From 4854929a1ddca8dad7e12d294c8b455c1557d13a Mon Sep 17 00:00:00 2001
From: msramalho <19508417+msramalho@users.noreply.github.com>
Date: Thu, 2 Feb 2023 13:49:56 +0000
Subject: [PATCH] thumbnail and bot token

---
 src/auto_archiver/archivers/telethon_archiver.py | 5 +++--
 src/auto_archiver/core/metadata.py               | 5 +++++
 src/auto_archiver/databases/gsheet_db.py         | 4 ++++
 3 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/src/auto_archiver/archivers/telethon_archiver.py b/src/auto_archiver/archivers/telethon_archiver.py
index 59369ca..f30f2a4 100644
--- a/src/auto_archiver/archivers/telethon_archiver.py
+++ b/src/auto_archiver/archivers/telethon_archiver.py
@@ -28,7 +28,7 @@ class TelethonArchiver(Archiver):
         return {
             "api_id": {"default": None, "help": "telegram API_ID value, go to https://my.telegram.org/apps"},
             "api_hash": {"default": None, "help": "telegram API_HASH value, go to https://my.telegram.org/apps"},
-            # "bot_token": {"default": None, "help": "optional, but allows access to more content such as large videos, talk to @botfather"},
+            "bot_token": {"default": None, "help": "optional, but allows access to more content such as large videos, talk to @botfather"},
             "session_file": {"default": "secrets/anon", "help": "optional, records the telegram login session for future usage, '.session' will be appended to the provided value."},
             "join_channels": {"default": True, "help": "disables the initial setup with channel_invites config, useful if you have a lot and get stuck"},
             "channel_invites": {
@@ -111,7 +111,8 @@ class TelethonArchiver(Archiver):
         result = Metadata()
 
         # NB: not using bot_token since then private channels cannot be archived: self.client.start(bot_token=self.bot_token)
-        with self.client.start():
+        # with self.client.start():
+        with self.client.start(bot_token=self.bot_token):
             try:
                 post = self.client.get_messages(chat,   ids=post_id)
             except ValueError as e:
diff --git a/src/auto_archiver/core/metadata.py b/src/auto_archiver/core/metadata.py
index 7a741f7..00eefe9 100644
--- a/src/auto_archiver/core/metadata.py
+++ b/src/auto_archiver/core/metadata.py
@@ -122,6 +122,11 @@ class Metadata:
         for m in self.media:
             if m.get("id") == id: return m
         return default
+    
+    def get_first_image(self, default=None) -> Media:
+        for m in self.media:
+            if "image" in m.mimetype: return m
+        return default
 
     def set_final_media(self, final: Media) -> Metadata:
         """final media is a special type of media: if you can show only 1 this is it, it's useful for some DBs like GsheetDb"""
diff --git a/src/auto_archiver/databases/gsheet_db.py b/src/auto_archiver/databases/gsheet_db.py
index 8c711e8..30b37b2 100644
--- a/src/auto_archiver/databases/gsheet_db.py
+++ b/src/auto_archiver/databases/gsheet_db.py
@@ -70,6 +70,10 @@ class GsheetsDb(Database):
         if (screenshot := item.get_media_by_id("screenshot")):
             batch_if_valid('screenshot', "\n".join(screenshot.urls))
 
+        if (thumbnail := item.get_first_image("thumbnail")):
+            batch_if_valid('thumbnail', f'=IMAGE("{thumbnail.urls[0]}")')
+
+
         if (browsertrix := item.get_media_by_id("browsertrix")):
             batch_if_valid('wacz', "\n".join(browsertrix.urls))
             batch_if_valid('replaywebpage', "\n".join([f'https://replayweb.page/?source={quote(wacz)}#view=pages&url={quote(item.get_url())}' for wacz in browsertrix.urls]))