Update utils.py

utils.py

@@ -2,8 +2,11 @@ from bs4 import BeautifulSoup
 import requests
 import numpy as np
 from datetime import datetime
-from xhtml2pdf import pisa
+from reportlab.lib.pagesizes import letter
+from reportlab.pdfgen import canvas
+from reportlab.lib.utils import ImageReader
 import io
+from PIL import Image
 
 def gen_link():
     if np.random.choice([True, False]):
@@ -95,17 +98,48 @@ def gen_html(num):
     '''
     return all_q
 
-def convert_html_to_pdf(source_html, output_filename):
-    try:
-        result_file = open(output_filename, "w+b")
-        pisa_status = pisa.CreatePDF(
-            io.StringIO(source_html),
-            dest=result_file
-        )
-        result_file.close()
-        if pisa_status.err:
-            raise Exception("Error converting HTML to PDF")
-    except Exception as e:
-        print(f"Error: {e}")
-        raise
-    return pisa_status.err
+def generate_pdf_content(html_content):
+    # Use BeautifulSoup to parse the HTML content
+    soup = BeautifulSoup(html_content, 'html.parser')
+
+    # Extract text and images
+    elements = []
+    for tag in soup.find_all(['p', 'a', 'img']):
+        if tag.name == 'p':
+            elements.append(('text', tag.get_text()))
+        elif tag.name == 'a':
+            elements.append(('link', tag.get('href'), tag.get_text()))
+        elif tag.name == 'img':
+            img_url = tag.get('src')
+            response = requests.get(img_url)
+            img = Image.open(io.BytesIO(response.content))
+            elements.append(('image', img))
+
+    return elements
+
+def create_pdf(filename, content):
+    c = canvas.Canvas(filename, pagesize=letter)
+    width, height = letter
+    y = height - 40
+
+    for elem in content:
+        if elem[0] == 'text':
+            c.drawString(30, y, elem[1])
+            y -= 20
+        elif elem[0] == 'link':
+            c.drawString(30, y, f'{elem[2]}: {elem[1]}')
+            y -= 20
+        elif elem[0] == 'image':
+            img_reader = ImageReader(elem[1])
+            c.drawImage(img_reader, 30, y - elem[1].size[1], width=elem[1].size[0], height=elem[1].size[1])
+            y -= elem[1].size[1] + 20
+
+        if y < 50:
+            c.showPage()
+            y = height - 40
+
+    c.save()
+
+def convert_html_to_pdf(html_content, output_filename):
+    content = generate_pdf_content(html_content)
+    create_pdf(output_filename, content)