Make structure of docx c as epub s

src/docx_converter/image_processing.py

@@ -0,0 +1,39 @@
+import os
+import logging
+import pathlib
+from shutil import copyfile
+
+
+def process_images(body_tag, access, html_path, book_id):
+    """
+    Function to process <img> tag. Img should be sent Amazon S3 and then return new tag with valid link.
+    For now images are moved to one folder.
+    """
+    img_tags = body_tag.find_all('img')
+
+    if len(img_tags):
+        if access is None:
+            folder_path = os.path.dirname(
+                os.path.dirname(os.path.abspath(__file__)))
+            new_path = pathlib.Path(os.path.join(
+                folder_path, f'json/img_{book_id}/'))
+            new_path.mkdir(exist_ok=True)
+
+        for img in img_tags:
+            img_name = img.attrs.get('src')
+            # quick fix for bad links
+            if (len(img_name) >= 3) and img_name[:3] == '../':
+                img_name = img_name[3:]
+
+            img_path = pathlib.Path(f'{html_path.parent}', f'{img_name}')
+
+            if access is not None:
+                link = access.send_image(img_path, doc_id=book_id)
+                img.attrs['src'] = link
+            else:
+                img_size = os.path.getsize(img_path)
+                new_img_path = new_path / img_name
+                copyfile(img_path, new_img_path)
+                img.attrs["src"] = str(new_img_path)
+
+    return img_tags