From 6aea13a56bb5f0978b941d2cc25dac901b53b3b9 Mon Sep 17 00:00:00 2001
From: Tyler Perkins <tperki17@kent.edu>
Date: Fri, 5 May 2023 10:32:03 -0400
Subject: [PATCH] Add script

---
 README.md       | 11 ++++++++++-
 output/.gitkeep |  0
 scrape.py       | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 58 insertions(+), 1 deletion(-)
 create mode 100644 output/.gitkeep
 create mode 100644 scrape.py

diff --git a/README.md b/README.md
index 66454d4..1bbec5e 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,12 @@
 # Discord-scraper
 
-Scrape a discord channel of its messages
\ No newline at end of file
+Scrape a discord channel of its messages
+
+## Usage
+
+```
+BOT_TOKEN='mydiscordbottoken' python3 ./scrape.py <channel_id> <output_file>
+```
+
+Note that BOT_TOKEN is from the environment. The output of the above command
+will be placed in the passes file. The output will be a json file
diff --git a/output/.gitkeep b/output/.gitkeep
new file mode 100644
index 0000000..e69de29
diff --git a/scrape.py b/scrape.py
new file mode 100644
index 0000000..c0e2638
--- /dev/null
+++ b/scrape.py
@@ -0,0 +1,48 @@
+import discord
+from discord.ext import commands
+import asyncio
+import json
+import sys
+
+BOT_TOKEN   = os.environ['BOT_TOKEN']
+CHANNEL_ID  = sys.argv[1]
+OUTPUT_FILE = sys.argv[2]
+
+intents = discord.Intents.default()
+intents.messages = True
+
+bot = commands.Bot(command_prefix='!', intents=intents)
+
+@bot.event
+async def on_ready():
+    print(f'{bot.user} has connected to Discord!')
+    channel = bot.get_channel(CHANNEL_ID)
+    if channel is None:
+        print(f'Channel with ID {CHANNEL_ID} not found. Make sure the bot has access to the channel.')
+        await bot.logout()
+        return
+
+    print(f'Downloading chat history from #{channel.name}...')
+    messages = []
+    count = 0
+    async for message in channel.history(limit=None):
+        print("#{} {} - '{}'".format(count, message.author, message.content))
+        messages.append({
+            'timestamp': message.created_at.isoformat(),
+            'content': message.content,
+            'author': str(message.author),
+            'messageId': str(message.id)
+            })
+        count = count + 1
+
+    print("Got {} messages.".format(count))
+
+    messages.reverse()
+
+    with open(OUTPUT_FILE, 'w', encoding='utf-8') as f:
+        json.dump(messages, f, ensure_ascii=False, indent=2)
+
+    print(f'Chat history saved to {OUTPUT_FILE}.')
+    exit()
+
+bot.run(BOT_TOKEN)