feat: add custom regular expression

README.md

@@ -265,6 +265,28 @@ def main():
     md_converter.convert(md_folders, output_directory="converted")
 
 
+if __name__ == "__main__":
+    main()
+```
+
+### Custom Regular Expression
+`imarkdown` use regular expression to find your images. It supports `![](image_url)` and `<img src="image_url"/>` format, but there are still some other format `imarkdown` can not find it.
+
+At this point, `imarkdown` supports custom regular expression to address this issue. You can customize a regular expression which can find your markdown image url and pass it to MdImageConverter. The following example show how to use it.
+
+```python
+from imarkdown import MdImageConverter, LocalFileAdapter, MdFolder
+
+
+def main():
+    custom_re = r"(?:!\[(.*?)\]\((.*?)\))|<img.*?src=[\'\"](.*?)[\'\"].*?>"
+    adapter = LocalFileAdapter()
+    md_converter = MdImageConverter(adapter=adapter)
+
+    md_folder = MdFolder(name="mds")
+    md_converter.convert(md_folder, output_directory="output_mds", re_rule=custom_re)
+
+
 if __name__ == "__main__":
     main()
 ```

README_zh.md

@@ -270,6 +270,30 @@ if __name__ == "__main__":
     main()
 ```
 
+### 自定义正则表达式
+
+`imarkdown`是使用正则表达式对image的url进行识别，当前支持`![](image_url)`和`<img src="image_url"/>`两种图片url的格式，当然，如果你的图片url很奇怪，有的时候`imarkdown`默认的正则表达式也无法识别出来。
+
+这个时候，你可以自定义一个可以识别你的图片的正则表达式，传入`imarkdown`进行识别，下面的示例展示了怎么使用自定义的正则表达式来识别图片。
+
+```python
+from imarkdown import MdImageConverter, LocalFileAdapter, MdFolder
+
+
+def main():
+    custom_re = r"(?:!\[(.*?)\]\((.*?)\))|<img.*?src=[\'\"](.*?)[\'\"].*?>"
+    adapter = LocalFileAdapter()
+    md_converter = MdImageConverter(adapter=adapter)
+
+    md_folder = MdFolder(name="mds")
+    md_converter.convert(md_folder, output_directory="output_mds", re_rule=custom_re)
+
+
+if __name__ == "__main__":
+    main()
+```
+
+
 ## 开发计划
 
 - [ ] 添加客户端支持
@@ -282,6 +306,8 @@ if __name__ == "__main__":
 - [ ] 提供文件自定义命名
 - [ ] 提供图片自定义格式化命名方式
 - [ ] 构建PDF转换器
+- [ ] 提供markdown其他元素的替换
+
 
 ## FAQ
 

imarkdown/converter.py

@@ -89,6 +89,9 @@ class BaseMdImageConverter(BaseModel):
     md_file_output_directory: Optional[str] = None
     """The storage directory of converted markdown file."""
     converted_md_file_name: Optional[str] = None
+    """The converted markdown file name."""
+    re_rule: str = r"(?:!\[(.*?)\]\((.*?)\))|<img.*?src=[\'\"](.*?)[\'\"].*?>"
+    """Default regular expression to find images, you can custom re_rule."""
 
     @root_validator(pre=True)
     def variables_check(
@@ -167,6 +170,7 @@ def convert(
         image_local_storage_directory: Optional[str] = None,
         output_md_directory: Optional[str] = None,
         is_local_images: Optional[bool] = None,
+        re_rule: Optional[str] = None,
         **kwargs,
     ):
         """Convert Markdown image url and generate a new Markdown file.
@@ -176,7 +180,8 @@ def convert(
             image_local_storage_directory(Optional[str]): Specified image storage path. You can pass an absolute or a
                 relative path. Default image directory path is the Markdown directory named `markdown_dir/images`.
             output_md_directory(Optional[str]): The storage directory of converted markdown file.
-            is_local_images:
+            re_rule(Optional[str]): Regular expression to find images, you can custom re_rule.
+            is_local_images: It is a local images.
             **kwargs:
                 enable_rename(bool): Default is true, it means the generated markdown file will receive a new name.
                 name_prefix(Optional[str]): Prefix name of generated markdown file.
@@ -189,6 +194,9 @@ def convert(
             return
         if is_local_images:
             self.is_local_images = is_local_images
+        if re_rule:
+            logger.debug(f"[imarkdown] reset regular expression <{re_rule}>")
+            self.re_rule = re_rule
 
         self.set_converted_md_file_name(md_file_path, **kwargs)
         self.set_md_file_original_directory(md_file_path)
@@ -212,7 +220,7 @@ def convert(
         _write_data(converted_md_path, modified_data)
         logger.info(f"[imarkdown] <{md_file_path}> converted task end")
 
-    def _find_img_and_replace(self, md_str: str) -> str:
+    def _find_img_and_replace(self, md_str: str, re_rule: Optional[str] = None) -> str:
         """Input original markdown str and replace images address
         It can find `[]()` type image url and `<img/>` type image url
 
@@ -223,7 +231,7 @@ def _find_img_and_replace(self, md_str: str) -> str:
             Markdown data for the image url has been changed.
         """
         _images = re.findall(
-            r"(?:!\[(.*?)\]\((.*?)\))|<img.*?src=[\'\"](.*?)[\'\"].*?>", md_str
+            self.re_rule, md_str
         )
 
         images = []
@@ -311,6 +319,15 @@ def convert(
         enable_save_images: bool = True,
         **kwargs,
     ):
+        """Markdown Image convert.
+
+        Args:
+            mediums(Union[MdFile, MdFolder, List[Union[MdFile, MdFolder]]]): MdFile or MdFolder you need to convert.
+            output_directory(Optional[str]): output directory
+            enable_save_images(bool): It is save image?
+            **kwargs:
+                re_rule(Optional[str]): custom regular expression to find specified element like image.
+        """
         def check_warning(medium: Union[MdFile, MdFolder]):
             if not output_directory and isinstance(medium, MdFolder):
                 raise ValueError(

imarkdown/schema.py

@@ -18,7 +18,7 @@
 class BaseMdMedium(BaseModel):
     name: str
     """markdown medium name"""
-    absolute_path_name: str
+    absolute_path_name: str = ""
     """path + name"""
     image_directory: Optional[str] = None
     """image storage path if it exists"""
@@ -32,7 +32,7 @@ class BaseMdMedium(BaseModel):
 
 
 class MdFile(BaseMdMedium):
-    absolute_path: str
+    absolute_path: str = ""
     """absolute path of markdown file"""
 
     def update_config(self, **kwargs):

setup.py

@@ -21,7 +21,7 @@
 
 setuptools.setup(
     name="imarkdown",
-    version="1.1.2",
+    version="1.2.1",
     author="Zeeland",
     author_email="zeeland@foxmail.com",
     description="A practical Markdown image url converter",