Merge pull request #143 from abilash-dev/master

Feature upgrade: DiscordChatExporterPy 2.9.1

Author: doluk

README.md

@@ -362,6 +362,50 @@ async def save(ctx: commands.Context):
 
     await ctx.send(file=transcript_file)
 
+```
+</details>
+
+<details><summary>AttachmentToWebhookHandler</summary>
+
+Assuming you want to store your attachments in a discord channel using webhook, you can use the `AttachmentToWebhookHandler`. 
+Please note that discord recent changes regarding content links will result in the attachments links being broken 
+after 24 hours. While this is therefor not a recommended way to store your attachments, it should give you a good 
+idea how to perform asynchronous storing of the attachments.
+
+```python
+import io
+import discord
+from discord.ext import commands
+import chat_exporter
+from chat_exporter import AttachmentToWebhookHandler
+
+...
+
+# Establish the webhook handler
+webhook_handler = AttachmentToWebhookHandler(
+    webhook_link="https://discord.com/api/webhooks/....",
+)
+
+@bot.command()
+async def save(ctx: commands.Context):
+    transcript = await chat_exporter.export(
+        ctx.channel,
+        attachment_handler=webhook_handler,
+    )
+
+    if transcript is None:
+        return
+    
+    # Due to Discord webhook file size limits (8MB),
+    # Attachments larger than 8MB are not attached directly.
+    # Instead, it stores a placeholder image saying "Attachment size is too high".
+    transcript_file = discord.File(
+        io.BytesIO(transcript.encode()),
+        filename=f"transcript-{ctx.channel.name}.html",
+    )
+
+    await ctx.send(file=transcript_file)
+
 ```
 </details>
 </ol>

chat_exporter/__init__.py

@@ -4,6 +4,7 @@
     quick_export,
     AttachmentHandler,
     AttachmentToLocalFileHostHandler,
+    AttachmentToWebhookHandler,
     AttachmentToDiscordChannelHandler)
 
 __version__ = "2.9.0"
@@ -14,5 +15,6 @@
     quick_export,
     AttachmentHandler,
     AttachmentToLocalFileHostHandler,
+    AttachmentToWebhookHandler,
     AttachmentToDiscordChannelHandler,
 )

chat_exporter/chat_exporter.py

@@ -4,7 +4,7 @@
 
 from chat_exporter.construct.transcript import Transcript
 from chat_exporter.ext.discord_import import discord
-from chat_exporter.construct.attachment_handler import AttachmentHandler, AttachmentToLocalFileHostHandler, AttachmentToDiscordChannelHandler
+from chat_exporter.construct.attachment_handler import AttachmentHandler, AttachmentToLocalFileHostHandler, AttachmentToDiscordChannelHandler, AttachmentToWebhookHandler
 
 
 async def quick_export(

chat_exporter/construct/attachment_handler.py

@@ -4,6 +4,8 @@
 from typing import Union
 import urllib.parse
 
+import asyncio
+import os
 
 import aiohttp
 from chat_exporter.ext.discord_import import discord
@@ -68,3 +70,37 @@ async def process_asset(self, attachment: discord.Attachment) -> discord.Attachm
 		except discord.errors.HTTPException as e:
 			# discords http errors, including missing permissions
 			raise e
+		
+class AttachmentToWebhookHandler(AttachmentHandler):
+	"""Save the attachment to a discord channel using webhook and embed the assets in the transcript from there."""
+
+	def __init__(self, webhook_link: str) -> None:
+		self.webhook_link = webhook_link
+		self.size_limit = 8 * 1024 * 1024 # 8 MB = 8 * 1024 KB * 1024 B
+		self.placeholder_path = os.path.join(os.path.dirname(__file__), "too_large.png")
+
+	async def process_asset(self, attachment: discord.Attachment) -> discord.Attachment:
+		"""Implement this to process the asset and return a url to the stored attachment.
+		:param attachment: discord.Attachment
+		:return: str"""
+		try:  
+			if attachment.size > self.size_limit:
+				file = discord.File(self.placeholder_path, filename="too_large.png")
+			else:
+				file = await attachment.to_file()
+				
+			async with aiohttp.ClientSession() as session:
+				webhook = discord.Webhook.from_url(self.webhook_link, session=session)
+				for i in range(3):
+					try:
+						message = await webhook.send(file=file, wait=True)
+						break
+					except aiohttp.ClientConnectionError:
+						print(f"Retry {i+1}/3 | Error - Webhook connection failed.")
+						await asyncio.sleep(3) # to prevent frequent retries on connection error
+
+		except discord.errors.HTTPException as e:
+			# discords http errors, including missing permissions
+			raise e
+		else:
+			return message.attachments[0]

chat_exporter/construct/message.py

@@ -24,6 +24,7 @@
     message_content,
     message_reference,
     message_reference_unknown,
+    message_reference_forwarded,
     message_interaction,
     img_attachment,
     start_message,
@@ -84,6 +85,14 @@ def __init__(
 
         self.message_created_at, self.message_edited_at = self.set_time()
         self.meta_data = meta_data
+        self.forwarded = False
+
+    def get_message_snapshots(self):
+        if hasattr(self.message, "message_snapshots"):
