检测Word文档中单词和页面的出现位置。

1. 使用Python-docx模块：

from docx import Document

def search_word(doc, word): location_dict = {} for paragraph in doc.paragraphs: if word in paragraph.text: location_dict.setdefault(paragraph.text, []).append(doc.paragraphs.index(paragraph)) return location_dict

def get_page_num(doc, paragraph_index): doc_element = doc.part.element namespace = '{http://schemas.openxmlformats.org/wordprocessingml/2006/main}' for element in doc_element.iter(namespace+'p'): if str(doc_element.index(element)) == str(paragraph_index): return element.xpath(namespace+'pPr')[0].xpath(namespace+'numPr')[0].xpath(namespace+'ilvl')[0].get(namespace+'val')

使用方法：

doc = Document('document.docx') location_dict = search_word(doc, 'example') for key, value in location_dict.items(): for idx in value: print('单词“{}”出现在第{}页，第{}段落。'.format('example', get_page_num(doc, idx), idx))

2. 使用win32com模块：

import win32com.client

def search_word(doc, word): location_dict = {} for p in range(doc.Range().Paragraphs.Count): para_text = doc.Range().Paragraphs(p+1).Range.Text if word in para_text: location_dict.setdefault(para_text, []).append(p+1) return location_dict

def get_page_num(doc, paragraph_index): return doc.Range().Paragraphs(paragraph_index).Range.Information(win32com.client.constants.wdActiveEndPageNumber)

使用方法：

word = win32com.client.Dispatch('Word.Application') word.Visible = False doc = word.Documents.Open('document.docx') location_dict = search_word(doc, 'example') for key, value in location_dict.items(): for idx in value: print('单词“{}”出现在第{}页，第{}段落。'.format('example', get_page_num(doc, idx), idx))

注意：以上代码示例仅适用于文本样式单一的Word文档，若文档中存在多种样