python使用PyPDF2 和 pdfplumber操作PDF文件

import os.path
from PyPDF2 import PdfFileReader, PdfFileWriter

pdf_path = r"D:\自动化\pdf.pdf"
out_dir = r"D:\自动化\pdf\拆分"

if not os.path.exists(out_dir):
	os.makedirs(out_dir)
	
# 获取 PdfFileReader 对象
pdf_reader = PdfFileReader(pdf_path)

# 获取 pdf 文件页数
pageCount = pdf_reader.getNumPages()
for page in range(pageCount):
	pdf_writer = PdfFileWriter()
	pdf_writer.addPage(pdf_reader.getPage(page))
	out_path = out_dir + "\\%s.pdf" % page
	with open(out_path, "wb") as out:
		pdf_writer.write(out)

import os
from PyPDF2 import PdfFileWriter, PdfFileReader

"""
	拆分PDF为多个小的PDF文件，
	@param filename:拆分后的文件名
	@param filepath:文件路径
	@param save_dir:保存小的PDF的文件路径
	@param step: 每step间隔的页面生成一个文件，例如step=3，表示0-2页、2-5页...为一个文件
	@return:
"""
def 拆分PDF(file_name, file_path, save_dir, step=3):
	if not os.path.exists(save_dir):
		os.mkdir(save_dir)

	if step < 1:
		print("输入的拆分间隔不能小于1")
		return

	pdf_reader = PdfFileReader(file_path)
	# 获取文件总页数
	pageCount = pdf_reader.getNumPages()
	# 读取每一页的数据
	for page in range(0, pageCount, step):
		pdf_writer = PdfFileWriter()
		# 拆分pdf，每 step 页的拆分成一个文件
		for index in range(page, page + step):
			if index < pageCount:
				pdf_writer.addPage(pdf_reader.getPage(index))
		# 保存拆分后的小文件
		childName = '%s%s.pdf' % (file_name, int(page / step) + 1)
		save_path = os.path.join(save_dir, childName)
		print(save_path)
		with open(save_path, "wb") as out:
			pdf_writer.write(out)
	print("文件已成功拆分，保存路径为：" + save_dir)

if __name__ == '__main__':
	拆分PDF('拆分PDF', 'D:\自动化\pdf\二期第1讲.pdf', 'D:\自动化\pdf\拆分2', 4)

from PyPDF2 import PdfFileReader, PdfFileWriter
import os

pdf_dir = r"D:\自动化\pdf\拆分"
out_path = r"D:\自动化\pdf\merge.pdf"

pdfList = os.listdir(pdf_dir)
pdf_writer = PdfFileWriter()
for i in range(len(pdfList)):
	path = pdf_dir + "\\%s.pdf" % i
	pdf_reader = PdfFileReader(path)
	for page in range(pdf_reader.getNumPages()):
		pdf_writer.addPage(pdf_reader.getPage(page))

with open(out_path, "wb") as out:
	pdf_writer.write(out)

import pdfplumber

pdf_path = r"D:\自动化\pdf\道德经.pdf"
with pdfplumber.open(pdf_path) as pdf:
	# 读取所有内容
	for page in pdf.pages:
		print(page.extract_text())

# 读取第一页的文字内容
# page = pdf.pages[0]
# print(page.extract_text())

import pdfplumber
pdf_path = r"D:\自动化\pdf\道德经.pdf"
with pdfplumber.open(pdf_path) as pdf:
	# 获取第2页数据
	page = pdf.pages[1]
	# 获取第2页的第一个表格的内容
	table = page.extract_table()
	print(type(table), table)
	
	# 获取第2页所有表格的内容
	tables = page.extract_tables()
	print(type(tables), tables)

from PyPDF2 import PdfFileReader, PdfFileWriter

pdf_path = r"D:\自动化\pdf\道德经.pdf"
sava_path = r"D:\自动化\pdf\加密后.pdf"

pdf_reader = PdfFileReader(pdf_path)
pdf_writer = PdfFileWriter()
for page in range(pdf_reader.getNumPages()):
	pdf_writer.addPage(pdf_reader.getPage(page))

# 添加密码
pdf_writer.encrypt("mima")

with open(sava_path, "wb") as out:
	pdf_writer.write(out)

from PyPDF2 import PdfFileReader, PdfFileWriter

pdf_path = r"D:\自动化\pdf\加密后.pdf"
sava_path = r"D:\自动化\pdf\解密后.pdf"

pdf_reader = PdfFileReader(pdf_path)

# 利用密码解密
pdf_reader.decrypt('mima')
pdf_writer = PdfFileWriter()
for page in range(pdf_reader.getNumPages()):
	pdf_writer.addPage(pdf_reader.getPage(page))
with open(sava_path, "wb") as out:
	pdf_writer.write(out)