File size: 14,355 Bytes
22087d0 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 | """
Export API for converting HTML/Markdown to PDF and DOCX
This module provides endpoints for exporting content from the mobile/web app
to various formats (PDF, DOCX, HTML, Markdown).
"""
from pathlib import Path
from io import BytesIO
from typing import Optional
from fastapi import APIRouter, HTTPException, Depends, Request
from fastapi.responses import Response
from pydantic import BaseModel, Field
from urllib.parse import quote
from core.utils.auth_utils import verify_and_get_user_id_from_jwt
try:
from weasyprint import HTML, CSS
except (ImportError, OSError) as e:
weasyprint_available = False
print(f"[WARNING] WeasyPrint not available: {e}")
print("[INFO] To fix on macOS, run: export DYLD_FALLBACK_LIBRARY_PATH=$(brew --prefix)/lib:$DYLD_FALLBACK_LIBRARY_PATH")
else:
weasyprint_available = True
try:
from docx import Document
from docx.shared import Inches, Pt, RGBColor
from docx.enum.text import WD_ALIGN_PARAGRAPH
except ImportError:
docx_available = False
else:
docx_available = True
try:
from bs4 import BeautifulSoup
except ImportError:
beautifulsoup_available = False
else:
beautifulsoup_available = True
router = APIRouter(prefix="/export", tags=["export"])
class ExportRequest(BaseModel):
"""Request model for export endpoints"""
content: str = Field(..., description="HTML content to export")
fileName: str = Field(..., description="Base filename (without extension)")
class ExportResponse(BaseModel):
"""Response model for export endpoints"""
success: bool
message: str
filename: Optional[str] = None
# Professional PDF styles matching the Next.js implementation
PDF_STYLES = """
* {
margin: 0;
padding: 0;
box-sizing: border-box;
}
body {
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', Arial, sans-serif;
font-size: 11pt;
line-height: 1.6;
color: #1a1a1a;
padding: 0;
margin: 0;
background: #fff;
}
h1, h2, h3, h4, h5, h6 {
font-weight: 600;
line-height: 1.3;
color: #111;
letter-spacing: -0.02em;
page-break-after: avoid;
}
h1 {
font-size: 18pt;
margin: 24pt 0 12pt 0;
padding-bottom: 6pt;
border-bottom: 1pt solid #e0e0e0;
}
h1:first-child { margin-top: 0; }
h2 { font-size: 15pt; margin: 20pt 0 10pt 0; }
h2:first-child { margin-top: 0; }
h3 { font-size: 13pt; margin: 16pt 0 8pt 0; }
h3:first-child { margin-top: 0; }
h4 { font-size: 11pt; margin: 14pt 0 6pt 0; }
h4:first-child { margin-top: 0; }
h5 { font-size: 11pt; margin: 12pt 0 4pt 0; }
h5:first-child { margin-top: 0; }
h6 {
font-size: 10pt;
margin: 12pt 0 4pt 0;
color: #555;
text-transform: uppercase;
letter-spacing: 0.5pt;
}
h6:first-child { margin-top: 0; }
p { margin: 8pt 0; line-height: 1.65; }
p:first-child { margin-top: 0; }
p:last-child { margin-bottom: 0; }
strong, b { font-weight: 600; }
em, i { font-style: italic; }
u { text-decoration: underline; }
s, strike, del { text-decoration: line-through; color: #666; }
a { color: #0066cc; text-decoration: underline; }
ul, ol { margin: 10pt 0; padding-left: 28pt; }
ul:first-child, ol:first-child { margin-top: 0; }
ul:last-child, ol:last-child { margin-bottom: 0; }
li { margin: 4pt 0; line-height: 1.5; padding-left: 4pt; }
li > ul, li > ol { margin: 4pt 0; }
blockquote {
margin: 12pt 0;
padding: 8pt 12pt;
border-left: 3pt solid #e0e0e0;
background: #fafafa;
color: #555;
font-style: italic;
border-radius: 0 4pt 4pt 0;
}
code {
font-family: 'Courier New', Consolas, 'Lucida Console', monospace;
font-size: 10pt;
background: #f4f4f5;
padding: 2pt 4pt;
border-radius: 2pt;
color: #1a1a1a;
}
pre {
margin: 12pt 0;
padding: 12pt;
background: #f4f4f5;
border: 1pt solid #e4e4e7;
border-radius: 4pt;
overflow-x: auto;
font-size: 9.5pt;
