使用python讀取文件，其中pdf、docx、pptx可以直接讀，.ppt和.doc文件不能直接讀，需要轉(zhuǎn)換成.pptx和.docx文件，并且需要區(qū)分系統(tǒng)
如果是linux系統(tǒng)，請(qǐng)先安裝組件

#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代碼如下：文章來(lái)源地址http://www.zghlxwxcb.cn/news/detail-668601.html

import os


def read_pptx(fp):
    import pptx
    prs = pptx.Presentation(fp)
    for i, slide in enumerate(prs.slides):
        # if i == 1:  在這里可以指定提取ppt的具體頁(yè)數(shù)
        for shape in slide.shapes:
            if shape.has_text_frame:
                text_frame = shape.text_frame
                print(str(i) + '頁(yè)：' + 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("段落數(shù):" + str(len(file.paragraphs)))  # 段落數(shù)為13，每個(gè)回車(chē)隔離一段
    # 輸出每一段的內(nèi)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("文件后綴：" + file_extension)
if file_extension == '.pptx':
    print("讀取pptx文件")
    read_pptx(file_path)
elif file_extension == '.ppt':
    print("讀取ppt文件")
    read_ppt(file_path)
elif file_extension == ".docx":
    print("讀取docx文件")
    read_docx(file_path)
elif file_extension == ".doc":
    print("讀取doc文件")
    read_doc(file_path)
elif file_extension == ".pdf":
    print("讀取pdf文件")
    read_pdf(file_path)

到了這里，關(guān)于python讀取pdf、doc、docx、ppt、pptx文件內(nèi)容的文章就介紹完了。如果您還想了解更多內(nèi)容，請(qǐng)?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！