2017-06-09 17:13:39 +03:00
|
|
|
"""
|
|
|
|
Utilities for working with the Telegram API itself (such as handy methods
|
2018-09-22 20:18:42 +03:00
|
|
|
to convert between an entity like a User, Chat, etc. into its Input version)
|
2017-06-09 17:13:39 +03:00
|
|
|
"""
|
2018-08-01 00:23:52 +03:00
|
|
|
import base64
|
|
|
|
import binascii
|
2019-02-12 13:33:06 +03:00
|
|
|
import imghdr
|
|
|
|
import inspect
|
|
|
|
import io
|
2018-06-05 22:27:49 +03:00
|
|
|
import itertools
|
2019-03-04 10:50:33 +03:00
|
|
|
import logging
|
2017-10-01 14:24:04 +03:00
|
|
|
import math
|
2018-02-12 12:33:51 +03:00
|
|
|
import mimetypes
|
2018-03-15 11:52:45 +03:00
|
|
|
import os
|
2017-12-27 02:50:09 +03:00
|
|
|
import re
|
2018-08-01 00:23:52 +03:00
|
|
|
import struct
|
2018-03-15 11:52:45 +03:00
|
|
|
from mimetypes import guess_extension
|
2018-07-22 20:26:34 +03:00
|
|
|
from types import GeneratorType
|
2017-12-27 02:50:09 +03:00
|
|
|
|
2018-06-10 12:30:51 +03:00
|
|
|
from .extensions import markdown, html
|
2018-06-29 12:04:42 +03:00
|
|
|
from .helpers import add_surrogate, del_surrogate
|
2018-07-22 20:26:34 +03:00
|
|
|
from .tl import types
|
2016-10-09 13:57:38 +03:00
|
|
|
|
2018-07-15 12:31:14 +03:00
|
|
|
try:
|
|
|
|
import hachoir
|
|
|
|
import hachoir.metadata
|
|
|
|
import hachoir.parser
|
|
|
|
except ImportError:
|
|
|
|
hachoir = None
|
|
|
|
|
2019-01-23 16:37:28 +03:00
|
|
|
# Register some of the most common mime-types to avoid any issues.
|
|
|
|
# See https://github.com/LonamiWebs/Telethon/issues/1096.
|
|
|
|
mimetypes.add_type('image/png', '.png')
|
|
|
|
mimetypes.add_type('image/jpeg', '.jpeg')
|
2018-08-27 18:19:10 +03:00
|
|
|
mimetypes.add_type('image/webp', '.webp')
|
2019-01-23 16:37:28 +03:00
|
|
|
mimetypes.add_type('image/gif', '.gif')
|
|
|
|
mimetypes.add_type('image/bmp', '.bmp')
|
|
|
|
mimetypes.add_type('image/x-tga', '.tga')
|
|
|
|
mimetypes.add_type('image/tiff', '.tiff')
|
|
|
|
mimetypes.add_type('image/vnd.adobe.photoshop', '.psd')
|
|
|
|
|
|
|
|
mimetypes.add_type('video/mp4', '.mp4')
|
|
|
|
mimetypes.add_type('video/quicktime', '.mov')
|
|
|
|
mimetypes.add_type('video/avi', '.avi')
|
|
|
|
|
2019-04-04 11:10:54 +03:00
|
|
|
mimetypes.add_type('audio/mpeg', '.mp3')
|
2019-01-23 16:37:28 +03:00
|
|
|
mimetypes.add_type('audio/m4a', '.m4a')
|
|
|
|
mimetypes.add_type('audio/aac', '.aac')
|
2018-08-28 22:17:10 +03:00
|
|
|
mimetypes.add_type('audio/ogg', '.ogg')
|
2019-01-23 16:37:28 +03:00
|
|
|
mimetypes.add_type('audio/flac', '.flac')
|
2018-08-27 18:19:10 +03:00
|
|
|
|
2017-12-27 02:50:09 +03:00
|
|
|
USERNAME_RE = re.compile(
|
2018-02-22 12:27:12 +03:00
|
|
|
r'@|(?:https?://)?(?:www\.)?(?:telegram\.(?:me|dog)|t\.me)/(joinchat/)?'
