feat(parsing): append enclosures to Telegraph post

Signed-off-by: Rongrong <[email protected]>

docs/CHANGELOG.md

@@ -5,6 +5,7 @@
 ### Enhancements
 
 - **`wsrv.nl` via relay**: Try to use `wsrv.nl` (environment variable `IMAGES_WESERV_NL`) via the media relay server (environment variable `IMG_RELAY_SERVER`). This is a workaround for images from domains/TLDs banned by `wsrv.nl` or CDNs that ban `wsrv.nl`. It can hopefully reduce the frequency of seeing "invalid media" in messages since RSStT uses `wsrv.nl` heavily to convert images into formats accepted by Telegram DCs. See also [#369](https://github.com/Rongronggg9/RSS-to-Telegram-Bot/issues/369).
+- **Append enclosures to Telegraph post**: Append enclosures (if any) to Telegraph post if any. Previously, enclosures can only be sent in Telegram messages, but not in Telegraph posts.
 
 ### Bug fixes
 

docs/CHANGELOG.zh.md

@@ -5,6 +5,8 @@
 ### 增强
 
 - **经反代的 `wsrv.nl`: 尝试通过媒体反代服务器 (环境变量 `IMG_RELAY_SERVER`) 使用 `wsrv.nl` (环境变量 `IMAGES_WESERV_NL`)。这是对那些来自被 `wsrv.nl` 封禁的域名或将 `wsrv.nl` 封禁的 CDN 的图片的变通解决方案。考虑到 RSStT 大量使用 `wsrv.nl` 将图片转换为 Telegram DC 所接受的格式，这有望减少在消息中见到 "Invalid media" 的频率。另请参阅 [#369](https://github.com/Rongronggg9/RSS-to-Telegram-Bot/issues/369)。
+- - **Append enclosures to Telegraph post**: Append enclosures (if any) to Telegraph post if any. Previously, enclosures can only be sent in Telegram messages, but not in Telegraph posts.
+- **将 enclosure 附加到 Telegraph 文章**: 如果有的话，将 enclosure (附件) 附加到 Telegraph 文章。先前，enclosure 只能在 Telegram 消息中发送，而无法在 Telegraph 文章中发送。
 
 ### Bug 修复
 

src/parsing/medium.py

@@ -109,6 +109,10 @@ async def fallback(self, reason: Union[Exception, str] = None) -> bool:
     def type_fallback_chain(self) -> Optional[AbstractMedium]:
         pass
 
+    @abstractmethod
+    def get_multimedia_html(self) -> Optional[str]:
+        pass
+
     @abstractmethod
     def get_link_html_node(self) -> Optional[Text]:
         pass
@@ -274,6 +278,12 @@ def type_fallback_chain(self) -> Optional[Medium]:
              else None)
         ) if not self.drop_silently else None
 
+    def get_multimedia_html(self) -> str:
+        url = self.original_urls[0]
+        if isAbsoluteHttpLink(url):
+            return f'<a href="{url}">{self.type}</a>'
+        return f'{self.type} (<code>{url}</code>)'
+
     def get_link_html_node(self) -> Text:
         url = self.original_urls[0]
         if isAbsoluteHttpLink(url):
@@ -566,6 +576,9 @@ def __init__(self, urls: Union[str, list[str]]):
                          for i in range(min(len(urls_not_weserv), 3)))  # use for final fallback
         self.chosen_url = self.urls[0]
 
+    def get_multimedia_html(self) -> str:
+        return f'<img src="{self.original_urls[0]}" />'
+
     async def change_server(self) -> bool:
         if weserv_relayed := insert_image_relay_into_weserv_url(self.chosen_url):
             # success if:
@@ -598,6 +611,9 @@ class Video(Medium):
     typeFallbackAllowSelfUrls = False
     inputMediaExternalType = InputMediaDocumentExternal
 
+    def get_multimedia_html(self) -> str:
+        return f'<video src="{self.original_urls[0]}" />'
+
 
 class Audio(Medium):
     type = AUDIO
@@ -659,6 +675,9 @@ def __init__(self, file: Union[bytes, BytesIO, Callable, Awaitable], file_name:
         self.file_name = file_name
         self.uploaded_file: Union[InputFile, InputFileBig, None] = None
 
+    def get_multimedia_html(self) -> None:
+        return None
+
     def telegramize(self) -> Optional[InputMediaUploadedPhoto]:
         if self.valid is None:
             raise RuntimeError('validate() must be called before telegramize()')

src/parsing/post_formatter.py

@@ -11,7 +11,7 @@
 from .splitter import get_plain_text_length
 from .html_parser import parse
 from .html_node import *
-from .medium import Media, Image, Video, Audio, File, Animation, construct_weserv_url_convert_to_2560
+from .medium import Media, AbstractMedium, Image, Video, Audio, File, Animation, construct_weserv_url_convert_to_2560
 
 AUTO: Final = 0
 DISABLE: Final = -1
@@ -86,6 +86,7 @@ def __init__(self,
         self.parsed: bool = False
         self.html_tree: Optional[HtmlTree] = None
         self.media: Optional[Media] = None
+        self.enclosure_medium_l: Optional[list[AbstractMedium]] = None
         self.parsed_html: Optional[str] = None
         self.plain_length: Optional[int] = None
         self.telegraph_link: Optional[Union[str, False]] = None  # if generating failed, will be False
@@ -515,6 +516,7 @@ async def parse_html(self):
         self.html = parsed.parser.html  # use a validated HTML
         self.parsed = True
         if self.enclosures:
+            self.enclosure_medium_l = []
             for enclosure in self.enclosures:
                 # https://www.iana.org/assignments/media-types/media-types.xhtml
                 if not enclosure.url:
@@ -550,13 +552,17 @@ async def parse_html(self):
                 else:
                     medium = File(enclosure.url)
                 self.media.add(medium)
+                self.enclosure_medium_l.append(medium)
 
     async def telegraph_ify(self):
         if isinstance(self.telegraph_link, str) or self.telegraph_link is False:
             return self.telegraph_link
 
+        html = self.html
+        if self.enclosure_medium_l:
+            html += f"<p>{'<br>'.join(medium.get_multimedia_html() for medium in self.enclosure_medium_l)}</p>"
         try:
-            self.telegraph_link = await tgraph.TelegraphIfy(self.html,
+            self.telegraph_link = await tgraph.TelegraphIfy(html,
                                                             title=self.title,
                                                             link=self.link,
                                                             feed_title=self.feed_title,