处理 PDF 和 Word 文档

书到用时方恨少、事非经过不知难。——陆游

PDF 文档需要第三方类库

pip install PyPDF2

使用

使用

PyPDF2 没有办法从文档中提取图像,图表或者其他媒体,它可以提取文本,并将文本返回 Python 字符串,加密的 PDF 不能支持

PyPDF2 包含了 PdfFileReader, PdfFileWriter, PdfFileMerger,PageObject

从 PDF 读取文件

• PdfFileReader,getPage(0),extractText(),close()

from PyPDF2 import PdfFileReader, PdfFileWriter

readFile = './测试.pdf'

writeFile = './写入.pdf'


def extract_information(pdf_path):
    with open(pdf_path, 'rb') as f:
        pdf = PdfFileReader(f)
        information = pdf.getDocumentInfo()
        # print(information)  # 获取信息
        # print(pdf.numPages)  # 获取所有页码
        Page = pdf.getPage(0)  # 获取到页面
        Page_content = Page.extractText()  # 获取页面的内容
        print(Page_content)  # 这样就获取到了内容


extract_information(readFile)

处理解密 PDF

• isEncrypted 判断有没有密码

• decrypt 输入密码

from PyPDF2 import PdfFileReader, PdfFileWriter

readFile = './测试.pdf'

writeFile = './写入.pdf'

def extract_information(pdf_path):
with open(pdf_path, 'rb') as f:
pdf = PdfFileReader(f)
print(pdf.isEncrypted) # 要是 True 就代表加密,False 就代表不加密 # 如果要是 True
passwordflag = pdf.decrypt('密码') # decrypt 就是输入的密码
if passwordflag == 0: # 0 就表示输入错误 1 就表示输入正确
print("密码输入失败")
else:
print("密码输入对了")

extract_information(readFile)

合并 PDF

from PyPDF2 import PdfFileReader, PdfFileWriter


def merge_pdfs(paths, output):
    pdf_writer = PdfFileWriter()
    for path in paths:
        pdf_reader = PdfFileReader(path)
        for page in range(pdf_reader.getNumPages()):
                 # 将每页添加到writer对象
            pdf_writer.addPage(pdf_reader.getPage(page))
            # 写入合并的pdf
            with open(output, 'wb') as out:
                pdf_writer.write(out)


if __name__ == '__main__':
    paths = ['测试.pdf', '测试2.pdf']
    merge_pdfs(paths, output='merged.pdf')

拆分 PDF

• 拆分

from PyPDF2 import PdfFileReader, PdfFileWriter


def split(path, name_of_split):
    pdf = PdfFileReader(path)
    for page in range(pdf.getNumPages()):
        pdf_writer = PdfFileWriter()
        pdf_writer.addPage(pdf.getPage(page))
        output = f'{name_of_split}{page}.pdf'
    with open(output, 'wb') as output_pdf:
        pdf_writer.write(output_pdf)


if __name__ == '__main__':
    path = './merged.pdf'
    split(path, 'jupyter_page')
else:
    print("失败了")