hoelee/Telethon
1
0
Fork 0
mirror of https://github.com/LonamiWebs/Telethon.git synced 2025-06-19 11:36:41 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Add batch_size and wait_time to get_message_history (#565)

Browse Source
This commit is contained in:
Matteo 2018-01-27 15:29:38 -05:00 committed by Lonami
parent 3b8365f871
commit 067006d248
1 changed files with 23 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
telethon/telegram_client.py
View File

@ -646,7 +646,8 @@ class TelegramClient(TelegramBareClient):
return self(messages.DeleteMessagesRequest(message_ids, revoke=revoke)) return self(messages.DeleteMessagesRequest(message_ids, revoke=revoke))
def get_message_history(self, entity, limit=20, offset_date=None, def get_message_history(self, entity, limit=20, offset_date=None,
offset_id=0, max_id=0, min_id=0, add_offset=0): offset_id=0, max_id=0, min_id=0, add_offset=0,
batch_size=100, wait_time=1):
""" """
Gets the message history for the specified entity Gets the message history for the specified entity
@ -681,6 +682,15 @@ class TelegramClient(TelegramBareClient):
Additional message offset (all of the specified offsets + Additional message offset (all of the specified offsets +
this offset = older messages). this offset = older messages).
batch_size (:obj:`int`):
Number of messages to be returned by each Telegram API
"getHistory" request. Notice that Telegram has a hard limit
of 100 messages per API call.
wait_time (:obj:`int`):
Wait time between different "getHistory" requests. Use this
parameter to avoid hitting the "FloodWaitError" (see note below).
Returns: Returns:
A list of messages with extra attributes: A list of messages with extra attributes:
@ -689,6 +699,16 @@ class TelegramClient(TelegramBareClient):
* ``.fwd_from.sender`` = if fwd_from, who sent it originally. * ``.fwd_from.sender`` = if fwd_from, who sent it originally.
* ``.fwd_from.channel`` = if fwd_from, original channel. * ``.fwd_from.channel`` = if fwd_from, original channel.
* ``.to`` = entity to which the message was sent. * ``.to`` = entity to which the message was sent.
Notes:
Telegram limit for "getHistory" requests seems to be 3000 messages
within 30 seconds. Therefore, please adjust "batch_size" and
"wait_time" parameters accordingly to avoid incurring into a
"FloodWaitError". For example, if you plan to retrieve more than 3000
messages (i.e. limit=3000 or None) in batches of 100 messages
(i.e. batch_size=100) please make sure to select a wait time of at
least one second (i.e. wait_time=1).
""" """
entity = self.get_input_entity(entity) entity = self.get_input_entity(entity)
limit = float('inf') if limit is None else int(limit) limit = float('inf') if limit is None else int(limit)
@ -705,7 +725,7 @@ class TelegramClient(TelegramBareClient):
entities = {} entities = {}
while len(messages) < limit: while len(messages) < limit:
# Telegram has a hard limit of 100 # Telegram has a hard limit of 100
real_limit = min(limit - len(messages), 100) real_limit = min(limit - len(messages), min(batch_size,100))
result = self(GetHistoryRequest( result = self(GetHistoryRequest(
peer=entity, peer=entity,
limit=real_limit, limit=real_limit,
@ -738,8 +758,7 @@ class TelegramClient(TelegramBareClient):
# batches of 100 messages each request (since the FloodWait was # batches of 100 messages each request (since the FloodWait was
# of 30 seconds). If the limit is greater than that, we will # of 30 seconds). If the limit is greater than that, we will
# sleep 1s between each request. # sleep 1s between each request.
if limit > 3000: time.sleep(wait_time)
time.sleep(1)
# Add a few extra attributes to the Message to make it friendlier. # Add a few extra attributes to the Message to make it friendlier.
messages.total = total_messages messages.total = total_messages