RISE/Resume-python
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update gai

Browse Source 
filiter no message channel
This commit is contained in:
fxxk-research
2025-06-26 13:36:15 +08:00
committed by GitHub
parent aa9b756d37
commit 30bda684fe
1 changed files with 7 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
gai
View File

@@ -133,7 +133,7 @@ async def download_media(channel, message):
media_file_name = message.file.name or f"{message.id}.{message.file.ext if message.file.ext else 'bin'}"
if not media_file_name:
print(f"Unable to determine file name for message {message.id}. Skipping download.")
# print(f"Unable to determine file name for message {message.id}. Skipping download.")
logging.info(f"Unable to determine file name for message {message.id}. Skipping download.")
return None
@@ -153,7 +153,7 @@ async def download_media(channel, message):
logging.info("message.media为MessageMediaDocument")
media_path = await message.download_media(file=media_folder)
if media_path:
print(f"Successfully downloaded media to: {media_path}")
logging.info(f"Successfully downloaded media to: {media_path}")
break
except (TimeoutError, aiohttp.ClientError, RPCError) as e:
@@ -263,12 +263,16 @@ async def continuous_scraping():
async def export_data():
for channel in state['channels']:
if state['channels'][channel] == 0:
print(f"No messages to export for channel {channel}. Skipping export.")
continue
export_to_csv(channel)
export_to_json(channel)
def export_to_csv(channel):
db_file = os.path.join(channel, f'{channel}.db')
csv_file = os.path.join(channel, f'{channel}.csv')
# print(f"Trying to open database file: {db_file}")
conn = sqlite3.connect(db_file)
c = conn.cursor()
c.execute('SELECT * FROM messages')
@@ -376,7 +380,7 @@ async def manage_channels():
#读取csv的第二列
channel_list = set(state['channels'].keys())
print("Reading csv file...")
with open('tudou.csv', 'r') as f:
with open('username.csv', 'r') as f:
reader = csv.reader(f)
for row in tqdm(reader, desc="Processing channels"):
row[1] = row[1].strip().lstrip('@')