一文教会你用Python读取PDF文件

> pip install pdfplumber -i https://pypi.tuna.tsinghua.edu.cn/simple

import pdfplumber

with pdfplumber.open('./dddd.pdf') as pdf:
    for page in pdf.pages:
        print(page.extract_text())

        # 每页打印一分页分隔
        print('---------- 分页分隔 ----------')

pdfplumber.open("文件名", password = "密码", laparams = { "line_overlap": 0.7 })

import PyPDF2

from PyPDF2.pdf import PageObject

# 创建一个读PDF文件的Reader对象

reader = PyPDF2.PdfFileReader('resources/XGBoost.pdf')

# 创建一个写PDF文件的Writer对象

writer = PyPDF2.PdfFileWriter()

# 对PDF文件所有页进行循环遍历

for page_num in range(reader.numPages):

      # 获取指定页码的Page对象

      current_page = reader.getPage(page_num) # type: PageObject

      if page_num % 2 == 0:

         # 奇数页顺时针旋转90度

         current_page.rotateClockwise(90)

      else:

# 偶数页反时针旋转90度

             current_page.rotateCounterClockwise(90)

      writer.addPage(current_page)

# 最后添加一个空白页并旋转90度

page = writer.addBlankPage() # type: PageObject

page.rotateClockwise(90)

# 通过Writer对象的write方法将PDF写入文件

with open('resources/XGBoost-modified.pdf', 'wb') as file:

    writer.write(file)

import PyPDF2

reader = PyPDF2.PdfFileReader('resources/XGBoost.pdf')
writer = PyPDF2.PdfFileWriter()

for page_num in range(reader.numPages):
     writer.addPage(reader.getPage(page_num))

# 通过encrypt方法加密PDF文件，方法的参数就是rre

#设置的密码
writer.encrypt('foobared')

with open('resources/XGBoost-encrypted.pdf', 'wb') as file:

       writer.write(file)

import PyPDF2

from PyPDF2.pdf import PageObject

reader1 = PyPDF2.PdfFileReader('resources/XGBoost.pdf') reader2 = PyPDF2.PdfFileReader('resources/watermark.pdf')
writer = PyPDF2.PdfFileWriter()

# 获取水印页
watermark_page = reader2.getPage(0)

for page_num in range(reader1.numPages):

     current_page = reader1.getPage(page_num) # type: PageObject                                           current_page.mergePage(watermark_page)

     # 将原始页和水印页进行合并
     writer.addPage(current_page) 

# 将PDF写入文件
with open('resources/XGBoost-watermarked.pdf', 'wb') as file:

       writer.write(file)