python - "Not implemented"使用pywin32控制Adobe Acrobat时出现异常

Question

我使用 pywin32 在 python 中编写了一个脚本，用于将 pdf 文件保存为文本，直到最近都运行良好。我在 Excel 中使用类似的方法。代码如下:

def __pdf2Txt(self, pdf, fileformat="com.adobe.acrobat.accesstext"):
    outputLoc = os.path.dirname(pdf)
    outputLoc = os.path.join(outputLoc, os.path.splitext(os.path.basename(pdf))[0] + '.txt')

    try:
        win32com.client.gencache.EnsureModule('{E64169B3-3592-47d2-816E-602C5C13F328}', 0, 1, 1)
        adobe = win32com.client.DispatchEx('AcroExch.App')
        pdDoc = win32com.client.DispatchEx('AcroExch.PDDoc')
        pdDoc.Open(pdf)
        jObject = pdDoc.GetJSObject()
        jObject.SaveAs(outputLoc, "com.adobe.acrobat.accesstext")
    except:
        traceback.print_exc()
        return False
    finally:
        del jObject
        pdDoc.Close()
        del pdDoc
        adobe.Exit()
        del adobe

但是这段代码突然停止工作，我得到以下输出:

Traceback (most recent call last):
  File "C:\Documents and Settings\ablishen\workspace\HooverKeyCreator\src\HooverKeyCreator.py", line 38, in __pdf2Txt
    jObject.SaveAs(outputLoc, "com.adobe.acrobat.accesstext")
  File "C:\Python27\lib\site-packages\win32com\client\dynamic.py", line 505, in __getattr__
    ret = self._oleobj_.Invoke(retEntry.dispid,0,invoke_type,1)
com_error: (-2147467263, 'Not implemented', None, None)
False

我有类似的用 VB 编写的代码可以正常工作，所以我猜测它与 COM 接口(interface)没有正确绑定(bind)到适当的函数有关？ (我的 COM 知识是零散的)。

Answer 1

Blish, this thread掌握您正在寻找的解决方案的关键:https://mail.python.org/pipermail/python-win32/2002-March/000260.html

我承认上面的帖子不是最容易找到的(可能是因为谷歌根据内容的年龄给它评分很低？)。

具体来说，申请 this piece建议将使事情为您运行:https://mail.python.org/pipermail/python-win32/2002-March/000265.html

作为引用，不需要您手动修补 dynamic.py 的完整代码片段(片段应该开箱即用):

# gets all files under ROOT_INPUT_PATH with FILE_EXTENSION and tries to extract text from them into ROOT_OUTPUT_PATH with same filename as the input file but with INPUT_FILE_EXTENSION replaced by OUTPUT_FILE_EXTENSION
from win32com.client import Dispatch
from win32com.client.dynamic import ERRORS_BAD_CONTEXT

import winerror

# try importing scandir and if found, use it as it's a few magnitudes of an order faster than stock os.walk
try:
    from scandir import walk
except ImportError:
    from os import walk

import fnmatch

import sys
import os

ROOT_INPUT_PATH = None
ROOT_OUTPUT_PATH = None
INPUT_FILE_EXTENSION = "*.pdf"
OUTPUT_FILE_EXTENSION = ".txt"

def acrobat_extract_text(f_path, f_path_out, f_basename, f_ext):
    avDoc = Dispatch("AcroExch.AVDoc") # Connect to Adobe Acrobat

    # Open the input file (as a pdf)
    ret = avDoc.Open(f_path, f_path)
    assert(ret) # FIXME: Documentation says "-1 if the file was opened successfully, 0 otherwise", but this is a bool in practise?

    pdDoc = avDoc.GetPDDoc()

    dst = os.path.join(f_path_out, ''.join((f_basename, f_ext)))

    # Adobe documentation says "For that reason, you must rely on the documentation to know what functionality is available through the JSObject interface. For details, see the JavaScript for Acrobat API Reference"
    jsObject = pdDoc.GetJSObject()

    # Here you can save as many other types by using, for instance: "com.adobe.acrobat.xml"
    jsObject.SaveAs(dst, "com.adobe.acrobat.accesstext")

    pdDoc.Close()
    avDoc.Close(True) # We want this to close Acrobat, as otherwise Acrobat is going to refuse processing any further files after a certain threshold of open files are reached (for example 50 PDFs)
    del pdDoc

if __name__ == "__main__":
    assert(5 == len(sys.argv)), sys.argv # <script name>, <script_file_input_path>, <script_file_input_extension>, <script_file_output_path>, <script_file_output_extension>

    #$ python get.txt.from.multiple.pdf.py 'C:\input' '*.pdf' 'C:\output' '.txt'

    ROOT_INPUT_PATH = sys.argv[1]
    INPUT_FILE_EXTENSION = sys.argv[2]
    ROOT_OUTPUT_PATH = sys.argv[3]
    OUTPUT_FILE_EXTENSION = sys.argv[4]

    # tuples are of schema (path_to_file, filename)
    matching_files = ((os.path.join(_root, filename), os.path.splitext(filename)[0]) for _root, _dirs, _files in walk(ROOT_INPUT_PATH) for filename in fnmatch.filter(_files, INPUT_FILE_EXTENSION))

    # patch ERRORS_BAD_CONTEXT as per https://mail.python.org/pipermail/python-win32/2002-March/000265.html
    global ERRORS_BAD_CONTEXT
    ERRORS_BAD_CONTEXT.append(winerror.E_NOTIMPL)

    for filename_with_path, filename_without_extension in matching_files:
        print "Processing '{}'".format(filename_without_extension)
        acrobat_extract_text(filename_with_path, ROOT_OUTPUT_PATH, filename_without_extension, OUTPUT_FILE_EXTENSION)

我已经在 WinPython x64 2.7.6.3、Acrobat X Pro 上测试过了