(nèi)容
pdf_reader = PyPDF2.PdfFileReader(pdf)  # 讀取PDF內(nèi)容
print(f'PDF頁數(shù)為：{pdf_reader.numPages}')
print(f'PDF頁數(shù)為：{len(pdf_reader.pages)}')

# 3.讀取PDF頁面內(nèi)容
"""
- 使用PdfFileReader()方法讀取PDF文件后，可使用getPage(n)（或pages[n]）獲取第n頁的PDF內(nèi)容
- PDF頁面從第0頁開始計(jì)算
- 頁面內(nèi)容被讀入后，可使用extractText()取得該頁的字符串內(nèi)容
"""
for i in range(pdf_reader.numPages):
    pageObj = pdf_reader.getPage(i)  # 讀取第i頁內(nèi)容
    # pageObj = pdf_reader.pages[i]  # 讀取第i頁內(nèi)容
    page_content = pageObj.extractText()  # 提取頁面內(nèi)容
    print(page_content)

# author:mlnt
# createdate:2022/8/16

import PyPDF2
from PyPDF2 import PdfReader, PdfWriter


def checkEncrypted(filename):
    """檢查文件是否加密"""
    pdfObj = open(file=filename, mode='rb')  # 以二進(jìn)制方式打開
    pdfRd = PyPDF2.PdfFileReader(pdfObj)  # 讀取PDF內(nèi)容
    # 判斷文件是否加密
    if pdfRd.isEncrypted:
        print(f'{filename}屬于加密文件')
    else:
        print(f'{filename}未加密')


def pdfEncrypt(filename):
    """pdf加密"""
    reader = PdfReader(filename)  # 創(chuàng)建RdfReader對(duì)象
    writer = PdfWriter()  # 創(chuàng)建PdfWriter對(duì)象

    # 將所有頁面添加到writer
    for page in reader.pages:
        # PDF頁面旋轉(zhuǎn)
        page.rotate_clockwise(90)  # 旋轉(zhuǎn)90度
        page.rotate_clockwise(-180)  # 逆時(shí)針旋轉(zhuǎn)180度
        writer.add_page(page)

    # 添加密碼
    writer.encrypt('123456')

    new_name = filename[:filename.rfind('.pdf')] + '-encrypted.pdf'
    # 保存pdf
    with open(new_name, 'wb') as f:
        writer.write(f)


def pdfDecrypt(filename):
    """pdf解密"""
    reader = PdfReader(filename)
    writer = PdfWriter()

    # 判斷是否加密
    if reader.isEncrypted:
        reader.decrypt('123456')

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

    new_name = filename[:filename.rfind('.pdf')] + '-decrypted.pdf'
    # 保存pdf
    with open(new_name, 'wb') as f:
        writer.write(f)


checkEncrypted('test.pdf')
pdfEncrypt('test.pdf')
pdfDecrypt('test-encrypted.pdf')

# author:mlnt
# createdate:2022/8/16
from PyPDF2 import PdfMerger

merger = PdfMerger()  # 創(chuàng)建PdfMerger對(duì)象

pdf1 = open('test.pdf', 'rb')

pdf2 = open('watermark.pdf', 'rb')

# 將整個(gè)文檔添加到merger
merger.append(fileobj=pdf1)

# 將pdf2插入到merger，從第0頁開始
merger.merge(position=0, fileobj=pdf2)

with open('merger-test.pdf', 'wb') as f:
    merger.write(f)

merger.close()