Python中用PyPDF2拆分pdf提取页面

<p style="line-height: 1.75em;"><span style="font-family: 微软雅黑, "Microsoft YaHei";">pip install PyPDF2<br></span></p>

<p style="line-height: 1.75em;"><span style="font-family: 微软雅黑, "Microsoft YaHei";">from PyPDF2 import PdfFileReader, PdfFileWriter

def split_pdf(filename, result, start=0, end=None):

    """从filename中提取[start,end)之间的页码内容保存为result"""

    # 打开原始 pdf 文件

    pdf_src = PdfFileReader(filename)

    if end is None:

        # 获取页数

        end = pdf_src.getNumPages()

    with open(result, "wb") as fp:

        # 创建空白pdf文件

        pdf = PdfFileWriter()

        # 提取页面内容，写入空白文件

        for num in range(start, end):

            pdf.addPage(pdf_src.getPage(num))

        # 写入结果pdf

        pdf.write(fp)

fn = r"G:\a001\第九天.pdf"

split_pdf(fn, "1.pdf", 0, 3)

split_pdf(fn, "2.pdf", 1, 3)

split_pdf(fn, "3.pdf", 2, 3)<br></span></p>

<p style="line-height: 1.75em;"><span style="font-family: 微软雅黑, "Microsoft YaHei";">Traceback (most recent call last):

  File "G:/a001/pdf.py", line 22, insplit_pdf(fn, "1.pdf", 0, 3)

  File "G:/a001/pdf.py", line 7, in split_pdf

    pdf_src = PdfFileReader(filename)

  File "E:\project_luffy\luffy\lib\site-packages\PyPDF2\pdf.py", line 1084, in __init__

    self.read(stream)

  File "E:\project_luffy\luffy\lib\site-packages\PyPDF2\pdf.py", line 1901, in read

    raise utils.PdfReadError("Could not find xref table at specified location")

PyPDF2.utils.PdfReadError: Could not find xref table at specified location<br></span></p>

<p style="line-height: 1.75em;"><span style="font-family: 微软雅黑, "Microsoft YaHei";">PdfReadWarning: Xref table not zero-indexed. ID numbers for objects will be corrected. [pdf.py:1736]<br></span></p>

<p style="line-height: 1.75em;"><span style="font-family: 微软雅黑, "Microsoft YaHei";">import sys

if not sys.warnoptions:

    import warnings

    warnings.simplefilter("ignore")<br></span></p>