line-height: 1.5;
page-break-inside: avoid;
}
pre code {
background: none;
padding: 0;
border-radius: 0;
}
table {
width: 100%;
margin: 14pt 0;
border-collapse: collapse;
font-size: 10.5pt;
page-break-inside: avoid;
}
th {
padding: 8pt 10pt;
border: 1pt solid #d0d0d0;
text-align: left;
font-weight: 600;
background: #f8f9fa;
}
td {
padding: 8pt 10pt;
border: 1pt solid #d0d0d0;
text-align: left;
vertical-align: top;
}
hr { border: none; border-top: 1pt solid #e0e0e0; margin: 20pt 0; }
img { max-width: 100%; height: auto; display: block; margin: 12pt 0; page-break-inside: avoid; }
@media print {
body { font-size: 11pt; -webkit-print-color-adjust: exact; print-color-adjust: exact; }
pre { white-space: pre-wrap; word-wrap: break-word; page-break-inside: avoid; }
h1, h2, h3, h4, h5, h6 { page-break-after: avoid; }
table { page-break-inside: avoid; }
img { page-break-inside: avoid; }
tr { page-break-inside: avoid; }
}
@page { size: A4; margin: 20mm; }
"""
def sanitize_filename(name: str) -> str:
"""Sanitize filename for safe file system use"""
import re
return re.sub(r'[^\w\s-]', '', name).strip()[:100] or 'document'
def preprocess_html(html: str) -> str:
"""Preprocess HTML for better conversion"""
import re
if not html or not isinstance(html, str):
return '<p></p>'
# If content is a full HTML document, extract just the body content
# This prevents nested HTML documents when we wrap it later
if '<!DOCTYPE' in html.upper() or '<html' in html.lower():
# Try to extract body content
body_match = re.search(r'<body[^>]*>(.*?)</body>', html, re.IGNORECASE | re.DOTALL)
if body_match:
html = body_match.group(1)
# Remove script/style tags
html = re.sub(r'<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>', '', html, flags=re.IGNORECASE)
html = re.sub(r'<style\b[^<]*(?:(?!<\/style>)<[^<]*)*<\/style>', '', html, flags=re.IGNORECASE)
# Clean up empty paragraphs
html = re.sub(r'<p>\s*<\/p>', '', html)
return html.strip()
@router.post("/pdf")
async def export_to_pdf(
request: ExportRequest,
user_id: str = Depends(verify_and_get_user_id_from_jwt)
):
"""
Export HTML content to PDF using WeasyPrint
Requires authentication.
Returns the PDF file directly for download.
"""
if not weasyprint_available:
raise HTTPException(
status_code=503,
detail="PDF export is not available. WeasyPrint is not installed."
)
try:
content = request.content
file_name = sanitize_filename(request.fileName)
print(f"[PDF Export] User: {user_id}, File: {file_name}, Content length: {len(content)}")
# Preprocess HTML
preprocessed_html = preprocess_html(content)
# Create full HTML document with styles
full_html = f"""<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title>{file_name}</title>
<style>{PDF_STYLES}</style>
</head>
<body>
{preprocessed_html}
</body>
</html>"""
# Generate PDF with WeasyPrint
pdf_bytes = HTML(string=full_html).write_pdf()
# Return PDF file
encoded_filename = quote(f"{file_name}.pdf", safe="")
return Response(
content=pdf_bytes,
media_type="application/pdf",
headers={
"Content-Disposition": f"attachment; filename*=UTF-8''{encoded_filename}"
}
)
except Exception as e:
print(f"❌ PDF export error: {e}")
import traceback
traceback.print_exc()
raise HTTPException(
status_code=500,
detail=f"Failed to generate PDF: {str(e)}"
)
@router.post("/docx")
async def export_to_docx(
request: ExportRequest,
user_id: str = Depends(verify_and_get_user_id_from_jwt)
):
"""
Export HTML content to DOCX format
Requires authentication.
Returns the DOCX file directly for download.
"""
if not docx_available or not beautifulsoup_available:
raise HTTPException(
status_code=503,
detail="DOCX export is not available. Required libraries are not installed."
