使用Python docx库匹配段落时无法添加新行并插入表格的问题

问题说明 #

匹配到字符串Test criteria / Testkriterien后，想要在其下方插入表格，预期是表格位于两段文字之间独立显示；但实际效果是表格与后续文本混排，后续文本被挤入表格首单元格中。

原代码 #

from docx import Document
from docx.shared import RGBColor
from docx.oxml.ns import qn
from docx.oxml import OxmlElement
document = Document(r'D:\Reqquirement_doc\cb test automation\requirements and other documents\Template_Testreport_8PA3.1.docx')

# 创建并填充表格
table = document.add_table(rows=1, cols=len(post(read_only).columns))
table.style = 'Table Grid'

for x, col_name in enumerate(post(read_only).columns):
    cell = table.cell(0, x)
    cell.text = col_name
            
    # 设置单元格背景色
    tblCell = cell._tc
    tblCellProperties = tblCell.get_or_add_tcPr()
    clShading = OxmlElement('w:shd')
    clShading.set(qn('w:fill'), "D5B076")
    tblCellProperties.append(clShading)

# 填充表格数据行
for x, row in (post(read_only).iterrows()):
    new_row = table.add_row().cells
    for y, val in enumerate(row):
        cell = new_row[y]
        cell.text = str(val)
        tblCell = cell._tc
        tblCellProperties = tblCell.get_or_add_tcPr()
        clShading = OxmlElement('w:shd')
        clShading.set(qn('w:fill'), "F6EFE3")
        tblCellProperties.append(clShading)

# 遍历段落插入表格
for i in range(len(document.paragraphs)):
    if document.paragraphs[i].text == 'Test criteria / Testkriterien':
        document.paragraphs[i+1].add_run().add_break()
        document.paragraphs[i+1]._element.append(table._element)
        break 
modified_file_path = r'D:\Reqquirement_doc\cb test automation\requirements and other documents\Template_Testreport_8PA3.1_modified.docx'
document.save(modified_file_path)

问题原因 #

原代码把表格元素直接追加到了目标段落（document.paragraphs[i+1]）的内部元素中，导致表格成为该段落的一部分，后续文本自然会被纳入表格首单元格。

解决方法 #

需要将表格作为独立元素插入到文档的body中，放在匹配段落的下一个位置。可额外添加空段落来保证排版间距。

修改后的代码 #

from docx import Document
from docx.shared import RGBColor
from docx.oxml.ns import qn
from docx.oxml import OxmlElement
document = Document(r'D:\Reqquirement_doc\cb test automation\requirements and other documents\Template_Testreport_8PA3.1.docx')

# 创建并填充表格
table = document.add_table(rows=1, cols=len(post(read_only).columns))
table.style = 'Table Grid'

for x, col_name in enumerate(post(read_only).columns):
    cell = table.cell(0, x)
    cell.text = col_name
            
    # 设置表头单元格背景色
    tblCell = cell._tc
    tblCellProperties = tblCell.get_or_add_tcPr()
    clShading = OxmlElement('w:shd')
    clShading.set(qn('w:fill'), "D5B076")
    tblCellProperties.append(clShading)

# 填充表格数据行
for x, row in post(read_only).iterrows():
    new_row = table.add_row().cells
    for y, val in enumerate(row):
        cell = new_row[y]
        cell.text = str(val)
        tblCell = cell._tc
        tblCellProperties = tblCell.get_or_add_tcPr()
        clShading = OxmlElement('w:shd')
        clShading.set(qn('w:fill'), "F6EFE3")
        tblCellProperties.append(clShading)

# 遍历段落找到目标位置插入表格
for i, para in enumerate(document.paragraphs):
    if para.text == 'Test criteria / Testkriterien':
        # 获取文档body元素
        body = document._body._body
        target_element = para._element
        
        # 在目标段落后插入空段落（用于调整间距）
        empty_para = OxmlElement('w:p')
        target_element.addnext(empty_para)
        
        # 在空段落后插入表格
        empty_para.addnext(table._element)
        
        # 表格后再插入空段落（可选）
        empty_para2 = OxmlElement('w:p')
        table._element.addnext(empty_para2)
        
        break 

modified_file_path = r'D:\Reqquirement_doc\cb test automation\requirements and other documents\Template_Testreport_8PA3.1_modified.docx'
document.save(modified_file_path)

内容的提问来源于stack exchange，提问作者sathwik