python操作pdf文件

安装模块

pip install pdfplumber
pip install PyPDF2
pip install pypwin32

pdf 文件读取

"""
path: pdf的文件路径
pdfplumber.open(path): 文件打开读取
_pdf.pages： 获取pdf总页数
_pdf.pages[i].extract_text() ： 获取每页的pdf的内容
"""

def get_pdf_content(path):
    _pdf = pdfplumber.open(path)
    pages = len(_pdf.pages)  # _pdf.pages  输出的是列表数据
    all_content = [_pdf.pages[i].extract_text() for i in range(pages)]
    return all_content
    
if __name__ == '__main__':
    data = get_pdf_content('test.pdf')
    print(data[0])

读取pdf中的表格数据

def get_pdf_tables(path):
    _pdf = pdfplumber.open(path)
    pages = len(_pdf.pages)  # _pdf.pages  输出的是列表数据
    all_table = []
    for i in range(pages):
        # 读取每页pdf 中含有表格的数据
        for j in _pdf.pages[i].extract_tables():
            # 获取每页table， 每一行的数据，
            content = [k for k in j if '' not in k]
            all_table.append(content)
    return all_table
        

获取pdf中的table数据， 并写入表格

import pdfplumber
import pandas as pd


def get_pdf_tables(path):
    _pdf = pdfplumber.open(path)
    pages = len(_pdf.pages)  # _pdf.pages  输出的是列表数据
    all_table = []
    for i in range(pages):
        # 读取每页pdf 中含有表格的数据
        for j in _pdf.pages[i].extract_tables():
            # 获取每页table， 每一行的数据，
            content = [k for k in j if '' not in k]
            all_table.append(content)
    return all_table


# 获取pdf 中的表格数据， 并写入pdf数据
def write_to_excel(all_tables):
    writer = pd.ExcelWriter("表格数据.xlsx")
    for index, content in enumerate(all_tables):
        name = "pd_{}".format(index)
        df = pd.DataFrame(content)
        df.to_excel(writer, sheet_name=name, encoding="gbk")
    # 最后保存写入，并释放
    writer.save()
    writer.close()
if __name__ == '__main__':
    data = get_pdf_tables('test.pdf')
    write_to_excel(data)

word转换成pdf

from win32com.client import constants, gencache


def word_to_pdf(word_path, pdf_path):
    """
    word转pdf
    :param word_path: word文件路径
    :param pdf_path:  生成pdf文件路径
    """
    word = gencache.EnsureDispatch('Word.Application')
    doc = word.Documents.Open(word_path, ReadOnly=1)
    doc.ExportAsFixedFormat(pdf_path,
                            constants.wdExportFormatPDF,
                            Item=constants.wdExportDocumentWithMarkup,
                            CreateBookmarks=constants.wdExportCreateHeadingBookmarks)
    word.Quit(constants.wdDoNotSaveChanges)

pdf 添加水印

from PyPDF2 import PdfFileReader, PdfFileWriter


def water_to_file(pdf_path, water_path):
    """
    :param pdf_path:  需要加水印的pdf
    :param water_path: 水印的pdf
    :return: 
    """
    pdf = PdfFileReader(pdf_path)
    water_pdf = PdfFileReader(water_path)
    water = water_pdf.getPage(0)
    writer = PdfFileWriter()
    for i in range(pdf.getNumPages()):
        pdf.getPage(i).mergePage(water)
        writer.addPage(pdf.getPage(i))
    writer.write(open('new.pdf', 'wb'))