add code file

src/ebook/extract_book_code.py

@@ -9,14 +9,17 @@ from .ebook_get_request import get_chapter_content
 
 def extract_code():
 
-    book_mapping_path = "data/book_mapping.json"
-    with open(book_mapping_path, "r") as f:
-        book_mapping = json.load(f)
+    # book_mapping_path = "data/book_mapping.json"
+    # with open(book_mapping_path, "r") as f:
+    #     book_mapping = json.load(f)
+    book_mapping = {
+        "全程软件测试（第3版）": "825acb73c85c4c4bb9632afe858bc097",
+    }
     for book_idx, book_name in enumerate(book_mapping.keys()):
         if book_name == 'Python编程无师自通':
             continue
-        book_dir_name = '{}.{}'.format(book_idx + 1, book_name)
-        book_dir = os.path.join('data/books', book_dir_name)
+        book_dir_name = book_name
+        book_dir = os.path.join('data', book_dir_name)
         if not os.path.exists(book_dir):
             os.mkdir(book_dir)
         print(book_dir_name)
@@ -73,10 +76,13 @@ def extract_code():
                     section_dir_list.append(section_dir)
                 for idx, section_content in enumerate(section_content_list):
                     if idx == 0:
-                        save_dir = os.path.join(chapter_dir, 'text.html')
+                        html_save_path = os.path.join(chapter_dir, 'text.html')
                     else:
-                        save_dir = os.path.join(section_dir_list[idx - 1],
-                                                'text.html')
+                        html_save_path = os.path.join(
+                            section_dir_list[idx - 1], 'text.html')
+                    with open(html_save_path, 'w', encoding='utf-8') as f:
+                        f.write(section_content)
+
                     code_list = re.findall(r'<code>(.*?)</code>',
                                            section_content, re.S)