使用pywin32控制Adobe Acrobat时出现“未实现”异常

Question

我已经使用 pywin32 在 python 中编写了一个脚本来将 pdf 文件保存为文本，直到最近它工作正常。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，所以我猜它与 COM 接口没有正确绑定到适当的函数有关？ （我的 COM 知识不完整）。

Answer 1

Blish，this thread 掌握着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打分低？）。

具体来说，应用 this piece of 建议会让事情顺利进行：https://mail.python.org/pipermail/python-win32/2002-March/000265.html

作为参考，不需要您手动修补 dynamic.py 的完整代码（sn-p 应该可以立即运行）：

# 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)

我已在 WinPython x64 2.7.6.3、Acrobat X Pro 上对此进行了测试

Answer 2

makepy.py 是 win32com python 包自带的脚本。

为您的安装运行它“连接”python 到 Windows 中的 COM/OLE 对象。以下是我用来与 Excel 对话并在其中做一些事情的一些代码的摘录。此示例获取当前工作簿中工作表 1 的名称。如果出现异常，它会自动运行 makepy：

import win32com;
import win32com.client;
from win32com.client import selecttlb;

def attachExcelCOM():
   makepyExe = r'python C:\Python25\Lib\site-packages\win32com\client\makepy.py';
   typeList = selecttlb.EnumTlbs();
   for tl in typeList:
      if (re.match('^Microsoft.*Excel.*', tl.desc, re.IGNORECASE)):
          makepyCmd = "%s -d \"%s\"" % (makepyExe, tl.desc);
          os.system(makepyCmd);
      # end if
   # end for
# end def

def getSheetName(sheetNum):
   try:
      xl = win32com.client.Dispatch("Excel.Application");
      wb = xl.Workbooks.Item(sheetNum);
   except Exception, detail:
      print 'There was a problem attaching to Excel, refreshing connect config...';
      print Exception, str(detail);
      attachExcelCOM();
      try:
         xl = win32com.client.Dispatch("Excel.Application");
         wb = xl.Workbooks.Item(sheetNum);
      except:
         print 'Could not attach to Excel...';
         sys.exit(-1);
      # end try/except
   # end try/except

   wsName = wb.Name;
   if (wsName == 'PERSONAL.XLS'):
      return( None );
   # end if
   print 'The target worksheet is:';
   print '      ', wsName;
   print 'Is this correct? [Y/N]',;
   answer = string.strip( sys.stdin.readline() );
   answer = answer.upper();
   if (answer != 'Y'):
      print 'Sheet not identified correctly.';
      return(None);
   # end if
   return( (wb, wsName) );
# end def

# -- Main --
sheetInfo = getSheetName(sheetNum);
if (sheetInfo == None):
   print 'Sheet not found';
   sys.exit(-1);
else:
   (wb, wsName) = sheetInfo;
# end if