DZone Snippets: com code

Find & Replace in Word Document with Ruby

timmorgan (Tim Morgan) — Mon, 12 Nov 2007 14:48:47 GMT

I use this to open a "template" (really just a plain Word document with [text to replace] inside), do the substitutions, and save as a new filename.



require 'win32ole'



word = WIN32OLE.new('Word.Application')

#word.Visible = true # uncomment if you want to see it happen

doc = word.Documents.Open('c:\file_to_open.doc')

{

  'name' => 'Tim Morgan',

  'date' => Date.today.strftime('%B %d, %Y'),

  ...

}.each do |key, value|

  word.Selection.HomeKey(unit=6) # start at beginning

  find = word.Selection.Find

  find.Text = "[#{key}]" # text must be in square brackets

  while word.Selection.Find.Execute

    word.Selection.TypeText(text=value)

  end

end

doc.SaveAs('c:\output_file.doc')

doc.Close

Script Word from Python

timmorgan (Tim Morgan) — Tue, 16 May 2006 00:10:53 GMT

A quick and dirty class for working with Word via COM in Python. By far, not all of the power of Word is available here, but it's a good start for simple tasks.



from win32com.client import constants, Dispatch



import pythoncom



wdStory = 6



class WordDocument(object):

  """

  Some convenience methods for Word documents accessed

  through COM.

  """

  

  def __init__(self, visible=False):

    self.app = Dispatch("Word.Application")

    self.app.Visible = visible

  

  def new(self, filename=None):

    """

    Create a new Word document. If 'filename' specified,

    use the file as a template.

    """

    self.app.Documents.Add(filename)

  

  def open(self, filename):

    """

    Open an existing Word document for editing.

    """

    self.app.Documents.Open(filename)

  

  def save(self, filename=None):

    """

    Save the active document. If 'filename' is given,

    do a Save As.

    """

    if filename:

      self.app.ActiveDocument.SaveAs(filename)

    else:

      self.app.ActiveDocument.Save()

  

  def save_as(self, filename):

    return self.save(filename)

  

  def print_out(self):

    """

    Print the active document.

    """

    self.app.Application.PrintOut()

  

  def close(self):

    """

    Close the active document.

    """

    self.app.ActiveDocument.Close()

  

  def quit(self):

    """

    Quit Word.

    """

    return self.app.Quit()

  

  def find_and_replace(self, find_str, replace_str):

    """

    Find all occurances of 'find_str' and replace with 'replace_str'

    in the active document.

    """

    self.app.Selection.HomeKey(Unit=wdStory)

    find = self.app.Selection.Find

    find.Text = find_str

    while self.app.Selection.Find.Execute():

      self.app.Selection.TypeText(Text=replace_str)

Script Excel from Python

timmorgan (Tim Morgan) — Tue, 16 May 2006 00:07:51 GMT

A quick and dirty class for working with Excel via COM in Python. By far, not all of the power of Excel is available here, but it's a good start for simple tasks.



from win32com.client import constants, Dispatch

import pythoncom

import os



borderTop = 3

borderBottom = 4

borderLeft = 1

borderRight = 2

borderSolid = 1

borderDashed = 2

borderDotted = 3

colorBlack = 1

directionUp = -4162

directionDown = -4121

directionLeft = -4131

directionRight = -4152



class ExcelDocument(object):

  """

  Some convenience methods for Excel documents accessed

  through COM.

  """

  

  def __init__(self, visible=False):

    self.app = Dispatch("Excel.Application")

    self.app.Visible = visible

    self.sheet = 1

  

  def new(self, filename=None):

    """

    Create a new Excel workbook. If 'filename' specified,

    use the file as a template.

    """

    self.app.Workbooks.Add(filename)

  

  def open(self, filename):

    """

    Open an existing Excel workbook for editing.

    """

    self.app.Workbooks.Open(filename)

  

  def set_sheet(self, sheet):

    """

    Set the active worksheet.