+            return self.message.message_snapshots
+        elif hasattr(self.message, "snapshots"):
+            return self.message.snapshots
+        return []
 
     async def construct_message(
         self,
@@ -149,17 +158,28 @@ async def build_meta_data(self):
             ]
 
     async def build_content(self):
-        if not self.message.content:
+        if not self.message.content and not self.get_message_snapshots():
             self.message.content = ""
             return
 
         if self.message_edited_at:
             self.message_edited_at = _set_edit_at(self.message_edited_at)
 
-        self.message.content = html.escape(self.message.content)
+        snapshots = self.get_message_snapshots()
+        if snapshots:
+            combined = f"{self.message.content} {' '.join(s.content for s in snapshots if hasattr(s, 'content'))}"
+            self.forwarded = True
+        else:
+            combined = self.message.content
+
+        combined = html.escape(combined or "")
+
+        if self.forwarded:
+            combined = f'<div class="quote">{combined}</div>'
+
         self.message.content = await fill_out(self.guild, message_content, [
-            ("MESSAGE_CONTENT", self.message.content, PARSE_MODE_MARKDOWN),
-            ("EDIT", self.message_edited_at, PARSE_MODE_NONE)
+            ("MESSAGE_CONTENT", combined, PARSE_MODE_MARKDOWN),
+            ("EDIT", self.message_edited_at, PARSE_MODE_NONE),
         ])
 
     async def build_reference(self):
@@ -174,6 +194,9 @@ async def build_reference(self):
                 message: discord.Message = await self.message.channel.fetch_message(self.message.reference.message_id)
             except (discord.NotFound, discord.HTTPException) as e:
                 self.message.reference = ""
+                if self.forwarded:
+                    self.message.reference = message_reference_forwarded
+                    return
                 if isinstance(e, discord.NotFound):
                     self.message.reference = message_reference_unknown
                 return
@@ -251,13 +274,30 @@ async def build_interaction(self):
         ])
 
     async def build_sticker(self):
-        if not self.message.stickers or not hasattr(self.message.stickers[0], "url"):
+        sticker = None
+        sticker_image_url = None
+        
+        if self.message.stickers and hasattr(self.message.stickers[0], "url"):
+            sticker_image_url = self.message.stickers[0].url
+        if not sticker_image_url:
+            for snapshot in self.get_message_snapshots():
+                if hasattr(snapshot, "stickers") and snapshot.stickers and hasattr(snapshot.stickers[0], "url"):
+                    sticker_image_url = snapshot.stickers[0].url
+                    self.message.reference = message_reference_forwarded
+                    break
+
+        if not sticker_image_url:
             return
-
-        sticker_image_url = self.message.stickers[0].url
+            
 
         if sticker_image_url.endswith(".json"):
-            sticker = await self.message.stickers[0].fetch()
+            try:
+                sticker = await self.message.stickers[0].fetch()
+            except:
+                for snapshot in self.get_message_snapshots():
+                    if hasattr(snapshot, "stickers") and snapshot.stickers and hasattr(snapshot.stickers[0], "url"):
+                        sticker = await snapshot.stickers[0].fetch()
+                        break
             sticker_image_url = (
                 f"https://cdn.jsdelivr.net/gh/mahtoid/DiscordUtils@master/stickers/{sticker.pack_id}/{sticker.id}.gif"
             )
@@ -271,14 +311,34 @@ async def build_assets(self):
         for e in self.message.embeds:
             self.embeds += await Embed(e, self.guild).flow()
 
+        for snapshot in self.get_message_snapshots():
+            if hasattr(snapshot, "embeds"):
+                for se in snapshot.embeds:
+                    self.embeds += await Embed(se, self.guild).flow()
+                    self.message.reference = message_reference_forwarded
+
         for a in self.message.attachments:
             if self.attachment_handler and isinstance(self.attachment_handler, AttachmentHandler):
                 a = await self.attachment_handler.process_asset(a)
             self.attachments += await Attachment(a, self.guild).flow()
+        
+        for snapshot in self.get_message_snapshots():
+            if hasattr(snapshot, "attachments"):
+                for sa in snapshot.attachments:
+                    if self.attachment_handler:
+                        sa = await self.attachment_handler.process_asset(sa)
+                    self.attachments += await Attachment(sa,self.guild).flow()
+                    self.message.reference = message_reference_forwarded
 
         for c in self.message.components:
             self.components += await Component(c, self.guild).flow()
 
