from win32com.client import gencache
from win32com.client import constants, gencache
def createPdf(wordPath, pdfPath):
    """
    word轉(zhuǎn)pdf
    :param wordPath: word文件路徑
    :param pdfPath:  生成pdf文件路徑
    """
    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)
createPdf('D:\桌面\論文閱讀筆記.docx','D:\桌面\論文閱讀筆記.pdf')

# Import Module
from win32com import client
# Open Microsoft Excel
excel = client.Dispatch("Excel.Application")
# Read Excel File
sheets = excel.Workbooks.Open('F:\書籍借閱信息.xlsx')
work_sheets = sheets.Worksheets[0]
# Convert into PDF File
work_sheets.ExportAsFixedFormat(0, 'F:\書籍借閱信息.pdf')
# 關(guān)閉服務(wù)
excel.Quit()

# 1). 導(dǎo)入需要的模塊(打開應(yīng)用程序的模塊)
import win32com.client
import os
def ppt2pdf(filename, output_filename):
    """
    PPT文件導(dǎo)出為pdf格式
    :param filename: PPT文件的名稱
    :param output_filename: 導(dǎo)出的pdf文件的名稱
    :return:
    """
    # 2). 打開PPT程序
    ppt_app = win32com.client.Dispatch('PowerPoint.Application')
    # ppt_app.Visible = True  # 程序操作應(yīng)用程序的過程是否可視化
    # 3). 通過PPT的應(yīng)用程序打開指定的PPT文件
    # filename = "C:/Users/Administrator/Desktop/PPT辦公自動化/ppt/PPT素材1.pptx"
    # output_filename = "C:/Users/Administrator/Desktop/PPT辦公自動化/ppt/PPT素材1.pdf"
    ppt = ppt_app.Presentations.Open(filename)
    # 4). 打開的PPT另存為pdf文件。17數(shù)字是ppt轉(zhuǎn)圖片，32數(shù)字是ppt轉(zhuǎn)pdf。
    ppt.SaveAs(output_filename, 32)
    print("導(dǎo)出成pdf格式成功!!!")
    # 退出PPT程序
    ppt_app.Quit()
# 要處理的目錄名稱
dirname = 'D:\桌面\智能算法設(shè)計與實現(xiàn)'
# 列出指定目錄的內(nèi)容
filenames = os.listdir(dirname)
# for循環(huán)依次訪問指定目錄的所有文件名
for filename in filenames:
    # 判斷文件的類型，對所有的ppt文件進行處理(ppt文件以ppt或者pptx結(jié)尾的)
    if filename.endswith('ppt') or filename.endswith('pptx'):
        # print(filename)           # PPT素材1.pptx -> PPT素材1.pdf
        # 將filename以.進行分割，返回2個信息，文件的名稱和文件的后綴名
        base, ext = filename.split('.')  # base=PPT素材1 ext=pdf
        new_name = base + '.pdf'         # PPT素材1.pdf
        # ppt文件的完整位置: C:/Users/Administrator/Desktop/PPT辦公自動化/ppt/PPT素材1.pptx
        filename = dirname + '/' + filename
        # pdf文件的完整位置: C:/Users/Administrator/Desktop/PPT辦公自動化/ppt/PPT素材1.pdf
        output_filename = dirname + '/' + new_name
        # 將ppt轉(zhuǎn)成pdf文件
        ppt2pdf(filename, output_filename)

from PIL import Image
import os
# 防止字符串亂碼
os.environ['NLS_LANG'] = 'SIMPLIFIED CHINESE_CHINA.UTF8'
def pic2pdf(img_path, pdf_path):
    file_list = os.listdir(img_path)
    for x in file_list:
        if "jpg" in x or 'png' in x or 'jpeg' in x:
            pdf_name = x.split('.')[0]
            im1 = Image.open(os.path.join(img_path, x))
            im1.save(pdf_path + pdf_name + '.pdf', "PDF", resolution=100.0)
if __name__ == '__main__':
    # 待轉(zhuǎn)換圖像路徑
    img_path = r"D:\桌面\\"
    # 轉(zhuǎn)換后的pdf存放路徑
    pdf_path = r'D:\桌面\\'
    pic2pdf(img_path=img_path, pdf_path=pdf_path)

from pdf2docx import Converter
pdf_file = r'D:\桌面\論文閱讀筆記.pdf'
docx_file = r'D:\桌面\論文閱讀筆記.docx'
cv = Converter(pdf_file)
cv.convert(docx_file, start=0, end=None)
cv.close()

from pdf2image import convert_from_path
pages = convert_from_path('D:\桌面\論文閱讀筆記.pdf', 500)
# 保存
for page in pages:
    page.save('D:\桌面\論文閱讀筆記.jpg', 'JPEG')
# 多圖保存
for index, img in enumerate(pages):
    img.save('E:\識別\page_%s.jpg' % (index+1))

import pandas as pd
data = pd.read_csv('F:/train.csv',index_col=0)
data.to_excel('F:/train.xlsx',encoding='utf-8')

import pandas as pd
data = pd.read_excel('F:/train.xlsx',index_col=0)
data.to_csv('F:/train.csv',encoding='utf-8')