问题
I need help replacing a string in a word document while keeping the formatting of the entire document.
I'm using python-docx, after reading the documentation, it works with entire paragraphs, so I loose formatting like words that are in bold or italics. Including the text to replace is in bold, and I would like to keep it that way. I'm using this code:
from docx import Document
def replace_string2(filename):
doc = Document(filename)
for p in doc.paragraphs:
if 'Text to find and replace' in p.text:
print 'SEARCH FOUND!!'
text = p.text.replace('Text to find and replace', 'new text')
style = p.style
p.text = text
p.style = style
# doc.save(filename)
doc.save('test.docx')
return 1
So if I implement it and want something like (the paragraph containing the string to be replaced loses its formatting):
This is paragraph 1, and this is a text in bold.
This is paragraph 2, and I will replace old text
The current result is:
This is paragraph 1, and this is a text in bold.
This is paragraph 2, and I will replace new text
回答1:
I posted this question (even though I saw a few identical ones on here), because none of those (to my knowledge) solved the issue. There was one using a oodocx library, which I tried, but did not work. So I found a workaround.
The code is very similar, but the logic is: when I find the paragraph that contains the string I wish to replace, add another loop using runs. (this will only work if the string I wish to replace has the same formatting).
def replace_string(filename):
doc = Document(filename)
for p in doc.paragraphs:
if 'old text' in p.text:
inline = p.runs
# Loop added to work with runs (strings with same style)
for i in range(len(inline)):
if 'old text' in inline[i].text:
text = inline[i].text.replace('old text', 'new text')
inline[i].text = text
print p.text
doc.save('dest1.docx')
return 1
回答2:
This is what works for me to retain the text style when replacing text.
Based on Alo's answer and the fact the search text can be split over several runs, here's what worked for me to replace placeholder text in a template docx file. It checks all the document paragraphs and any table cell contents for the placeholders.
Once the search text is found in a paragraph it loops through it's runs identifying which runs contains the partial text of the search text, after which it inserts the replacement text in the first run then blanks out the remaining search text characters in the remaining runs.
I hope this helps someone. Here's the gist if anyone wants to improve it
Edit:
I have subsequently discovered python-docx-template which allows jinja2 style templating within a docx template. Here's a link to the documentation
python3 python-docx python-docx-template
def docx_replace(doc, data):
paragraphs = list(doc.paragraphs)
for t in doc.tables:
for row in t.rows:
for cell in row.cells:
for paragraph in cell.paragraphs:
paragraphs.append(paragraph)
for p in paragraphs:
for key, val in data.items():
key_name = '${{{}}}'.format(key) # I'm using placeholders in the form ${PlaceholderName}
if key_name in p.text:
inline = p.runs
# Replace strings and retain the same style.
# The text to be replaced can be split over several runs so
# search through, identify which runs need to have text replaced
# then replace the text in those identified
started = False
key_index = 0
# found_runs is a list of (inline index, index of match, length of match)
found_runs = list()
found_all = False
replace_done = False
for i in range(len(inline)):
# case 1: found in single run so short circuit the replace
if key_name in inline[i].text and not started:
found_runs.append((i, inline[i].text.find(key_name), len(key_name)))
text = inline[i].text.replace(key_name, str(val))
inline[i].text = text
replace_done = True
found_all = True
break
if key_name[key_index] not in inline[i].text and not started:
# keep looking ...
continue
# case 2: search for partial text, find first run
if key_name[key_index] in inline[i].text and inline[i].text[-1] in key_name and not started:
# check sequence
start_index = inline[i].text.find(key_name[key_index])
check_length = len(inline[i].text)
for text_index in range(start_index, check_length):
if inline[i].text[text_index] != key_name[key_index]:
# no match so must be false positive
break
if key_index == 0:
started = True
chars_found = check_length - start_index
key_index += chars_found
found_runs.append((i, start_index, chars_found))
if key_index != len(key_name):
continue
else:
# found all chars in key_name
found_all = True
break
# case 2: search for partial text, find subsequent run
if key_name[key_index] in inline[i].text and started and not found_all:
# check sequence
chars_found = 0
check_length = len(inline[i].text)
for text_index in range(0, check_length):
if inline[i].text[text_index] == key_name[key_index]:
key_index += 1
chars_found += 1
else:
break
# no match so must be end
found_runs.append((i, 0, chars_found))
if key_index == len(key_name):
found_all = True
break
if found_all and not replace_done:
for i, item in enumerate(found_runs):
index, start, length = [t for t in item]
if i == 0:
text = inline[index].text.replace(inline[index].text[start:start + length], str(val))
inline[index].text = text
else:
text = inline[index].text.replace(inline[index].text[start:start + length], '')
inline[index].text = text
# print(p.text)
# usage
doc = docx.Document('path/to/template.docx')
docx_replace(doc, dict(ItemOne='replacement text', ItemTwo="Some replacement text\nand some more")
doc.save('path/to/destination.docx')
回答3:
from docx import Document
document = Document('old.docx')
dic = {'name':'ahmed','me':'zain'}
for p in document.paragraphs:
inline = p.runs
for i in range(len(inline)):
text = inline[i].text
if text in dic.keys():
text=text.replace(text,dic[text])
inline[i].text = text
document.save('new.docx')
来源：https://stackoverflow.com/questions/34779724/python-docx-replace-string-in-paragraph-while-keeping-style