+        for snapshot in self.get_message_snapshots():
+            if hasattr(snapshot, "components"):
+                for ac in snapshot.components:
+                    self.components += await Component(ac,self.guild).flow()
+                    self.message.reference = message_reference_forwarded
+
         for r in self.message.reactions:
             self.reactions += await Reaction(r, self.guild).flow()
 
@@ -497,4 +557,4 @@ async def gather_messages(
         previous_message = message
 
     message_html += "</div>"
-    return message_html, meta_data
+    return message_html, meta_data

chat_exporter/construct/too_large.png

@@ -1,6 +1,6 @@
-import datetime
 import html
 import traceback
+from datetime import datetime
 
 import re
 from typing import List, Optional
@@ -32,8 +32,8 @@ def __init__(
         pytz_timezone,
         military_time: bool,
         fancy_times: bool,
-        before: Optional[datetime.datetime],
-        after: Optional[datetime.datetime],
+        before: Optional[datetime],
+        after: Optional[datetime],
         support_dev: bool,
         bot: Optional[discord.Client],
         attachment_handler: Optional[AttachmentHandler],
@@ -79,9 +79,9 @@ async def export_transcript(self, message_html: str, meta_data: str):
 
         timezone = pytz.timezone(self.pytz_timezone)
         if self.military_time:
-            time_now = datetime.datetime.now(timezone).strftime("%e %B %Y at %H:%M:%S (%Z)")
+            time_now = datetime.now(timezone).strftime("%e %B %Y at %H:%M:%S (%Z)")
         else:
-            time_now = datetime.datetime.now(timezone).strftime("%e %B %Y at %I:%M:%S %p (%Z)")
+            time_now = datetime.now(timezone).strftime("%e %B %Y at %I:%M:%S %p (%Z)")
 
         meta_data_html: str = ""
         for data in meta_data:

chat_exporter/construct/transcript.py

@@ -66,6 +66,7 @@ def read_file(filename):
 message_thread_remove = read_file(dir_path + "/html/message/thread_remove.html")
 message_thread_add = read_file(dir_path + "/html/message/thread_add.html")
 message_reference_unknown = read_file(dir_path + "/html/message/reference_unknown.html")
+message_reference_forwarded = read_file(dir_path + "/html/message/reference_forwarded.html")
 message_body = read_file(dir_path + "/html/message/message.html")
 end_message = read_file(dir_path + "/html/message/end.html")
 meta_data_temp = read_file(dir_path + "/html/message/meta.html")

chat_exporter/ext/html_generator.py

@@ -14,18 +14,27 @@
     <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
     <meta name="viewport" content="width=device-width" />
     <meta name="title" content="{{SERVER_NAME_SAFE}} - {{CHANNEL_NAME_SAFE}}">
-    <meta name="description" content="Transcript of channel {{CHANNEL_NAME_SAFE}} ({{CHANNEL_ID}}) from {{SERVER_NAME_SAFE}} ({{GUILD_ID}}) with {{MESSAGE_COUNT}} messages. This transcript was generated on {{DATE_TIME}}.">
+    <meta name="description" content="Channel: {{CHANNEL_NAME_SAFE}} ({{CHANNEL_ID}})
+                                    Server: {{SERVER_NAME_SAFE}} ({{GUILD_ID}})
+                                    Message Count: {{MESSAGE_COUNT}} Messages
+                                    Generated on: {{DATE_TIME}}"/>
     <meta name="theme-color" content="#638dfc" />
 
     <!-- Open Graph / Facebook -->
     <meta property="og:type" content="website" />
     <meta property="og:title" content="{{SERVER_NAME_SAFE}} - {{CHANNEL_NAME_SAFE}}" />
-    <meta property="og:description" content="Transcript of channel {{CHANNEL_NAME_SAFE}} ({{CHANNEL_ID}}) from {{SERVER_NAME_SAFE}} ({{GUILD_ID}}) with {{MESSAGE_COUNT}} messages. This transcript was generated on {{DATE_TIME}}." />
+    <meta property="og:description" content="Channel: {{CHANNEL_NAME_SAFE}} ({{CHANNEL_ID}})
+                                    Server: {{SERVER_NAME_SAFE}} ({{GUILD_ID}})
+                                    Message Count: {{MESSAGE_COUNT}} Messages
+                                    Generated on: {{DATE_TIME}}"/>
 
     <!-- Twitter -->
     <meta name="twitter:card" content="summary" />
     <meta name='twitter:title' content="{{SERVER_NAME_SAFE}} - {{CHANNEL_NAME_SAFE}}" />
-    <meta name='twitter:description' content="Transcript of channel {{CHANNEL_NAME_SAFE}} ({{CHANNEL_ID}}) from {{SERVER_NAME_SAFE}} ({{GUILD_ID}}) with {{MESSAGE_COUNT}} messages. This transcript was generated on {{DATE_TIME}}." />
+    <meta name='twitter:description' content="Channel: {{CHANNEL_NAME_SAFE}} ({{CHANNEL_ID}})
+                                    Server: {{SERVER_NAME_SAFE}} ({{GUILD_ID}})
+                                    Message Count: {{MESSAGE_COUNT}} Messages
+                                    Generated on: {{DATE_TIME}}"/>
 
 
     <style>

chat_exporter/html/base.html

@@ -0,0 +1,3 @@
+<div class="chatlog__followup">
+    <span class="chatlog__reference-forwarded"><em>Forwarded message.</em></span>
+</div>