python自动化操作PDF

一、模块安装

pip install pypdf2 -i https://pypi.tuna.tsinghua.edu.cn/simple  #模块主要作用： 读取、写入、分割、合并PDF文件
pip install pdfplumber -i https://pypi.tuna.tsinghua.edu.cn/simple #模块主要作用：更好的读取 PDF 文件中内容和提取 PDF 中的表格

二、模块使用示例

示例文件下载：https://pan.baidu.com/s/10GFAq0LNa43Q4H1bMhZ3eg?pwd=55ka 提取码: 55ka

1.提取页面文字

import pdfplumber

with pdfplumber.open('Netease Q2 2019 Earnings Release-Final.pdf') as pdf:
    first_page = pdf.pages[0]  # 获取指定页面的内容
    text = first_page.extract_text()  # 获取页面text内容
    print(text)

2.提取页面表格

import pdfplumber

with pdfplumber.open('Netease Q2 2019 Earnings Release-Final.pdf') as pdf:
    first_page = pdf.pages[0]  # 获取指定页面的内容
    table = first_page.extract_table()  # 获取页面table内容
    print(table)  # 将表格转换为[[],[],[]]格式



# 提取页面特定表格
with pdfplumber.open('Netease Q2 2019 Earnings Release-Final.pdf') as pdf:
    first_page = pdf.pages[9]  # 获取指定页面的内容
    table = first_page.extract_table(
        table_settings  ={
            'vertical_strat egy': 'text',
            'horizontal_strategy': 'text',
        }
    )
    workbook = Workbook()
    sheet = workbook.active
    for row in table:
        if not ''.join([str(item) for item in row]) == '':  # 拼接列表中所有元素，判断当前行是否是空行
            sheet.append(row)
    workbook.save(filename="Netease_Q2_2019_earnings.xlsx")

3.PDF分割　　

# 2.x版本
from PyPDF2 import PdfFileReader,PdfFileWriter
pdf_reader = PdfFileReader('Netease Q2 2019 Earnings Release-Final.pdf')
for page in range(pdf_reader.getNumPages()):
    pdf_writer = PdfFileWriter()
    pdf_writer.add_page(pdf_reader.getPage(page))
    with open(f'分割后_Netease Q2 2019 Earnings {page}.pdf','wb') as out:
        pdf_writer.write(out)


# 3.x版本
from PyPDF2 import PdfReader,PdfWriter
pdf_reader = PdfReader('Netease Q2 2019 Earnings Release-Final.pdf')
for page in range(len(pdf_reader.pages)):
    pdf_writer = PdfWriter()
    pdf_writer.add_page(pdf_reader.pages[page])
    with open(f'分割后_Netease Q2 2019 Earnings {page}.pdf','wb') as out:
        pdf_writer.write(out)

4.PDF合并

# 2.x版本
from PyPDF2 import PdfFileReader, PdfFileWriter

pdf_writer = PdfFileWriter()
for page in range(16):  # 16为文件的个数
    pdf_reader = PdfFileReader(f'分割后_Netease Q2 2019 Earnings {page}.pdf')
    for page in range(pdf_reader.getNumPages()):
        pdf_writer.addPage(pdf_reader.getPage(page))
with open('merged.pdf', 'wb') as out:
    pdf_writer.write(out)

# 3.x版本
from PyPDF2 import PdfReader,PdfWriter

pdf_writer = PdfWriter()
for page in range(16):  # 16为文件的个数
    pdf_reader = PdfReader(f'分割后_Netease Q2 2019 Earnings {page}.pdf')
    for page in range(len(pdf_reader.pages)):  # 循环PDF文件的每一页
        pdf_writer.add_page(pdf_reader.pages[page])
with open('merged.pdf', 'wb') as out:
    pdf_writer.write(out)

5.PDF页面旋转

# 2.x版本
from PyPDF2 import PdfFileReader, PdfFileWriter
pdf_reader = PdfFileReader('Netease Q2 2019 Earnings Release-Final.pdf')
pdf_writer = PdfFileWriter()
page = pdf_reader.getPage(0).rotateClockwise(90) #顺时针旋转，只能是90的倍数
pdf_writer.addPage(page)
page = pdf_reader.getPage(1).rotateClockwise(90) #逆时针旋转，只能是90的倍数
pdf_writer.addPage(page)
with open('rotated.pdf', 'wb') as out:
    pdf_writer.write(out)

# 3.x版本
from PyPDF2 import PdfReader, PdfWriter
pdf_reader = PdfReader('Netease Q2 2019 Earnings Release-Final.pdf')
pdf_writer = PdfWriter()
page = pdf_reader.pages[0].rotate(90) #指定页面旋转，只能是90的倍数 正数为顺时针旋转 负数为逆时针旋转
pdf_writer.add_page(page)
page = pdf_reader.pages[1].rotate(-90)
pdf_writer.add_page(page)
with open('rotated.pdf', 'wb') as out:
    pdf_writer.write(out)

6.PDF添加水印

# 2.x版本
from PyPDF2 import PdfFileReader, PdfFileWriter
from copy import copy

watermark_paf = PdfFileReader('shuiyin.pdf')
watermark_page = watermark_paf.getPage(0)
pdf_reader = PdfFileReader('Netease Q2 2019 Earnings Release-Final.pdf')
pdf_writer = PdfFileWriter()

for page in range(pdf_reader.getNumPages()):
    original_page = pdf_reader.getPage(page)
    new_page = copy(watermark_page)
    new_page.mergePage(original_page)
    pdf_writer.addPage(new_page)

with open('watermarked.pdf', 'wb') as out:
    pdf_writer.write(out)

# 3.x
from PyPDF2 import PdfReader, PdfWriter
from copy import copy

watermark_paf = PdfReader('shuiyin.pdf')
watermark_page = watermark_paf.pages[0]
pdf_reader = PdfReader('Netease Q2 2019 Earnings Release-Final.pdf')
pdf_writer = PdfWriter()

for page in range(len(pdf_reader.pages)):
    original_page = pdf_reader.pages[page]
    new_page = copy(watermark_page)  # 复制水印页面
    new_page.merge_page(original_page)  # 此处决定水印在文字下方还是上方 格式：下面的内容.merge_page(出现在上面的内容)
    pdf_writer.add_page(new_page)

with open('watermarked.pdf', 'wb') as out:
    pdf_writer.write(out)

7.PDF加解密

# 2.x
from PyPDF2 import PdfFileReader, PdfFileWriter

pdf_reader = PdfFileReader('Netease Q2 2019 Earnings Release-Final.pdf')
pdf_writer = PdfFileWriter()
for page in range(pdf_reader.getNumPages()):
    pdf_writer.addPage(pdf_reader.getPage(page))

pdf_writer.encrypt('makerbean')  # 加密的密码
with open('encrypted.pdf', 'wb') as out:
    pdf_writer.write(out)

# 3.x
from PyPDF2 import PdfReader, PdfWriter

pdf_reader = PdfReader('Netease Q2 2019 Earnings Release-Final.pdf')
pdf_writer = PdfWriter()
for page in range(len(pdf_reader.pages)):
    pdf_writer.add_page(pdf_reader.pages[page])

pdf_writer.encrypt('makerbean')  # 加密的密码
with open('encrypted.pdf', 'wb') as out:
    pdf_writer.write(out)

pdf_reader = PdfReader('encrypted.pdf')
pdf_reader.decrypt('makerbean')
pdf_writer = PdfWriter()
.... 解密后正常操作，不再赘述