First Commit
This commit is contained in:
Igor20264
@@ -0,0 +1,241 @@
|
||||
# md_to_docx_gost_final.py
|
||||
from docx import Document
|
||||
from docx.shared import Pt, Mm, RGBColor, Inches
|
||||
from docx.enum.text import WD_ALIGN_PARAGRAPH, WD_LINE_SPACING
|
||||
from docx.oxml.ns import qn
|
||||
from docx.oxml import OxmlElement
|
||||
from docx.enum.table import WD_TABLE_ALIGNMENT
|
||||
import re
|
||||
import requests
|
||||
from io import BytesIO
|
||||
|
||||
# Счётчик для листингов
|
||||
listing_counter = 0
|
||||
|
||||
|
||||
def setup_gost_style(doc):
|
||||
style = doc.styles['Normal']
|
||||
font = style.font
|
||||
font.name = 'Times New Roman'
|
||||
font.size = Pt(14)
|
||||
font.color.rgb = RGBColor(0, 0, 0) # Чёрный цвет
|
||||
|
||||
rFonts = style.element.rPr.get_or_add_rFonts()
|
||||
rFonts.set(qn('w:eastAsia'), 'Times New Roman')
|
||||
rFonts.set(qn('w:cs'), 'Times New Roman')
|
||||
|
||||
pf = style.paragraph_format
|
||||
pf.alignment = WD_ALIGN_PARAGRAPH.JUSTIFY
|
||||
pf.line_spacing_rule = WD_LINE_SPACING.ONE_POINT_FIVE
|
||||
pf.first_line_indent = Mm(1.25)
|
||||
pf.space_before = Pt(0)
|
||||
pf.space_after = Pt(0)
|
||||
|
||||
section = doc.sections[0]
|
||||
section.top_margin = Mm(20)
|
||||
section.bottom_margin = Mm(20)
|
||||
section.left_margin = Mm(30)
|
||||
section.right_margin = Mm(15)
|
||||
|
||||
|
||||
def add_heading(doc, text, level=1):
|
||||
heading = doc.add_heading(text, level=level)
|
||||
if level <= 3:
|
||||
heading.alignment = WD_ALIGN_PARAGRAPH.CENTER
|
||||
for run in heading.runs:
|
||||
run.font.bold = True
|
||||
run.font.size = Pt(16) if level == 1 else Pt(14)
|
||||
run.font.color.rgb = RGBColor(0, 0, 0)
|
||||
|
||||
|
||||
def add_listing_caption(doc, language="C++"):
|
||||
global listing_counter
|
||||
listing_counter += 1
|
||||
p = doc.add_paragraph(f"Листинг {listing_counter} — Код на {language}", style='Caption')
|
||||
p.alignment = WD_ALIGN_PARAGRAPH.CENTER
|
||||
p.style.font.color.rgb = RGBColor(0, 0, 0)
|
||||
for run in p.runs:
|
||||
run.font.color.rgb = RGBColor(0, 0, 0)
|
||||
|
||||
|
||||
def add_code_block_as_table(doc, code_lines, language=""):
|
||||
global listing_counter
|
||||
add_listing_caption(doc, language) # Подпись ДО таблицы
|
||||
|
||||
table = doc.add_table(rows=1, cols=1)
|
||||
table.style = 'Table Grid'
|
||||
table.alignment = WD_TABLE_ALIGNMENT.CENTER
|
||||
cell = table.cell(0, 0)
|
||||
|
||||
# Серый фон
|
||||
shading_elm = parse_xml(f'<w:shd {nsdecls("w")} w:fill="D9D9D9"/>')
|
||||
cell._tc.get_or_add_tcPr().append(shading_elm)
|
||||
|
||||
paragraph = cell.paragraphs[0]
|
||||
run = paragraph.add_run()
|
||||
run.font.name = 'Courier New'
|
||||
run._element.rPr.rFonts.set(qn('w:eastAsia'), 'Courier New')
|
||||
run.font.size = Pt(12)
|
||||
run.font.color.rgb = RGBColor(0, 0, 0)
|
||||
run.text = "\n".join(code_lines).strip()
|
||||
|
||||
# Запрещаем разрыв строки внутри первой строки таблицы
|
||||
tr = table.rows[0]._tr
|
||||
trPr = tr.get_or_add_trPr()
|
||||
cantSplit = OxmlElement('w:cantSplit')
|
||||
cantSplit.set(qn('w:val'), 'true')
|
||||
trPr.append(cantSplit)
|
||||
|
||||
|
||||
def add_image_from_url(doc, url, caption_text):
|
||||
try:
|
||||
response = requests.get(url.strip(), timeout=5)
|
||||
image_stream = BytesIO(response.content)
|
||||
p = doc.add_picture(image_stream, width=Inches(5))
|
||||
p.alignment = WD_ALIGN_PARAGRAPH.CENTER
|
||||
|
||||
# Подпись к рисунку
|
||||
caption = doc.add_paragraph(f"Рисунок — {caption_text}", style='Caption')
|
||||
caption.alignment = WD_ALIGN_PARAGRAPH.CENTER
|
||||
for run in caption.runs:
|
||||
run.font.color.rgb = RGBColor(0, 0, 0)
|
||||
except Exception as e:
|
||||
print(f"⚠️ Ошибка загрузки изображения: {url} — {e}")
|
||||
doc.add_paragraph(f"[Изображение не загружено: {caption_text}]").alignment = WD_ALIGN_PARAGRAPH.CENTER
|
||||
|
||||
|
||||
def parse_xml(xml):
|
||||
from docx.oxml import parse_xml as ox_parse
|
||||
return ox_parse(xml)
|
||||
|
||||
|
||||
def nsdecls(*namespaces):
