Improve EPUB restoration, book terminology and Calibre QA workflow

src/preprocessing/text_extractor.py

@@ -3,6 +3,7 @@ from typing import List, Dict, Any, Optional
 from bs4 import BeautifulSoup
 from loguru import logger
 
+from src.common.html import parse_html, translation_targets
 from src.common.data_model import BookStructure, ManifestEntry, BookProfile
 from src.preprocessing.format_extractor import FormatExtractor
 from src.common.utils import setup_logger
@@ -56,10 +57,10 @@ class FineGrainedExtractor:
             doc_type = self._classify_document(file_path)
             
             # Parse HTML
-            soup = BeautifulSoup(resource.content, 'html.parser')
+            soup = parse_html(resource.content)
             target_tags = ['p', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'li']
             
-            for element in soup.find_all(target_tags):
+            for element in translation_targets(soup):
                 # Ensure element has ID (should have been done by Cleaner)
                 element_id = element.get('id')
                 if not element_id: