def aw_extract_headings_and_contents_table_dict_id(file):
doc = aw.Document(file)
current_level = 0
data = []
doc.update_list_labels()
stack = []
for s in doc.sections:
sect = s.as_section()
for node in sect.body.get_child_nodes(aw.NodeType.ANY, True):
if node.node_type == aw.NodeType.PARAGRAPH:
node = node.as_paragraph()
if node.paragraph_format.outline_level in [0, 1, 2, 3, 4, 5]:
if node.node_type == aw.NodeType.FIELD_START:
continue
level = int(node.paragraph_format.outline_level) + 1
if level > current_level:
stack.append((current_level, data))
data = []
current_level = level
elif level < current_level:
while stack and stack[-1][0] >= level:
old_level, old_data = stack.pop()
data = old_data + data
current_level = old_level
label = ''
if node.list_format.is_list_item:
label = node.list_label.label_string
text_without_comments = node.get_text().strip()
data.append({"title": label + text_without_comments if label else text_without_comments, "content": [], "tables": []})
else:
if data and node.get_text().strip():
data[-1]["content"].append(node.get_text().strip().replace(" SEQ 表 \* ARABIC ", '').replace('TOC \h \c "表" HYPERLINK \l "_Toc14741"', '').replace("\u0013 SEQ 图 \\* ARABIC \u00141\u0015 ", '')+ "\n")
if node.node_type == aw.NodeType.TABLE:
parent_node = node.as_table()
table_content = aw_read_table_id(parent_node)
if data:
data[-1]["tables"].append(table_content)
while stack:
old_level, old_data = stack.pop()
data = old_data + data
return data
def aw_read_table_id(table=None, id=1):
table.convert_to_horizontally_merged_cells()
table_data = []
for row in table.rows:
content = {
"type": "tableRow",
"content": []
}
row_index = table.index_of(row)
cell = row.as_row().first_cell
row_span = 1
col_span = 1
current_cell = cell
cell_index = 0
cell_text = ""
while current_cell is not None:
cell_index = current_cell.parent_row.index_of(current_cell)
if current_cell.cell_format.vertical_merge == aw.tables.CellMerge.FIRST and current_cell.cell_format.horizontal_merge == aw.tables.CellMerge.FIRST:
cell_text = current_cell.get_text()
current_cell = current_cell.next_cell
for i in range(row_index, table.rows.count):
if table.rows[i].cells[cell_index].cell_format.vertical_merge == aw.tables.CellMerge.PREVIOUS:
row_span += 1
while current_cell is not None and current_cell.cell_format.horizontal_merge == aw.tables.CellMerge.PREVIOUS:
col_span = col_span + 1
current_cell = current_cell.next_cell
elif current_cell.cell_format.horizontal_merge == aw.tables.CellMerge.FIRST:
cell_text = current_cell.get_text()
current_cell = current_cell.next_cell
while current_cell is not None and current_cell.cell_format.horizontal_merge == aw.tables.CellMerge.PREVIOUS:
col_span = col_span + 1
current_cell = current_cell.next_cell
elif current_cell.cell_format.vertical_merge == aw.tables.CellMerge.FIRST:
cell_text = current_cell.get_text()
cell_index = current_cell.parent_row.index_of(current_cell)
for i in range(row_index, table.rows.count):
if table.rows[i].cells[cell_index].cell_format.vertical_merge == aw.tables.CellMerge.PREVIOUS:
row_span += 1
current_cell = current_cell.next_cell
else:
cell_text = current_cell.get_text()
current_cell = current_cell.next_cell
cell_content = {
"type": "tableCell",
"attrs": {
"colspan": col_span,
"rowspan": row_span,
"colwidth": None
},
"content": []
}
paragraph = {
"type": "paragraph",
"content": [
{
"type": "text",
"text": cell_text,
}
]
}
cell_content["content"].append(paragraph)
content["content"].append(cell_content)
col_span = 1
row_span = 1
table_data.append(content)
return_data = {
"type": "table",
"attrs": {
"id": id
},
"content": table_data
}
print(1111,return_data)
return return_data
上面aw_read_table_id的这个函数 怎么返回一个html表格的数据
@hhh1111
要将表格的节点转换为HTML格式，您可以使用Aspose.Words库中的功能来实现。以下是一个示例代码，展示了如何将表格转换为HTML格式：
import aspose.words as aw
def table_to_html(file_path):
# 加载文档
doc = aw.Document(file_path)
# 获取文档中的第一个表格
table = doc.get_child(aw.NodeType.TABLE, 0, True)
# 将表格转换为HTML
html = table.to_string(aw.SaveFormat.HTML)
return html
# 使用示例
file_path = "path/to/your/document.docx"
html_output = table_to_html(file_path)
print(html_output)
在这个示例中，我们首先加载一个Word文档，然后获取文档中的第一个表格。接着，我们使用to_string方法将表格转换为HTML格式。您可以根据需要调整文件路径和表格索引。
如果您需要处理多个表格或特定的表格，可以在代码中进行相应的修改。希望这能帮助您实现将表格节点转换为HTML格式的需求！
为什么我获取段落信息。 表格数据也出现在段落信息里面了
为什么我获取段落信息。 表格数据也出现在段落信息里面了
def aw_extract_headings_and_contents_table_dict_id(file):
doc = aw.Document(file)
current_level = 0
data = []
doc.update_list_labels()
stack = []
for s in doc.sections:
sect = s.as_section()
for node in sect.body.get_child_nodes(aw.NodeType.ANY, True):
if node.node_type == aw.NodeType.PARAGRAPH:
node = node.as_paragraph()
if node.paragraph_format.outline_level in [0, 1, 2, 3, 4, 5]:
if node.node_type == aw.NodeType.FIELD_START:
continue
level = int(node.paragraph_format.outline_level) + 1
if level > current_level:
stack.append((current_level, data))
data = []
current_level = level
elif level < current_level:
while stack and stack[-1][0] >= level:
old_level, old_data = stack.pop()
data = old_data + data
current_level = old_level
label = ''
if node.list_format.is_list_item:
label = node.list_label.label_string
text_without_comments = node.get_text().strip()
data.append(
{"title": label + text_without_comments if label else text_without_comments, "content": [],
"tables": []})
else:
if data and node.get_text().strip():
data[-1]["content"].append(node.get_text().strip().replace(" SEQ 表 \* ARABIC ", '').replace(
'TOC \h \c "表" HYPERLINK \l "_Toc14741"', '').replace(
"\u0013 SEQ 图 \\* ARABIC \u00141\u0015 ", '') + "\n")
if node.node_type == aw.NodeType.TABLE:
parent_node = node.as_table()
table_content = aw_read_table_id(parent_node)
if data:
data[-1]["tables"].append(table_content)
while stack:
old_level, old_data = stack.pop()
data = old_data + data
return data
不要把表格数据出现在 段落内容的content里面
@hhh1111 这是因为您可以获取文档中的所有节点。段落节点也是表格的一部分，因此在获取每个段落时，也会获取表格中的段落。在这种情况下，你可以仔细检查这个段落是不是表格的一部分：
if node.node_type == aw.NodeType.PARAGRAPH and node.get_ancestor(aw.NodeType.TABLE) is None:
hhh1111
October 18, 2024, 2:45am
10
def aw_extract_headings_and_contents_table_dict_id(file):
doc = aw.Document(file)
current_level = 0
data = {}
doc.update_list_labels()
stack = []
for s in doc.sections:
sect = s.as_section()
for node in sect.body.get_child_nodes(aw.NodeType.ANY, True):
if node.node_type == aw.NodeType.PARAGRAPH:
node = node.as_paragraph()
if node.paragraph_format.outline_level in [0, 1, 2, 3, 4, 5]:
if node.node_type == aw.NodeType.FIELD_START:
continue
level = int(node.paragraph_format.outline_level) + 1
if level > current_level:
stack.append((current_level, data))
data = {}
current_level = level
elif level < current_level:
while stack and stack[-1][0] >= level:
old_level, old_data = stack.pop()
data = {**old_data, **data}
current_level = old_level
label = ''
if node.list_format.is_list_item:
label = node.list_label.label_string
text_without_comments = node.get_text().strip()
current_key = label + text_without_comments if label else text_without_comments
new_run = node.as_run()
# new_run.text = i + aw.ControlChar.PARAGRAPH_BREAK_CHAR
print(new_run)
if current_key not in data:
data[current_key] = ""
else:
if node.list_format.is_list_item:
label = node.list_label.label_string
if node.get_text().strip() and not node.get_ancestor(
aw.NodeType.TABLE) and not node.get_ancestor(aw.NodeType.FIELD_START) and data:
last_key = list(data.keys())[-1]
data[last_key] += label + node.get_text().strip() if label else node.get_text().strip() + "\n"
if node.node_type == aw.NodeType.TABLE:
parent_node = node.as_table()
table_content = aw_read_table_as_markdown(parent_node)
if data:
last_key = list(data.keys())[-1]
data[last_key] += table_content + "\n"
while stack:
old_level, old_data = stack.pop()
data = {**old_data, **data}
return data
hhh1111
October 18, 2024, 3:56am
11
比如 一段话是有绿的色内容。提取出来给这段话前后加一个标签
@hhh1111 字体颜色有几种情况。
如果段落包含带有字体颜色的run，则需要使用：
doc = aw.Document("input.docx")
for run in doc.get_child_nodes(aw.NodeType.RUN, True):
run = run.as_run()
if run.font.color == drawing.Color.green:
new_run_1 = aw.Run(doc, "New text 1")
new_run_2 = aw.Run(doc, "New text 2")
para = run.parent_paragraph