|
2017-12-27 02:50:09 +03:00
|
|
|
)
|
2018-10-06 21:20:11 +03:00
|
|
|
TG_JOIN_RE = re.compile(
|
|
|
|
r'tg://(join)?invite='
|
|
|
|
)
|
2017-12-27 02:50:09 +03:00
|
|
|
|
2018-05-11 11:02:48 +03:00
|
|
|
# The only shorter-than-five-characters usernames are those used for some
|
|
|
|
# special, very well known bots. This list may be incomplete though:
|
|
|
|
# "[...] @gif, @vid, @pic, @bing, @wiki, @imdb and @bold [...]"
|
|
|
|
#
|
|
|
|
# See https://telegram.org/blog/inline-bots#how-does-it-work
|
|
|
|
VALID_USERNAME_RE = re.compile(
|
2018-06-17 13:08:55 +03:00
|
|
|
r'^([a-z]((?!__)[\w\d]){3,30}[a-z\d]'
|
2018-05-12 17:12:42 +03:00
|
|
|
r'|gif|vid|pic|bing|wiki|imdb|bold|vote|like|coub|ya)$',
|
2018-05-11 11:02:48 +03:00
|
|
|
re.IGNORECASE
|
|
|
|
)
|
2018-02-19 23:03:33 +03:00
|
|
|
|
2019-03-04 10:50:33 +03:00
|
|
|
_log = logging.getLogger(__name__)
|
|
|
|
|
2017-12-27 02:50:09 +03:00
|
|
|
|
2018-06-05 22:27:49 +03:00
|
|
|
def chunks(iterable, size=100):
|
|
|
|
"""
|
|
|
|
Turns the given iterable into chunks of the specified size,
|
|
|
|
which is 100 by default since that's what Telegram uses the most.
|
|
|
|
"""
|
|
|
|
it = iter(iterable)
|
|
|
|
size -= 1
|
|
|
|
for head in it:
|
|
|
|
yield itertools.chain([head], itertools.islice(it, size))
|
|
|
|
|
|
|
|
|
2016-10-09 13:57:38 +03:00
|
|
|
def get_display_name(entity):
|
2018-03-01 15:21:28 +03:00
|
|
|
"""
|
2018-03-23 23:40:24 +03:00
|
|
|
Gets the display name for the given entity, if it's an :tl:`User`,
|
|
|
|
:tl:`Chat` or :tl:`Channel`. Returns an empty string otherwise.
|
2018-03-01 15:21:28 +03:00
|
|
|
"""
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, types.User):
|
2017-06-16 10:11:49 +03:00
|
|
|
if entity.last_name and entity.first_name:
|
2016-10-09 13:57:38 +03:00
|
|
|
return '{} {}'.format(entity.first_name, entity.last_name)
|
2017-06-16 10:11:49 +03:00
|
|
|
elif entity.first_name:
|
|
|
|
return entity.first_name
|
|
|
|
elif entity.last_name:
|
|
|
|
return entity.last_name
|
|
|
|
else:
|
2017-12-24 18:18:09 +03:00
|
|
|
return ''
|
2016-10-09 13:57:38 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
elif isinstance(entity, (types.Chat, types.Channel)):
|
2016-10-09 13:57:38 +03:00
|
|
|
return entity.title
|
|
|
|
|
2017-12-24 18:18:09 +03:00
|
|
|
return ''
|
2017-05-23 10:45:48 +03:00
|
|
|
|
2016-10-09 13:57:38 +03:00
|
|
|
|
|
|
|
def get_extension(media):
|
2018-03-23 23:40:24 +03:00
|
|
|
"""Gets the corresponding extension for any Telegram media."""
|
2016-10-09 13:57:38 +03:00
|
|
|
|
|
|
|
# Photos are always compressed as .jpg by Telegram
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(media, (types.UserProfilePhoto,
|
|
|
|
types.ChatPhoto, types.MessageMediaPhoto)):
|
2016-10-09 13:57:38 +03:00
|
|
|
return '.jpg'
|
|
|
|
|
2017-08-24 18:44:38 +03:00
|
|
|
# Documents will come with a mime type
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(media, types.MessageMediaDocument):
|
2018-01-23 14:10:23 +03:00
|
|
|
media = media.document
|
2018-08-01 01:37:25 +03:00
|
|
|
if isinstance(media, (
|
|
|
|
types.Document, types.WebDocument, types.WebDocumentNoProxy)):
|
2018-01-23 14:10:23 +03:00
|
|
|
if media.mime_type == 'application/octet-stream':
|
|
|
|
# Octet stream are just bytes, which have no default extension
|
|
|
|
return ''
|
|
|
|
else:
|
|
|
|
return guess_extension(media.mime_type) or ''
|
2017-08-24 18:44:38 +03:00
|
|
|
|
|
|
|
return ''
|
2016-10-09 13:57:38 +03:00
|
|
|
|
|
|
|
|
2017-08-30 12:12:25 +03:00
|
|
|
def _raise_cast_fail(entity, target):
|
2017-12-28 02:22:28 +03:00
|
|
|
raise TypeError('Cannot cast {} to any kind of {}.'.format(
|
|
|
|
type(entity).__name__, target))
|
2017-08-30 12:12:25 +03:00
|
|
|
|
|
|
|
|
2018-12-15 14:23:14 +03:00
|
|
|
def get_input_peer(entity, allow_self=True, check_hash=True):
|
2018-03-23 23:40:24 +03:00
|
|
|
"""
|
|
|
|
Gets the input peer for the given "entity" (user, chat or channel).
|
2018-12-15 14:23:14 +03:00
|
|
|
|
|
|
|
A ``TypeError`` is raised if the given entity isn't a supported type
|
|
|
|
or if ``check_hash is True`` but the entity's ``access_hash is None``.
|
2018-12-24 19:32:16 +03:00
|
|
|
|
|
|
|
Note that ``check_hash`` **is ignored** if an input peer is already
|
|
|
|
passed since in that case we assume the user knows what they're doing.
|
|
|
|
This is key to getting entities by explicitly passing ``hash = 0``.
|
2018-03-23 23:40:24 +03:00
|
|
|
"""
|
2018-01-19 15:00:17 +03:00
|
|
|
try:
|
|
|
|
if entity.SUBCLASS_OF_ID == 0xc91c90b6: # crc32(b'InputPeer')
|
|
|
|
return entity
|
|
|
|
except AttributeError:
|
2018-04-13 14:08:29 +03:00
|
|
|
# e.g. custom.Dialog (can't cyclic import).
|
|
|
|
if allow_self and hasattr(entity, 'input_entity'):
|
2018-04-06 20:11:31 +03:00
|
|
|
return entity.input_entity
|
2018-04-13 14:08:29 +03:00
|
|
|
elif hasattr(entity, 'entity'):
|
|
|
|
return get_input_peer(entity.entity)
|
2018-04-06 20:11:31 +03:00
|
|
|
else:
|
|
|
|
_raise_cast_fail(entity, 'InputPeer')
|
2017-08-30 12:12:25 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, types.User):
|
2017-10-05 14:14:54 +03:00
|
|
|
if entity.is_self and allow_self:
|
2018-07-22 20:40:00 +03:00
|
|
|
return types.InputPeerSelf()
|
2018-12-15 14:23:14 +03:00
|
|
|
elif entity.access_hash is not None or not check_hash:
|
|
|
|
return types.InputPeerUser(entity.id, entity.access_hash)
|
2017-07-10 17:09:20 +03:00
|
|
|
else:
|
2018-12-15 14:23:14 +03:00
|
|
|
raise TypeError('User without access_hash cannot be input')
|
2017-06-15 18:03:59 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, (types.Chat, types.ChatEmpty, types.ChatForbidden)):
|
|
|
|
return types.InputPeerChat(entity.id)
|
2017-06-15 18:03:59 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, (types.Channel, types.ChannelForbidden)):
|
2018-12-15 14:23:14 +03:00
|
|
|
if entity.access_hash is not None or not check_hash:
|
|
|
|
return types.InputPeerChannel(entity.id, entity.access_hash)
|
|
|
|
else:
|
|
|
|
raise TypeError('Channel without access_hash cannot be input')
|
2016-10-09 13:57:38 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, types.InputUser):
|
|
|
|
return types.InputPeerUser(entity.user_id, entity.access_hash)
|
2017-07-10 17:09:20 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, types.InputChannel):
|
|
|
|
return types.InputPeerChannel(entity.channel_id, entity.access_hash)
|
2018-01-20 21:29:05 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, types.InputUserSelf):
|
|
|
|
return types.InputPeerSelf()
|
2017-11-12 20:03:42 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, types.UserEmpty):
|
|
|
|
return types.InputPeerEmpty()
|
2018-01-20 21:29:05 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, types.UserFull):
|
2017-07-10 17:09:20 +03:00
|
|
|
return get_input_peer(entity.user)
|
2017-06-15 18:03:59 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, types.ChatFull):
|
|
|
|
return types.InputPeerChat(entity.id)
|
2017-06-15 18:03:59 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, types.PeerChat):
|
|
|
|
return types.InputPeerChat(entity.chat_id)
|
2017-07-04 22:18:35 +03:00
|
|
|
|
2017-08-30 12:12:25 +03:00
|
|
|
_raise_cast_fail(entity, 'InputPeer')
|
2017-05-23 10:45:48 +03:00
|
|
|
|
2016-10-09 13:57:38 +03:00
|
|
|
|
2017-07-07 10:48:06 +03:00
|
|
|
def get_input_channel(entity):
|
2018-03-23 23:40:24 +03:00
|
|
|
"""Similar to :meth:`get_input_peer`, but for :tl:`InputChannel`'s alone."""
|
2018-01-19 15:00:17 +03:00
|
|
|
try:
|
|
|
|
if entity.SUBCLASS_OF_ID == 0x40f202fd: # crc32(b'InputChannel')
|
|
|
|
return entity
|
|
|
|
except AttributeError:
|
2017-08-30 12:12:25 +03:00
|
|
|
_raise_cast_fail(entity, 'InputChannel')
|
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, (types.Channel, types.ChannelForbidden)):
|
|
|
|
return types.InputChannel(entity.id, entity.access_hash or 0)
|
2017-07-07 10:48:06 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, types.InputPeerChannel):
|
|
|
|
return types.InputChannel(entity.channel_id, entity.access_hash)
|
2017-08-05 10:37:34 +03:00
|
|
|
|
2017-08-30 12:12:25 +03:00
|
|
|
_raise_cast_fail(entity, 'InputChannel')
|
2017-07-07 10:48:06 +03:00
|
|
|
|
|
|
|
|
2017-07-10 17:04:10 +03:00
|
|
|
def get_input_user(entity):
|
2018-03-23 23:40:24 +03:00
|
|
|
"""Similar to :meth:`get_input_peer`, but for :tl:`InputUser`'s alone."""
|
2018-01-19 15:00:17 +03:00
|
|
|
try:
|
|
|
|
if entity.SUBCLASS_OF_ID == 0xe669bf46: # crc32(b'InputUser'):
|
|
|
|
return entity
|
|
|
|
except AttributeError:
|
2017-08-30 12:12:25 +03:00
|
|
|
_raise_cast_fail(entity, 'InputUser')
|
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, types.User):
|
2017-07-10 17:04:10 +03:00
|
|
|
if entity.is_self:
|
2018-07-22 20:40:00 +03:00
|
|
|
return types.InputUserSelf()
|
2017-07-10 17:04:10 +03:00
|
|
|
else:
|
2018-07-22 20:40:00 +03:00
|
|
|
return types.InputUser(entity.id, entity.access_hash or 0)
|
2017-07-10 17:04:10 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, types.InputPeerSelf):
|
|
|
|
return types.InputUserSelf()
|
2017-10-24 10:42:51 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, (types.UserEmpty, types.InputPeerEmpty)):
|
|
|
|
return types.InputUserEmpty()
|
2017-07-10 17:04:10 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, types.UserFull):
|
2017-07-10 17:04:10 +03:00
|
|
|
return get_input_user(entity.user)
|
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(entity, types.InputPeerUser):
|
|
|
|
return types.InputUser(entity.user_id, entity.access_hash)
|
2017-07-10 17:09:20 +03:00
|
|
|
|
2017-08-30 12:12:25 +03:00
|
|
|
_raise_cast_fail(entity, 'InputUser')
|
2017-07-10 17:04:10 +03:00
|
|
|
|
|
|
|
|
2018-04-28 12:49:43 +03:00
|
|
|
def get_input_dialog(dialog):
|
|
|
|
"""Similar to :meth:`get_input_peer`, but for dialogs"""
|
|
|
|
try:
|
|
|
|
if dialog.SUBCLASS_OF_ID == 0xa21c9795: # crc32(b'InputDialogPeer')
|
|
|
|
return dialog
|
|
|
|
if dialog.SUBCLASS_OF_ID == 0xc91c90b6: # crc32(b'InputPeer')
|
2018-07-22 20:40:00 +03:00
|
|
|
return types.InputDialogPeer(dialog)
|
2018-04-28 12:49:43 +03:00
|
|
|
except AttributeError:
|
|
|
|
_raise_cast_fail(dialog, 'InputDialogPeer')
|
|
|
|
|
|
|
|
try:
|
2018-07-22 20:40:00 +03:00
|
|
|
return types.InputDialogPeer(get_input_peer(dialog))
|
2018-04-28 12:49:43 +03:00
|
|
|
except TypeError:
|
|
|
|
pass
|
|
|
|
|
|
|
|
_raise_cast_fail(dialog, 'InputDialogPeer')
|
|
|
|
|
|
|
|
|
2017-09-25 14:43:03 +03:00
|
|
|
def get_input_document(document):
|
2018-03-23 23:40:24 +03:00
|
|
|
"""Similar to :meth:`get_input_peer`, but for documents"""
|
2018-01-19 15:00:17 +03:00
|
|
|
try:
|
|
|
|
if document.SUBCLASS_OF_ID == 0xf33fdb68: # crc32(b'InputDocument'):
|
|
|
|
return document
|
|
|
|
except AttributeError:
|
2017-09-25 14:43:03 +03:00
|
|
|
_raise_cast_fail(document, 'InputDocument')
|
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(document, types.Document):
|
2018-07-23 13:19:41 +03:00
|
|
|
return types.InputDocument(
|
2018-12-25 03:04:27 +03:00
|
|
|
id=document.id, access_hash=document.access_hash,
|
|
|
|
file_reference=document.file_reference)
|
2017-09-25 14:43:03 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(document, types.DocumentEmpty):
|
|
|
|
return types.InputDocumentEmpty()
|
2017-09-25 14:43:03 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(document, types.MessageMediaDocument):
|
2017-09-25 14:43:03 +03:00
|
|
|
return get_input_document(document.document)
|
|
|
|
|
2018-07-22 20:26:34 +03:00
|
|
|
if isinstance(document, types.Message):
|
2017-09-25 14:43:03 +03:00
|
|
|
return get_input_document(document.media)
|
|
|
|
|
|
|
|
_raise_cast_fail(document, 'InputDocument')
|
|
|
|
|
|
|
|
|
|
|
|
def get_input_photo(photo):
|
2018-03-23 23:40:24 +03:00
|
|
|
"""Similar to :meth:`get_input_peer`, but for photos"""
|
2018-01-19 15:00:17 +03:00
|
|
|
try:
|
|
|
|
if photo.SUBCLASS_OF_ID == 0x846363e0: # crc32(b'InputPhoto'):
|
|
|
|
return photo
|
|
|
|
except AttributeError:
|
2017-09-25 14:43:03 +03:00
|
|
|
_raise_cast_fail(photo, 'InputPhoto')
|
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(photo, types.photos.Photo):
|
2017-10-08 14:45:14 +03:00
|
|
|
photo = photo.photo
|
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(photo, types.Photo):
|
2018-12-18 18:37:07 +03:00
|
|
|
return types.InputPhoto(id=photo.id, access_hash=photo.access_hash,
|
|
|
|
file_reference=photo.file_reference)
|
2017-09-25 14:43:03 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(photo, types.PhotoEmpty):
|
|
|
|
return types.InputPhotoEmpty()
|
2017-09-25 14:43:03 +03:00
|
|
|
|
2018-10-05 15:11:47 +03:00
|
|
|
if isinstance(photo, types.messages.ChatFull):
|
|
|
|
photo = photo.full_chat
|
|
|
|
if isinstance(photo, types.ChannelFull):
|
|
|
|
return get_input_photo(photo.chat_photo)
|
|
|
|
elif isinstance(photo, types.UserFull):
|
|
|
|
return get_input_photo(photo.profile_photo)
|
|
|
|
elif isinstance(photo, (types.Channel, types.Chat, types.User)):
|
|
|
|
return get_input_photo(photo.photo)
|
|
|
|
|
|
|
|
if isinstance(photo, (types.UserEmpty, types.ChatEmpty,
|
|
|
|
types.ChatForbidden, types.ChannelForbidden)):
|
|
|
|
return types.InputPhotoEmpty()
|
|
|
|
|
2017-09-25 14:43:03 +03:00
|
|
|
_raise_cast_fail(photo, 'InputPhoto')
|
|
|
|
|
|
|
|
|
2018-10-05 15:11:47 +03:00
|
|
|
def get_input_chat_photo(photo):
|
|
|
|
"""Similar to :meth:`get_input_peer`, but for chat photos"""
|
|
|
|
try:
|
|
|
|
if photo.SUBCLASS_OF_ID == 0xd4eb2d74: # crc32(b'InputChatPhoto')
|
|
|
|
return photo
|
|
|
|
elif photo.SUBCLASS_OF_ID == 0xe7655f1f: # crc32(b'InputFile'):
|
|
|
|
return types.InputChatUploadedPhoto(photo)
|
|
|
|
except AttributeError:
|
|
|
|
_raise_cast_fail(photo, 'InputChatPhoto')
|
|
|
|
|
|
|
|
photo = get_input_photo(photo)
|
|
|
|
if isinstance(photo, types.InputPhoto):
|
|
|
|
return types.InputChatPhoto(photo)
|
|
|
|
elif isinstance(photo, types.InputPhotoEmpty):
|
|
|
|
return types.InputChatPhotoEmpty()
|
|
|
|
|
|
|
|
_raise_cast_fail(photo, 'InputChatPhoto')
|
|
|
|
|
|
|
|
|
2017-09-25 14:43:03 +03:00
|
|
|
def get_input_geo(geo):
|
2018-03-23 23:40:24 +03:00
|
|
|
"""Similar to :meth:`get_input_peer`, but for geo points"""
|
2018-01-19 15:00:17 +03:00
|
|
|
try:
|
|
|
|
if geo.SUBCLASS_OF_ID == 0x430d225: # crc32(b'InputGeoPoint'):
|
|
|
|
return geo
|
|
|
|
except AttributeError:
|
2017-09-25 14:43:03 +03:00
|
|
|
_raise_cast_fail(geo, 'InputGeoPoint')
|
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(geo, types.GeoPoint):
|
|
|
|
return types.InputGeoPoint(lat=geo.lat, long=geo.long)
|
2017-09-25 14:43:03 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(geo, types.GeoPointEmpty):
|
|
|
|
return types.InputGeoPointEmpty()
|
2017-09-25 14:43:03 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(geo, types.MessageMediaGeo):
|
2017-09-25 14:43:03 +03:00
|
|
|
return get_input_geo(geo.geo)
|
|
|
|
|
2018-07-22 20:26:34 +03:00
|
|
|
if isinstance(geo, types.Message):
|
2017-09-25 14:43:03 +03:00
|
|
|
return get_input_geo(geo.media)
|
|
|
|
|
|
|
|
_raise_cast_fail(geo, 'InputGeoPoint')
|
|
|
|
|
|
|
|
|
2019-02-13 14:33:11 +03:00
|
|
|
def get_input_media(
|
|
|
|
media, *,
|
|
|
|
is_photo=False, attributes=None, force_document=False,
|
|
|
|
voice_note=False, video_note=False, supports_streaming=False
|
|
|
|
):
|
2018-03-23 23:40:24 +03:00
|
|
|
"""
|
|
|
|
Similar to :meth:`get_input_peer`, but for media.
|
2017-09-25 14:43:03 +03:00
|
|
|
|
2019-02-13 14:33:11 +03:00
|
|
|
If the media is :tl:`InputFile` and ``is_photo`` is known to be ``True``,
|
|
|
|
it will be treated as an :tl:`InputMediaUploadedPhoto`. Else, the rest
|
|
|
|
of parameters will indicate how to treat it.
|
2017-09-25 14:43:03 +03:00
|
|
|
"""
|
2018-01-19 15:00:17 +03:00
|
|
|
try:
|
2018-04-23 16:33:44 +03:00
|
|
|
if media.SUBCLASS_OF_ID == 0xfaf846f4: # crc32(b'InputMedia')
|
2018-01-19 15:00:17 +03:00
|
|
|
return media
|
2018-04-23 16:33:44 +03:00
|
|
|
elif media.SUBCLASS_OF_ID == 0x846363e0: # crc32(b'InputPhoto')
|
2018-07-22 20:40:00 +03:00
|
|
|
return types.InputMediaPhoto(media)
|
2018-04-23 16:33:44 +03:00
|
|
|
elif media.SUBCLASS_OF_ID == 0xf33fdb68: # crc32(b'InputDocument')
|
2018-07-22 20:40:00 +03:00
|
|
|
return types.InputMediaDocument(media)
|
2018-01-19 15:00:17 +03:00
|
|
|
except AttributeError:
|
2017-09-25 14:43:03 +03:00
|
|
|
_raise_cast_fail(media, 'InputMedia')
|
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(media, types.MessageMediaPhoto):
|
|
|
|
return types.InputMediaPhoto(
|
2017-09-25 14:43:03 +03:00
|
|
|
id=get_input_photo(media.photo),
|
2018-03-02 23:28:33 +03:00
|
|
|
ttl_seconds=media.ttl_seconds
|
2017-09-25 14:43:03 +03:00
|
|
|
)
|
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(media, (types.Photo, types.photos.Photo, types.PhotoEmpty)):
|
|
|
|
return types.InputMediaPhoto(
|
2018-03-27 12:22:31 +03:00
|
|
|
id=get_input_photo(media)
|
|
|
|
)
|
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(media, types.MessageMediaDocument):
|
|
|
|
return types.InputMediaDocument(
|
2017-09-25 14:43:03 +03:00
|
|
|
id=get_input_document(media.document),
|
2018-03-02 23:28:33 +03:00
|
|
|
ttl_seconds=media.ttl_seconds
|
2017-09-25 14:43:03 +03:00
|
|
|
)
|
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(media, (types.Document, types.DocumentEmpty)):
|
|
|
|
return types.InputMediaDocument(
|
2018-03-27 12:22:31 +03:00
|
|
|
id=get_input_document(media)
|
|
|
|
)
|
|
|
|
|
2019-02-13 14:33:11 +03:00
|
|
|
if isinstance(media, (types.InputFile, types.InputFileBig)):
|
2017-09-25 14:43:03 +03:00
|
|
|
if is_photo:
|
2018-07-22 20:40:00 +03:00
|
|
|
return types.InputMediaUploadedPhoto(file=media)
|
2017-09-25 14:43:03 +03:00
|
|
|
else:
|
2019-02-13 14:33:11 +03:00
|
|
|
attrs, mime = get_attributes(
|
|
|
|
media,
|
|
|
|
attributes=attributes,
|
|
|
|
force_document=force_document,
|
|
|
|
voice_note=voice_note,
|
|
|
|
video_note=video_note,
|
|
|
|
supports_streaming=supports_streaming
|
2017-09-25 14:43:03 +03:00
|
|
|
)
|
2019-02-13 14:33:11 +03:00
|
|
|
return types.InputMediaUploadedDocument(
|
|
|
|
file=media, mime_type=mime, attributes=attrs)
|
2017-09-25 14:43:03 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(media, types.MessageMediaGame):
|
|
|
|
return types.InputMediaGame(id=media.game.id)
|
2017-09-25 14:43:03 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(media, (types.ChatPhoto, types.UserProfilePhoto)):
|
|
|
|
if isinstance(media.photo_big, types.FileLocationUnavailable):
|
2018-01-23 14:04:35 +03:00
|
|
|
media = media.photo_small
|
2017-09-25 14:43:03 +03:00
|
|
|
else:
|
2018-01-23 14:04:35 +03:00
|
|
|
media = media.photo_big
|
2018-03-02 23:28:33 +03:00
|
|
|
return get_input_media(media, is_photo=True)
|
2017-09-25 14:43:03 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(media, types.MessageMediaContact):
|
|
|
|
return types.InputMediaContact(
|
2017-09-25 14:43:03 +03:00
|
|
|
phone_number=media.phone_number,
|
|
|
|
first_name=media.first_name,
|
2018-06-29 14:20:45 +03:00
|
|
|
last_name=media.last_name,
|
|
|
|
vcard=''
|
2017-09-25 14:43:03 +03:00
|
|
|
)
|
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(media, types.MessageMediaGeo):
|
|
|
|
return types.InputMediaGeoPoint(geo_point=get_input_geo(media.geo))
|
2017-09-25 14:43:03 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(media, types.MessageMediaVenue):
|
|
|
|
return types.InputMediaVenue(
|
2017-09-25 14:43:03 +03:00
|
|
|
geo_point=get_input_geo(media.geo),
|
|
|
|
title=media.title,
|
|
|
|
address=media.address,
|
|
|
|
provider=media.provider,
|
2018-01-16 16:01:14 +03:00
|
|
|
venue_id=media.venue_id,
|
|
|
|
venue_type=''
|
2017-09-25 14:43:03 +03:00
|
|
|
)
|
|
|
|
|
2017-10-13 12:38:12 +03:00
|
|
|
if isinstance(media, (
|
2018-07-22 20:40:00 +03:00
|
|
|
types.MessageMediaEmpty, types.MessageMediaUnsupported,
|
|
|
|
types.ChatPhotoEmpty, types.UserProfilePhotoEmpty,
|
|
|
|
types.FileLocationUnavailable)):
|
|
|
|
return types.InputMediaEmpty()
|
2017-09-25 14:43:03 +03:00
|
|
|
|
2018-07-22 20:26:34 +03:00
|
|
|
if isinstance(media, types.Message):
|
2018-03-02 23:28:33 +03:00
|
|
|
return get_input_media(media.media, is_photo=is_photo)
|
2017-09-25 14:43:03 +03:00
|
|
|
|
|
|
|
_raise_cast_fail(media, 'InputMedia')
|
|
|
|
|
|
|
|
|
2018-04-23 12:05:38 +03:00
|
|
|
def get_input_message(message):
|
|
|
|
"""Similar to :meth:`get_input_peer`, but for input messages."""
|
|
|
|
try:
|
|
|
|
if isinstance(message, int): # This case is really common too
|
2018-07-22 20:40:00 +03:00
|
|
|
return types.InputMessageID(message)
|
2018-04-23 12:05:38 +03:00
|
|
|
elif message.SUBCLASS_OF_ID == 0x54b6bcc5: # crc32(b'InputMessage'):
|
|
|
|
return message
|
|
|
|
elif message.SUBCLASS_OF_ID == 0x790009e3: # crc32(b'Message'):
|
2018-07-22 20:40:00 +03:00
|
|
|
return types.InputMessageID(message.id)
|
2018-04-23 12:05:38 +03:00
|
|
|
except AttributeError:
|
|
|
|
pass
|
|
|
|
|
|
|
|
_raise_cast_fail(message, 'InputMedia')
|
|
|
|
|
|
|
|
|
2018-06-09 23:05:06 +03:00
|
|
|
def get_message_id(message):
|
2018-07-29 16:49:12 +03:00
|
|
|
"""Similar to :meth:`get_input_peer`, but for message IDs."""