    """

    self.sheet = sheet

  

  def get_range(self, range):

    """

    Get a range object for the specified range or single cell.

    """

    return self.app.ActiveWorkbook.Sheets(self.sheet).Range(range)

  

  def set_value(self, cell, value=''):

    """

    Set the value of 'cell' to 'value'.

    """

    self.get_range(cell).Value = value

  

  def get_value(self, cell):

    """

    Get the value of 'cell'.

    """

    value = self.get_range(cell).Value

    if isinstance(value, tuple):

      value = [v[0] for v in value]

    return value

  

  def set_border(self, range, side, line_style=borderSolid, color=colorBlack):

    """

    Set a border on the specified range of cells or single cell.

    'range' = range of cells or single cell

    'side' = one of borderTop, borderBottom, borderLeft, borderRight

    'line_style' = one of borderSolid, borderDashed, borderDotted, others?

    'color' = one of colorBlack, others?

    """

    range = self.get_range(range).Borders(side)

    range.LineStyle = line_style

    range.Color = color

  

  def sort(self, range, key_cell):

    """

    Sort the specified 'range' of the activeworksheet by the

    specified 'key_cell'.

    """

    range.Sort(Key1=self.get_range(key_cell), Order1=1, Header=0, OrderCustom=1, MatchCase=False, Orientation=1)

  

  def hide_row(self, row, hide=True):

    """

    Hide the specified 'row'.

    Specify hide=False to show the row.

    """

    self.get_range('a%s' % row).EntireRow.Hidden = hide

  

  def hide_column(self, column, hide=True):

    """

    Hide the specified 'column'.

    Specify hide=False to show the column.

    """

    self.get_range('%s1' % column).EntireColumn.Hidden = hide

  

  def delete_row(self, row, shift=directionUp):

    """

    Delete the entire 'row'.

    """

    self.get_range('a%s' % row).EntireRow.Delete(Shift=shift)

  

  def delete_column(self, column, shift=directionLeft):

    """

    Delete the entire 'column'.

    """

    self.get_range('%s1' % column).EntireColumn.Delete(Shift=shift)

    

  def fit_column(self, column):

    """

    Resize the specified 'column' to fit all its contents.

    """

    self.get_range('%s1' % column).EntireColumn.AutoFit()

  

  def save(self):

    """

    Save the active workbook.

    """

    self.app.ActiveWorkbook.Save()

  

  def save_as(self, filename, delete_existing=False):

    """

    Save the active workbook as a different filename.

    If 'delete_existing' is specified and the file already

    exists, it will be deleted before saving.

    """

    if delete_existing and os.path.exists(filename):

      os.remove(filename)

    self.app.ActiveWorkbook.SaveAs(filename)

  

  def print_out(self):

    """

    Print the active workbook.

    """

    self.app.Application.PrintOut()

  

  def close(self):

    """

    Close the active workbook.

    """

    self.app.ActiveWorkbook.Close()

  

  def quit(self):

    """

    Quit Excel.

    """

    return self.app.Quit()

Mass conversion from word to HTML

korakot (Korakot Chaovavanich) — Tue, 28 Jun 2005 00:02:06 GMT

I got 1000 word files. Each contains 1 main image and some decorations.
(This is actually a big book scanned into 1-file-per-page format)
I need to extract all the images. What do I do?

Python can do some automation using COM. (or something like that)



import pythoncom, win32com.client



app = win32com.client.gencache.EnsureDispatch("Word.Application")



doc = 'C:\\lang\\try\\bdham\\p1'

app.Documents.Open(doc + '.doc')

app.ActiveDocument.SaveAs(doc + '.html', FileFormat=win32com.client.constants.wdFormatHTML)

app.ActiveDocument.Close()

# now repeat with p2, p3, etc.

Actually, I should put it in a loop. But this non-loop version
is easier to read and remember.