import os.path
from PyPDF2 import PdfFileReader, PdfFileWriter

pdf_path = r"D:\自動化\pdf.pdf"
out_dir = r"D:\自動化\pdf\拆分"

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

# 獲取 pdf 文件頁數(shù)
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為多個小的PDF文件，
	@param filename:拆分后的文件名
	@param filepath:文件路徑
	@param save_dir:保存小的PDF的文件路徑
	@param step: 每step間隔的頁面生成一個文件，例如step=3，表示0-2頁、2-5頁...為一個文件
	@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("輸入的拆分間隔不能小于1")
		return

	pdf_reader = PdfFileReader(file_path)
	# 獲取文件總頁數(shù)
	pageCount = pdf_reader.getNumPages()
	# 讀取每一頁的數(shù)據(jù)
	for page in range(0, pageCount, step):
		pdf_writer = PdfFileWriter()
		# 拆分pdf，每 step 頁的拆分成一個文件
		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，保存路徑為：" + save_dir)

if __name__ == '__main__':
	拆分PDF('拆分PDF', 'D:\自動化\pdf\二期第1講.pdf', 'D:\自動化\pdf\拆分2', 4)

from PyPDF2 import PdfFileReader, PdfFileWriter
import os

pdf_dir = r"D:\自動化\pdf\拆分"
out_path = r"D:\自動化\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:\自動化\pdf\道德經(jīng).pdf"
with pdfplumber.open(pdf_path) as pdf:
	# 讀取所有內(nèi)容
	for page in pdf.pages:
		print(page.extract_text())

# 讀取第一頁的文字內(nèi)容
# page = pdf.pages[0]
# print(page.extract_text())

import pdfplumber
pdf_path = r"D:\自動化\pdf\道德經(jīng).pdf"
with pdfplumber.open(pdf_path) as pdf:
	# 獲取第2頁數(shù)據(jù)
	page = pdf.pages[1]
	# 獲取第2頁的第一個表格的內(nèi)容
	table = page.extract_table()
	print(type(table), table)
	
	# 獲取第2頁所有表格的內(nèi)容
	tables = page.extract_tables()
	print(type(tables), tables)

from PyPDF2 import PdfFileReader, PdfFileWriter

pdf_path = r"D:\自動化\pdf\道德經(jīng).pdf"
sava_path = r"D:\自動化\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))

# 添加密碼
pdf_writer.encrypt("mima")

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

from PyPDF2 import PdfFileReader, PdfFileWriter

pdf_path = r"D:\自動化\pdf\加密后.pdf"
sava_path = r"D:\自動化\pdf\解密后.pdf"

pdf_reader = PdfFileReader(pdf_path)

# 利用密碼解密
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)