)
try:
content = request.content
file_name = sanitize_filename(request.fileName)
print(f"[DOCX Export] User: {user_id}, File: {file_name}, Content length: {len(content)}")
# Preprocess HTML to extract body content if it's a full document
preprocessed_content = preprocess_html(content)
# Create DOCX document with clean black/white styling
doc = Document()
# Set default font to clean black/white theme
style = doc.styles['Normal']
style.font.name = 'Calibri'
style.font.size = Pt(11)
style.font.color.rgb = RGBColor(26, 26, 26) # #1a1a1a - dark gray/black
# Parse HTML with BeautifulSoup
soup = BeautifulSoup(preprocessed_content, 'html.parser')
# Convert HTML elements to DOCX
for element in soup.children:
process_html_element(element, doc)
# Save to BytesIO buffer
buffer = BytesIO()
doc.save(buffer)
buffer.seek(0)
# Return DOCX file
encoded_filename = quote(f"{file_name}.docx", safe="")
return Response(
content=buffer.getvalue(),
media_type="application/vnd.openxmlformats-officedocument.wordprocessingml.document",
headers={
"Content-Disposition": f"attachment; filename*=UTF-8''{encoded_filename}"
}
)
except Exception as e:
print(f"❌ DOCX export error: {e}")
raise HTTPException(
status_code=500,
detail=f"Failed to generate DOCX: {str(e)}"
)
def process_html_element(element, doc, parent_paragraph=None):
"""Process HTML element and add to DOCX document"""
if element.name is None:
text = str(element).strip()
if text and parent_paragraph:
parent_paragraph.add_run(text)
return
if element.name == 'p':
p = doc.add_paragraph()
for child in element.children:
process_inline_element(child, p)
elif element.name in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6']:
level = int(element.name[1])
heading = doc.add_heading(element.get_text(), level)
# Ensure heading is black
for run in heading.runs:
run.font.color.rgb = RGBColor(17, 17, 17) # #111 - dark black for headings
elif element.name == 'ul':
for li in element.find_all('li', recursive=False):
p = doc.add_paragraph(style='List Bullet')
for child in li.children:
process_inline_element(child, p)
elif element.name == 'ol':
for li in element.find_all('li', recursive=False):
p = doc.add_paragraph(style='List Number')
for child in li.children:
process_inline_element(child, p)
elif element.name == 'blockquote':
p = doc.add_paragraph()
p.paragraph_format.left_indent = Inches(0.5)
run = p.add_run(element.get_text())
run.font.italic = True
run.font.color.rgb = RGBColor(85, 85, 85) # #555 - gray for blockquotes
elif element.name == 'pre':
p = doc.add_paragraph()
run = p.add_run(element.get_text())
run.font.name = 'Courier New'
run.font.size = Pt(10)
run.font.color.rgb = RGBColor(26, 26, 26) # Black for code blocks
elif element.name == 'table':
process_table_element(element, doc)
def process_inline_element(element, paragraph):
"""Process inline HTML element and add to paragraph"""
if element.name is None:
text = str(element).strip()
if text:
paragraph.add_run(text)
return
if element.name == 'strong' or element.name == 'b':
run = paragraph.add_run(element.get_text())
run.bold = True
elif element.name == 'em' or element.name == 'i':
run = paragraph.add_run(element.get_text())
run.italic = True
elif element.name == 'u':
run = paragraph.add_run(element.get_text())
run.underline = True
elif element.name == 'code':
run = paragraph.add_run(element.get_text())
run.font.name = 'Courier New'
run.font.size = Pt(10)
run.font.color.rgb = RGBColor(26, 26, 26) # Black for inline code
elif element.name == 'a':
run = paragraph.add_run(element.get_text())
run.font.color.rgb = RGBColor(26, 26, 26) # Black instead of blue
run.underline = True
else:
for child in element.children:
process_inline_element(child, paragraph)
def process_table_element(table_element, doc):
"""Process HTML table and add to DOCX document"""
rows = table_element.find_all('tr')
if not rows:
return
max_cols = max(len(row.find_all(['td', 'th'])) for row in rows)
if max_cols == 0:
return
table = doc.add_table(rows=len(rows), cols=max_cols)
table.style = 'Table Grid'
for i, row in enumerate(rows):
cells = row.find_all(['td', 'th'])
for j, cell in enumerate(cells):
if j < max_cols:
table_cell = table.rows[i].cells[j]
table_cell.text = cell.get_text().strip()
if cell.name == 'th':
for paragraph in table_cell.paragraphs:
for run in paragraph.runs:
run.bold = True
run.font.color.rgb = RGBColor(17, 17, 17) # Black for table headers
@router.get("/health")
async def export_health_check():
"""Export service health check endpoint"""
return {
"status": "healthy",
"service": "export-api",
"pdf_available": weasyprint_available,
"docx_available": docx_available and beautifulsoup_available,
}
|