from spire.doc import Document, Paragraph, Field, FieldType

# 創(chuàng)建Document對(duì)象
doc = Document()

# 加載Word文件
doc.LoadFromFile("示例.docx")

# 創(chuàng)建字符串列表用于儲(chǔ)存超鏈接信息
hyperlinks = []

# 遍歷文檔中的節(jié)
for i in range(doc.Sections.Count):
    # 獲取當(dāng)前節(jié)
    section = doc.Sections.get_Item(i)
    # 遍歷節(jié)中的主體子對(duì)象
    for j in range(section.Body.ChildObjects.Count):
        # 獲取當(dāng)前子對(duì)象
        secObj = section.Body.ChildObjects.get_Item(j)
        # 判斷子對(duì)象是否為段落
        if isinstance(secObj, Paragraph):
            # 遍歷段落中的子對(duì)象
            for k in range(secObj.ChildObjects.Count):
                # 獲取當(dāng)前子對(duì)象
                paraObj = secObj.ChildObjects.get_Item(k)
                # 判斷子對(duì)象是否為域以及是否為超鏈接域
                if isinstance(paraObj, Field) and paraObj.Type == FieldType.FieldHyperlink:
                    # 獲取超鏈接的錨文本
                    anchorText = paraObj.FieldText
                    # 獲取超鏈接的URL
                    url = paraObj.Code.split('"')[1]
                    # 判斷是否存在屏幕提示
                    if "\\o" in paraObj.Code:
                        # 獲取屏幕提示
                        hyperlinkTip = paraObj.Code.split('\"')[3].strip()
                        # 將錨文本、URL和屏幕提示組合到字符串中
                        hyperlinks.append(f"錨文本：{anchorText}\nURL：{url}\n屏幕提示：{hyperlinkTip}\n\n")
                    else:
                        # 將錨文本和URL組合到字符串中
                        hyperlinks.append(f"錨文本：{anchorText}\nURL：{url}\n\n")

# 將超鏈接信息寫入文件
with open("output/提取的超鏈接.txt", "w", encoding="utf-8") as file:
    for hyperlink in hyperlinks:
        file.write(hyperlink)

# 關(guān)閉文檔
doc.Close()

import re
from docx import Document


def get_paragraph_from_docx(file_name):
    """
    網(wǎng)址：https:blog.csdn.net，這是一段有hyperlink的段落
    這是一段沒有hyperlink的段落
    可用于處理包含超鏈接的文本，但會(huì)自動(dòng)跳過表格
    :param file_name:
    :return:
    """
    text = []
    document = Document(file_name)
    for paragraph in document.paragraphs:
        t_para = u""
        # 有無超鏈接均可處理
        xml_str = str(paragraph.paragraph_format.element.xml)
        wt_list = re.findall('<w:t[\S\s]*?</w:t>', xml_str)
        for wt in wt_list:
            wt_content = re.sub('<[\S\s]*?>', u"", wt)
            t_para += wt_content
        if t_para:
            t_para = t_para.strip()
            t_para = re.sub('[\s]', '', t_para)
            if t_para:
                text.append(t_para)
    return text

d = docx.Document(./test.docx)
for p in d.paragraphs:
	xml = p.paragraph_format.element.xml
	xml_str = str(xml)
	wt_list = re.findall('<w:t[\S\s]*?</w:t>', xml_str)
	hyperlink = u''
	for wt in wt_list:
		wt_content = re.sub('<[\S\s]*?>', u'', wt)
		hyperlink += wt_content
	print(hyperlink)