Feature: docs/docx file support adding

audiobook/config.py

@@ -1,4 +1,4 @@
-supported_file_types = (".pdf", ".txt", ".epub")
+supported_file_types = (".pdf", ".txt", ".epub", ".docx", ".doc")
 speed_dict = {
     "slow": 100,
     "normal": 150,

audiobook/main.py

@@ -13,6 +13,7 @@
 from audiobook.utils import mobi_to_json
 from audiobook.utils import epub_to_json
 from audiobook.utils import html_to_json
+from audiobook.utils import docs_to_json
 
 
 from audiobook.config import speed_dict
@@ -82,6 +83,8 @@ def create_json_book(self, input_book_path, password=None):
             json_book, metadata = mobi_to_json(input_book_path)
         elif input_book_path.startswith("http"):
             json_book, metadata = html_to_json(input_book_path)
+        elif input_book_path.endswith((".docx", ".doc")):
+            json_book, metadata = docs_to_json(input_book_path)
 
         write_json_file(json_book, os.path.join(BOOK_DIR, json_filename))
 

audiobook/utils.py

@@ -1,5 +1,7 @@
 import re
 import os
+
+import docx2txt
 import mobi
 import json
 import PyPDF2
@@ -110,10 +112,19 @@ def txt_to_json(input_book_path):
     metadata["book_name"] = book_name
     return json_book, metadata
 
-
 def docs_to_json(input_book_path):
     """ sub method to create json book from docs file """
-    pass
+    metadata = {}
+    json_book = {}
+    book_name = os.path.basename(input_book_path).split(".")[0]
+    book_data = docx2txt.process(input_book_path)
+    for i in range(0, len(book_data), 2000):
+        page_num = i // 2000
+        json_book[str(page_num)] = book_data[i:i + 2000]
+
+    metadata["pages"] = len(json_book)
+    metadata["book_name"] = book_name
+    return json_book, metadata
 
 def epub_to_json(input_book_path):
     metadata = {}

requirements.txt

@@ -4,3 +4,6 @@ ebooklib==0.17.1
 beautifulsoup4==4.11.1
 html2text==2020.1.16
 mobi==0.3.3
+docx2txt>=0.8
+requests>=2.28.1
+tqdm>=4.64.1