Upload ebook_pipeline.py with huggingface_hub

ebook_pipeline.py

@@ -1,12 +1,14 @@
 import os
 from ebooklib import epub
 from fpdf import FPDF
+import markdown
 
 class BookBuilder:
-    def __init__(self, title, author, description=""):
+    def __init__(self, title, author, description="", cover_image=None):
         self.title = title
         self.author = author
         self.description = description
+        self.cover_image = cover_image
         self.chapters = []
         # Fetch Business Metadata from Environment
         self.business_name = os.environ.get("BUSINESS_NAME", "Fair Dinkum Publishing")
@@ -27,6 +29,14 @@ class BookBuilder:
         book.add_metadata("DC", "rights", f"Copyright (c) 2026 {self.owner}. ABN: {self.abn}")
 
         spine = ["nav"]
+
+        # Add Cover Image if provided
+        if self.cover_image and os.path.exists(self.cover_image):
+            with open(self.cover_image, 'rb') as img_file:
+                content = img_file.read()
+                img_ext = os.path.splitext(self.cover_image)[1][1:]
+                book.set_cover("cover.jpg", content)
+
         # Add Copyright Page
         copy_page = epub.EpubHtml(title="Copyright", file_name="copyright.xhtml", lang="en")
         copy_page.content = f"""
@@ -42,8 +52,9 @@ class BookBuilder:
         
         for i, ch in enumerate(self.chapters):
             chapter = epub.EpubHtml(title=ch["title"], file_name=f"chap_{i+1}.xhtml", lang="en")
-            content_html = ch["content"].replace("\n", "</p><p>")
-            chapter.content = f"<h1>{ch['title']}</h1><p>{content_html}</p>"
+            # Convert Markdown to HTML
+            content_html = markdown.markdown(ch["content"])
+            chapter.content = f"<h1>{ch['title']}</h1>{content_html}"
             book.add_item(chapter)
             spine.append(chapter)
 
@@ -56,9 +67,14 @@ class BookBuilder:
     def generate_pdf(self, output_path):
         pdf = FPDF()
         pdf.set_auto_page_break(auto=True, margin=15)
-        pdf.add_page()
         
         # Title Page
+        pdf.add_page()
+        if self.cover_image and os.path.exists(self.cover_image):
+            # Try to fit cover image on first page
+            pdf.image(self.cover_image, x=10, y=10, w=190)
+            pdf.add_page()
+
         pdf.set_font("Arial", "B", 24)
         pdf.cell(200, 40, self.title, ln=True, align="C")
         pdf.set_font("Arial", "I", 16)
@@ -77,8 +93,12 @@ class BookBuilder:
             pdf.set_font("Arial", "B", 18)
             pdf.cell(0, 10, ch["title"], ln=True)
             pdf.ln(10)
+            
+            # Use write_html to handle basic markdown-to-html conversion for FPDF
+            # FPDF2 supports basic HTML tags with write_html
+            html_content = markdown.markdown(ch["content"])
             pdf.set_font("Arial", "", 12)
-            pdf.multi_cell(0, 10, ch["content"])
+            pdf.write_html(html_content)
             
             # Footer on every page
             pdf.set_y(-15)
@@ -88,12 +108,12 @@ class BookBuilder:
         pdf.output(output_path)
         return output_path
 
-def create_ebook_files(title, author, content_list, base_name="ebook"):
+def create_ebook_files(title, author, content_list, base_name="ebook", cover_image=None):
     """
     Helper to create both formats.
     content_list: List of dicts with 'title' and 'content'.
     """
-    builder = BookBuilder(title, author)
+    builder = BookBuilder(title, author, cover_image=cover_image)
     for item in content_list:
         builder.add_chapter(item["title"], item["content"])