Created
June 4, 2020 06:17
-
-
Save rdapaz/9cc34f7b6341f1a244b6dae7ee9ea837 to your computer and use it in GitHub Desktop.
MS Word - Search and Replace
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import win32com.client as c | |
import pprint | |
import re | |
class Util: | |
@staticmethod | |
def pretty_printer(o): | |
pp = pprint.PrettyPrinter(indent=4) | |
pp.pprint(o) | |
class WordDocument: | |
def __init__(self, path): | |
self.path = path | |
self.wdApp = c.gencache.EnsureDispatch('Word.Application') | |
self.wdApp.Visible = True | |
self.doc = self.wdApp.Documents.Open(path) | |
self.txt = (self.doc.Content).Text.encode('ascii', errors='ignore') | |
self.txt = str(self.txt) | |
def getAllText(self, interestingText): | |
rex = re.compile(r"{}".format(interestingText)) | |
entries = set() | |
for entry in rex.findall(self.txt): | |
entries.add(entry) | |
Util.pretty_printer(entries) | |
for entry in sorted(list(entries)): | |
print(entry) | |
def searchAndReplace(self): | |
subs = { | |
"Old": "New" | |
} | |
WDREPLACEALL = 2 | |
for k, v in subs.items(): | |
rge = self.doc.Content | |
rge.Find.Execute(FindText=k, ReplaceWith=subs[k], Replace=WDREPLACEALL) | |
if __name__ == '__main__': | |
path = r'<doc.docx' | |
doc = WordDocument(path) | |
# doc.getAllText(r'V(?:NGU|OKH)\w+\d{2}') | |
doc.searchAndReplace() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment