python读取pdf、doc、docx、ppt、pptx文件内容

使用python读取文件，其中pdf、docx、pptx可以直接读，.ppt和.doc文件不能直接读，需要转换成.pptx和.docx文件，并且需要区分系统

如果是linux系统，请先安装组件

bash 复制代码

#doc2docx
yum install -y libreoffice-headless
yum install -y libreoffice-writer

# ppt2pptx
yum install epel-release -y
yum install libgdiplus -y
pip3 install aspose.slides

python代码如下：

python 复制代码

import os


def read_pptx(fp):
    import pptx
    prs = pptx.Presentation(fp)
    for i, slide in enumerate(prs.slides):
        # if i == 1:  在这里可以指定提取ppt的具体页数
        for shape in slide.shapes:
            if shape.has_text_frame:
                text_frame = shape.text_frame
                print(str(i) + '页：' + text_frame.text)


def read_ppt(fp):
    import platform
    os_type = platform.system()
    if os_type == "Windows":
        import win32com.client as wc
        powerpoint = wc.Dispatch("PowerPoint.Application")
        wc.gencache.EnsureDispatch("PowerPoint.Application")
        powerpoint.Visible = 1
        ppt = powerpoint.Presentations.Open(fp)
        ppt.SaveAs(fp+"x")
        powerpoint.Quit()
    elif os_type == "Linux":
        import aspose.slides as slides
        with slides.Presentation(fp) as presentation:
            presentation.save(fp+"x", slides.export.SaveFormat.PPTX)
    read_pptx(fp+"x")

def read_docx(fp):
    import docx
    file = docx.Document(fp)
    print("段落数:" + str(len(file.paragraphs)))  # 段落数为13，每个回车隔离一段
    # 输出每一段的内容
    for para in file.paragraphs:
        print(para.text)

def read_doc(fp):
    import platform
    os_type = platform.system()
    if os_type == "Windows":
        import doc2docx
        doc2docx.convert(fp,fp+"x")
    elif os_type == "Linux":
        import subprocess
        subprocess.check_output(["soffice", "--headless", "---invisible", "--convert-to", "docx", fp, "--outdir", fp+"x"])
    read_docx(fp + "x")


def read_pdf(fp):
    import pdfplumber
    pdfFile = open(fp,"rb")
    pdf = pdfplumber.open(pdfFile)
    for page in pdf.pages:
        text = page.extract_text()
        print(text)


# file_path = "*.pptx"
file_path = "*.ppt"
# file_path = "*.docx"
# file_path = "*.doc"
# file_path = "*.pdf"
file_extension = os.path.splitext(file_path)[-1].lower()
print("文件后缀：" + file_extension)
if file_extension == '.pptx':
    print("读取pptx文件")
    read_pptx(file_path)
elif file_extension == '.ppt':
    print("读取ppt文件")
    read_ppt(file_path)
elif file_extension == ".docx":
    print("读取docx文件")
    read_docx(file_path)
elif file_extension == ".doc":
    print("读取doc文件")
    read_doc(file_path)
elif file_extension == ".pdf":
    print("读取pdf文件")
    read_pdf(file_path)