|
||||
return ' '.join(f'xmlns:{ns}="http://schemas.openxmlformats.org/wordprocessingml/2006/main"' for ns in namespaces)
|
||||
|
||||
|
||||
def add_formatted_paragraph(doc, text):
|
||||
p = doc.add_paragraph()
|
||||
p.style = 'Normal'
|
||||
|
||||
parts = re.split(r'(\*\*[^*]+\*\*)', text)
|
||||
for part in parts:
|
||||
if part.startswith('**') and part.endswith('**'):
|
||||
clean_text = part[2:-2]
|
||||
run = p.add_run(clean_text)
|
||||
run.bold = True
|
||||
run.font.color.rgb = RGBColor(0, 0, 0)
|
||||
elif part.strip():
|
||||
run = p.add_run(part)
|
||||
run.font.color.rgb = RGBColor(0, 0, 0)
|
||||
|
||||
|
||||
def parse_markdown_and_fill(doc, md_text):
|
||||
global listing_counter
|
||||
lines = md_text.split('\n')
|
||||
i = 0
|
||||
in_code_block = False
|
||||
code_buffer = []
|
||||
code_language = ""
|
||||
|
||||
while i < len(lines):
|
||||
line = lines[i].rstrip()
|
||||
|
||||
# === Заголовки 1–4 ===
|
||||
if line.startswith('#### '):
|
||||
if in_code_block:
|
||||
add_code_block_as_table(doc, code_buffer, code_language)
|
||||
in_code_block = False
|
||||
code_buffer = []
|
||||
add_heading(doc, line[5:].strip(), level=4)
|
||||
|
||||
elif line.startswith('### '):
|
||||
if in_code_block:
|
||||
add_code_block_as_table(doc, code_buffer, code_language)
|
||||
in_code_block = False
|
||||
code_buffer = []
|
||||
add_heading(doc, line[4:].strip(), level=3)
|
||||
|
||||
elif line.startswith('## '):
|
||||
if in_code_block:
|
||||
add_code_block_as_table(doc, code_buffer, code_language)
|
||||
in_code_block = False
|
||||
code_buffer = []
|
||||
add_heading(doc, line[3:].strip(), level=2)
|
||||
|
||||
elif line.startswith('# '):
|
||||
if in_code_block:
|
||||
add_code_block_as_table(doc, code_buffer, code_language)
|
||||
in_code_block = False
|
||||
code_buffer = []
|
||||
add_heading(doc, line[2:].strip(), level=1)
|
||||
|
||||
# === Горизонтальная линия ===
|
||||
elif line.strip() == '---':
|
||||
doc.add_paragraph().add_run().add_break()
|
||||
|
||||
# === Блок кода ``` ===
|
||||
elif line.startswith('```'):
|
||||
if not in_code_block:
|
||||
in_code_block = True
|
||||
code_language = line[3:].strip() or "C++"
|
||||
code_buffer = []
|
||||
else:
|
||||
in_code_block = False
|
||||
add_code_block_as_table(doc, code_buffer, code_language)
|
||||
code_buffer = []
|
||||
|
||||
elif in_code_block:
|
||||
code_buffer.append(line)
|
||||
|
||||
# === Изображения:  ===
|
||||
elif re.match(r'^!\[.*?\]\(.*?\)$', line.strip()):
|
||||
match = re.match(r'^!\[(.*?)\]\((.*?)\)$', line.strip())
|
||||
if match:
|
||||
caption = match.group(1)
|
||||
url = match.group(2)
|
||||
add_image_from_url(doc, url, caption)
|
||||
|
||||
# === Маркированный список ===
|
||||
elif line.startswith('- '):
|
||||
p = doc.add_paragraph(line[2:], style='List Bullet')
|
||||
for run in p.runs:
|
||||
run.font.color.rgb = RGBColor(0, 0, 0)
|
||||
|
||||
# === Обычный абзац с жирным ===
|
||||
else:
|
||||
if line.strip():
|
||||
if '**' in line:
|
||||
add_formatted_paragraph(doc, line)
|
||||
else:
|
||||
p = doc.add_paragraph(line)
|
||||
p.style = 'Normal'
|
||||
for run in p.runs:
|
||||
run.font.color.rgb = RGBColor(0, 0, 0)
|
||||
|
||||
i += 1
|
||||
|
||||
# Остаток кода
|
||||
if in_code_block and code_buffer:
|
||||
add_code_block_as_table(doc, code_buffer, code_language)
|
||||
|
||||
|
||||
def main():
|
||||
try:
|
||||
with open(r"C:\Users\hlebushek\Desktop\Пример.txt", "r", encoding="utf-8") as f:
|
||||
md_content = f.read()
|
||||
except FileNotFoundError:
|
||||
print("Файл 'Пример.txt' не найден.")
|
||||
return
|
||||
|
||||
doc = Document()
|
||||
setup_gost_style(doc)
|
||||
parse_markdown_and_fill(doc, md_content)
|
||||
|
||||
output_filename = "Практическая_работа_6.docx"
|
||||
doc.save(output_filename)
|
||||
print(f"✅ Готово! Файл сохранён как '{output_filename}'")
|
||||
print(f"📎 Включены: изображения, чёрный текст, листинги перед кодом, нумерация.")
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
Reference in New Issue
Block a user