Python办公自动化【Word转换PDF、PDF读取内容、PDF合并文件、PDF拆分文件、PDF加密文件、PPT基本操作-增加幻灯片、增加内容】(六)-全面详解（学习总结---从入门到深化）

from win32com.client import gencache
from win32com.client import constants,gencache
def createPdf(wordPath, pdfPath):
  """
 word转pdf
 :param wordPath: word文件路径
 :param pdfPath: 生成pdf文件路径
 """
  word = gencache.EnsureDispatch('Word.Application')
  doc = word.Documents.Open(wordPath,ReadOnly=1)
  doc.ExportAsFixedFormat(pdfPath,
 constants.wdExportFormatPDF,
 Item=constants.wdExportDocumentWithMarkup,
 CreateBookmarks=constants.wdExportCreateHeadingBookmarks)
  word.Quit(constants.wdDoNotSaveChanges)
if __name__ == "__main__":
  # 路径填写绝对路径
  createPdf(
 r'D:\code\python\auto_code_word\base_data\原数据.docx',r'D:\code\python\auto_code_word\create_data
\10_word转换成pdf.pdf'
 )
  # 命令要安装pywin32模块,命令：pip install pywin32

#pip install pypdf2
from PyPDF2 import PdfFileReader
def read_pdf1():
  # 打开文件
  with open('./base_data/10_word转换成pdf.pdf','rb') as f:
    # 将打开的文件传递给Reader对象
    reader = PdfFileReader(f)
    # 获取页面的总页数
    number = reader.getNumPages()
    print(number)
    # 获取单页
    page = reader.getPage(0)
    # 提取文本
    info = page.extractText()
    print(info)
# pip install pdfplumber
def read_pdf2():
  import pdfplumber
  # 打开文件
  with pdfplumber.open('./base_data/10_word转换成pdf.pdf') as f:
    # 获取数据
    print(f.pages)
    for p in f.pages:
      print(p.extract_text())
if __name__ =='__main__':
  # read_pdf1()
  read_pdf2()

def merger_file(*m_path):
  from PyPDF2 import PdfFileReader,PdfFileWriter
  # 创建一个写入的对象
  writer = PdfFileWriter()
  # 读数据
  for path in m_path:
    # 创建reader
    reader = PdfFileReader(open(path,'rb'))
    # 读取页面数据
    for p in reader.pages:
      # 写新的pdf
      writer.addPage(p)
  # 保存
  with open('./create_data/02_合并pdf.pdf','wb') as f:
    writer.write(f)
if __name__ =='__main__':
  path = r'.\base_data\10_word转换成pdf.pdf'
  merger_file(path,path,path)

from PyPDF2 import
PdfFileReader,PdfFileWriter
def chai_pdf(path):
  # 读取文件
  reader = PdfFileReader(open(path,'rb'))
  # 获取页面数据
  for i,p in enumerate(reader.pages):
    writer = PdfFileWriter()
    writer.addPage(p)
    # 保存新pdf文件
    with open(f'./create_data/03_拆分pdf_{i}.pdf','wb') as f:
      writer.write(f)
if __name__ =='__main__':
  path = './create_data/02_合并pdf.pdf'
  chai_pdf(path)

from asyncore import write
from PyPDF2 import PdfFileReader,PdfFileWriter
def jia_mi(path):
  # 读取数据
  reader = PdfFileReader(open(path,'rb'))
  # 创建写Pdf的对象
  writer = PdfFileWriter()
  # 写入密码
  writer.encrypt('123')
  # 把内容复制pdf的writer中
  for p in reader.pages:
    writer.addPage(p)
  # 保存数据
  with open('./create_data/04_加密pdf.pdf','wb') as f:
    writer.write(f)
if __name__ =='__main__':
  path = r'base_data\10_word转换成pdf.pdf'
  jia_mi(path)

# pip install python-pptx
def create_ppt():
  from pptx import Presentation
  # 创建ppt
  ppt = Presentation()
  # 增加幻灯片
 ppt.slides.add_slide(ppt.slide_layouts[0])
 ppt.slides.add_slide(ppt.slide_layouts[1])
 ppt.slides.add_slide(ppt.slide_layouts[3])
 ppt.slides.add_slide(ppt.slide_layouts[6])
  # 保存
  ppt.save('./create_data/01_创建PPT.pptx')
if __name__ == '__main__':
  create_ppt()

from pptx import Presentation
from pptx.util import Pt
def create_info():
  # 创建一个ppt
  ppt = Presentation()
  # 添加内容
  # 增加第1个页面
  slide = ppt.slides.add_slide(ppt.slide_layouts[1])
  # 获取标题
  title = slide.shapes.title
  title.text = 'This is Python Title'
  # 获取内容框
  content = slide.placeholders[1]
  content.text = 'Content Info'
  # 增加第2个页面
  slide2 = ppt.slides.add_slide(ppt.slide_layouts[1])
  # 获取内容占位框
  content2 = slide2.placeholders[1]
  # 获取内容frame框对象
  tf = content2.text_frame
  # 增加段落内容
  par = tf.add_paragraph()
  # 设置段落内容
  par.text = '1级内容'
  # 设置内容等级
  par.level = 1
  par2 = tf.add_paragraph()
  par2.text = '2级内容'
  par2.level = 2
  par3 = tf.add_paragraph()
  par3.text = '3级内容'
  par3.level = 3
  # 增加第3个页面
  slide3 = ppt.slides.add_slide(ppt.slide_layouts[6])
  left = top = right = bottom = Pt(200)
  # 增加文本框
  tb = slide3.shapes.add_textbox(left,top,right,bottom)
  # 增加内容
  tf4 = tb.text_frame
  par4 = tf4.add_paragraph()
  par4.text = '1级内容'
  par4.font.bold = True
  par4.font.size = Pt(30)
  # 保存ppt
  ppt.save('./create_data/02_增加内容.pptx')
if __name__ =='__main__':
  create_info()