para.insert_before(new_run_1, para.first_child)
para.append_child(new_run_2)
doc.save("output.docx")
如果你需要找到字体颜色的段落，你需要使用：
doc = aw.Document("input.docx")
for para in doc.get_child_nodes(aw.NodeType.PARAGRAPH, True):
para = para.as_paragraph()
if para.paragraph_break_font.color == drawing.Color.green:
new_run = aw.Run(doc, "New text")
new_para_1 = aw.Paragraph(doc)
new_para_1.append_child(new_run)
new_para_2 = new_para_1.clone(True)
para.parent_node.insert_before(new_para_1, para)
para.parent_node.insert_after(new_para_2, para)
doc.save("output.docx")
@hhh1111 你应该为段落中的跑步设置颜色。例如：
ParagraphCollection paragraphs = doc.getFirstSection().getBody().getParagraphs();
for (Paragraph paragraph : paragraphs) {
for (Run run : paragraph.getRuns()) {
run.getFont().setColor(Color.GREEN);
}
}
runs = doc.get_child_nodes(aw.NodeType.RUN, True)
for run in runs:
run = run.as_run()
run.font.color = drawing.Color.green
hhh1111
November 6, 2024, 8:34am
15
vyacheslav.deryushev:
doc = aw.Document("input.docx")
for para in doc.get_child_nodes(aw.NodeType.PARAGRAPH, True):
para = para.as_paragraph()
if para.paragraph_break_font.color == drawing.Color.green:
new_run = aw.Run(doc, "New text")
new_para_1 = aw.Paragraph(doc)
new_para_1.append_child(new_run)
new_para_2 = new_para_1.clone(True)
para.parent_node.insert_before(new_para_1, para)
para.parent_node.insert_after(new_para_2, para)
doc.save("output.docx")
我还有一个问题 for part in parts:
hhh1111
November 6, 2024, 8:40am
16
builder.insert_html(part) 我需要对插入的表格重新设置表格样式
@hhh1111 您需要找到插入的表格并清除样式：
table = doc.first_section.body.tables[0]
table.clear_borders()
table.clear_shading()
之后，您可以使用例如table.style_identifier = aw.StyleIdentifier.TABLE_GRID来设置新的表格样式。
hhh1111
November 6, 2024, 10:16am
18
可是不能只获取一个table吧 我的代码如下 我需要在这里重置表格样式 # 处理表格内容
import aspose.words as aw
import jinja2
# 激活 Aspose.Words 许可证
lic = aw.License()
lic_path = "../Aspose.Total.Product.Family.lic"
lic.set_license(lic_path)
import aspose.pydrawing as drawing
import re
def set_paragraph_color(builder, color):
if color == "green":
builder.font.color = drawing.Color.green
elif color == "blue":
builder.font.color = drawing.Color.blue
else:
builder.font.clear_formatting()
def insert_title_content(doc_path, insertions):
doc = aw.Document(doc_path)
builder = aw.DocumentBuilder(doc)
builder.paragraph_format.clear_formatting()
for paragraph in doc.get_child_nodes(aw.NodeType.PARAGRAPH, True):
paragraph = paragraph.as_paragraph()
if "start_insert" in paragraph.get_text():
# 清除当前段落的内容
paragraph.get_child_nodes(aw.NodeType.RUN, True).clear()
builder.move_to(paragraph)
builder.paragraph_format.clear_formatting()
for title, content in insertions.items():
# 插入标题
heading_level = 1 # 默认标题级别为1
builder.paragraph_format.style_name = f"Heading {heading_level}"
builder.writeln(title.strip())
# 处理和插入内容
if content.strip():
# 用正则表达式匹配表格和blue标签的内容
parts = re.split(r'(<table.*?>.*?</table>|<blue>.*?</blue>|<green>.*?</green>)', content, flags=re.S)
for part in parts:
if part.startswith('<table'):
# 处理表格内容
builder.insert_html(part)
elif part.startswith('<blue>'):
# 处理blue标签内容
color_content = re.sub(r'</?blue>', '', part) # 去掉<blue>标签
set_paragraph_color(builder, "blue") # 设置绿色
builder.paragraph_format.style_name = "Normal"
builder.write(color_content.strip('<br>'))
set_paragraph_color(builder, None) # 恢复默认配色
elif part.startswith('<green>'):
# 处理blue标签内容
color_content = re.sub(r'</?green>', '', part) # 去掉<blue>标签
set_paragraph_color(builder, "green") # 设置绿色
builder.paragraph_format.style_name = "Normal"
builder.write(color_content.strip('<br>'))
set_paragraph_color(builder, None) # 恢复默认配色
else:
# 处理普通内容
builder.paragraph_format.style_name = "Normal"
builder.writeln(part.strip())
doc.save('result.docx')
import json
if name == ‘main ’:
@hhh1111 您可以在插入html表后获取当前段落，并获取前一个节点，该节点将是一个表。例如：
builder.insert_html(html_content);
table_node = builder.current_paragraph.previous_sibling
if table_node.node_type == aw.NodeType.TABLE:
table = table_node.as_table()
table.clear_borders()
table.clear_shading()
hhh1111
November 7, 2024, 2:19am
20
哪个属性是设置段前行间距的属性builder.paragraph_format.段前