我使用 Word 对象模型 从 Word 文档中提取带有回复的评论。有关评论对象的文档可 在此处 。此文档使用 Visual Basic for Applications (VBA)。但我能够使用 Python 中的函数，只需稍加修改即可。Word 对象模型的唯一问题是我必须使用 pywin32 中的 win32com 包，它在 Windows PC 上运行良好，但我不确定它是否可以在 macOS 上运行。
这是我用来提取带有相关回复的评论的示例代码：
import win32com.client as win32
from win32com.client import constants
word = win32.gencache.EnsureDispatch('Word.Application')
word.Visible = False
filepath = "path\to\file.docx"
def get_comments(filepath):
doc = word.Documents.Open(filepath)
doc.Activate()
activeDoc = word.ActiveDocument
for c in activeDoc.Comments:
if c.Ancestor is None: #checking if this is a top-level comment
print("Comment by: " + c.Author)
print("Comment text: " + c.Range.Text) #text of the comment
print("Regarding: " + c.Scope.Text) #text of the original document where the comment is anchored
if len(c.Replies)> 0: #if the comment has replies
print("Number of replies: " + str(len(c.Replies)))
for r in range(1, len(c.Replies)+1):
print("Reply by: " + c.Replies(r).Author)
print("Reply text: " + c.Replies(r).Range.Text) #text of the reply
doc.Close()
from docx import Document
from lxml import etree
import zipfile
ooXMLns = {'w':'http://schemas.openxmlformats.org/wordprocessingml/2006/main'}
#Function to extract all the comments of document(Same as accepted answer)
#Returns a dictionary with comment id as key and comment string as value
def get_document_comments(docxFileName):
comments_dict={}
docxZip = zipfile.ZipFile(docxFileName)
commentsXML = docxZip.read('word/comments.xml')
et = etree.XML(commentsXML)
comments = et.xpath('//w:comment',namespaces=ooXMLns)
for c in comments:
comment=c.xpath('string(.)',namespaces=ooXMLns)
comment_id=c.xpath('@w:id',namespaces=ooXMLns)[0]
comments_dict[comment_id]=comment
return comments_dict
#Function to fetch all the comments in a paragraph
def paragraph_comments(paragraph,comments_dict):
comments=[]
for run in paragraph.runs:
comment_reference=run._r.xpath("./w:commentReference")
if comment_reference:
comment_id=comment_reference[0].xpath('@w:id',namespaces=ooXMLns)[0]
comment=comments_dict[comment_id]
comments.append(comment)
return comments
#Function to fetch all comments with their referenced paragraph
#This will return list like this [{'Paragraph text': [comment 1,comment 2]}]
def comments_with_reference_paragraph(docxFileName):
document = Document(docxFileName)
comments_dict=get_document_comments(docxFileName)
comments_with_their_reference_paragraph=[]
for paragraph in document.paragraphs:
if comments_dict:
comments=paragraph_comments(paragraph,comments_dict)
if comments:
comments_with_their_reference_paragraph.append({paragraph.text: comments})
return comments_with_their_reference_paragraph
if __name__=="__main__":
document="test.docx" #filepath for the input document
print(comments_with_reference_paragraph(document))
from lxml import etree
import zipfile
ooXMLns = {'w':'http://schemas.openxmlformats.org/wordprocessingml/2006/main'}
def get_comments(docxFileName):
docxZip = zipfile.ZipFile(docxFileName)
commentsXML = docxZip.read('word/comments.xml')
et = etree.XML(commentsXML)
comments = et.xpath('//w:comment',namespaces=ooXMLns)
for c in comments:
# attributes:
print(c.xpath('@w:author',namespaces=ooXMLns))
print(c.xpath('@w:date',namespaces=ooXMLns))
# string value of the comment:
print(c.xpath('string(.)',namespaces=ooXMLns))
