Merge pull request parita#6 from sks147/master

Parita Pooj · web-flow · commit 20382603660c · 2016-10-30T23:52:42.000-04:00
Added new random subroutine which can extract text from ms-word file
diff --git a/random-snippets/extract_text_from_word_file.py b/random-snippets/extract_text_from_word_file.py
@@ -0,0 +1,20 @@
+#You can extract the text content from each Microsoft Word document in a directory
+#tree on Windows into a corresponding text file.
+#With the PyWin32 extension,we can access Word itself,through COM,to perform
+#the conversion:
+import fnmatch, os, sys, win32com.client
+wordapp = win32com.client.gencache.EnsureDispatch("Word.Application")
+try:
+    for path, dirs, files in os.walk(sys.argv[1]):
+        for filename in files:
+        if not fnmatch.fnmatch(filename, '*.doc'): continue
+        doc = os.path.abspath(os.path.join(path, filename))
+        print "processing %s" % doc
+        wordapp.Documents.Open(doc)
+        docastxt = doc[:-3] + 'txt'
+        wordapp.ActiveDocument.SaveAs(docastxt,
+            FileFormat=win32com.client.constants.wdFormatText)
+        wordapp.ActiveDocument.Close( )
+finally:
+    # ensure Word is properly shut down even if we get an exception
+    wordapp.Quit( )