|
2018-06-09 23:05:06 +03:00
|
|
|
if message is None:
|
|
|
|
return None
|
|
|
|
|
|
|
|
if isinstance(message, int):
|
|
|
|
return message
|
|
|
|
|
|
|
|
try:
|
|
|
|
if message.SUBCLASS_OF_ID == 0x790009e3:
|
|
|
|
# hex(crc32(b'Message')) = 0x790009e3
|
|
|
|
return message.id
|
|
|
|
except AttributeError:
|
|
|
|
pass
|
|
|
|
|
|
|
|
raise TypeError('Invalid message type: {}'.format(type(message)))
|
|
|
|
|
|
|
|
|
2019-03-04 10:50:33 +03:00
|
|
|
def _get_metadata(file):
|
|
|
|
# `hachoir` only deals with paths to in-disk files, while
|
|
|
|
# `_get_extension` supports a few other things. The parser
|
|
|
|
# may also fail in any case and we don't want to crash if
|
|
|
|
# the extraction process fails.
|
|
|
|
if hachoir and isinstance(file, str) and os.path.isfile(file):
|
|
|
|
try:
|
|
|
|
with hachoir.parser.createParser(file) as parser:
|
|
|
|
return hachoir.metadata.extractMetadata(parser)
|
|
|
|
except Exception as e:
|
|
|
|
_log.warning('Failed to analyze %s: %s %s', file, e.__class__, e)
|
|
|
|
|
|
|
|
|
2018-07-15 12:31:14 +03:00
|
|
|
def get_attributes(file, *, attributes=None, mime_type=None,
|
2019-01-21 21:46:33 +03:00
|
|
|
force_document=False, voice_note=False, video_note=False,
|
|
|
|
supports_streaming=False):
|
2018-07-15 12:31:14 +03:00
|
|
|
"""
|
|
|
|
Get a list of attributes for the given file and
|
|
|
|
the mime type as a tuple ([attribute], mime_type).
|
|
|
|
"""
|
2019-02-13 14:33:11 +03:00
|
|
|
# Note: ``file.name`` works for :tl:`InputFile` and some `IOBase` streams
|
2018-07-31 13:14:13 +03:00
|
|
|
name = file if isinstance(file, str) else getattr(file, 'name', 'unnamed')
|
|
|
|
if mime_type is None:
|
|
|
|
mime_type = mimetypes.guess_type(name)[0]
|
2018-07-15 12:31:14 +03:00
|
|
|
|
2018-07-31 13:14:13 +03:00
|
|
|
attr_dict = {types.DocumentAttributeFilename:
|
|
|
|
types.DocumentAttributeFilename(os.path.basename(name))}
|
2018-07-15 12:31:14 +03:00
|
|
|
|
2019-03-04 10:50:33 +03:00
|
|
|
if is_audio(file):
|
|
|
|
m = _get_metadata(file)
|
|
|
|
if m:
|
2018-07-31 13:14:13 +03:00
|
|
|
attr_dict[types.DocumentAttributeAudio] = \
|
|
|
|
types.DocumentAttributeAudio(
|
|
|
|
voice=voice_note,
|
|
|
|
title=m.get('title') if m.has('title') else None,
|
|
|
|
performer=m.get('author') if m.has('author') else None,
|
|
|
|
duration=int(m.get('duration').seconds
|
|
|
|
if m.has('duration') else 0)
|
|
|
|
)
|
|
|
|
|
|
|
|
if not force_document and is_video(file):
|
2019-03-04 10:50:33 +03:00
|
|
|
m = _get_metadata(file)
|
|
|
|
if m:
|
|
|
|
doc = types.DocumentAttributeVideo(
|
|
|
|
round_message=video_note,
|
|
|
|
w=m.get('width') if m.has('width') else 0,
|
|
|
|
h=m.get('height') if m.has('height') else 0,
|
|
|
|
duration=int(m.get('duration').seconds
|
|
|
|
if m.has('duration') else 0),
|
|
|
|
supports_streaming=supports_streaming
|
|
|
|
)
|
2018-07-31 13:14:13 +03:00
|
|
|
else:
|
|
|
|
doc = types.DocumentAttributeVideo(
|
2019-01-21 21:46:33 +03:00
|
|
|
0, 1, 1, round_message=video_note,
|
|
|
|
supports_streaming=supports_streaming)
|
2018-07-15 12:31:14 +03:00
|
|
|
|
2018-07-31 13:14:13 +03:00
|
|
|
attr_dict[types.DocumentAttributeVideo] = doc
|
2018-07-15 12:31:14 +03:00
|
|
|
|
|
|
|
if voice_note:
|
2018-07-22 20:40:00 +03:00
|
|
|
if types.DocumentAttributeAudio in attr_dict:
|
|
|
|
attr_dict[types.DocumentAttributeAudio].voice = True
|
2018-07-15 12:31:14 +03:00
|
|
|
else:
|
2018-07-22 20:40:00 +03:00
|
|
|
attr_dict[types.DocumentAttributeAudio] = \
|
|
|
|
types.DocumentAttributeAudio(0, voice=True)
|
2018-07-15 12:31:14 +03:00
|
|
|
|
|
|
|
# Now override the attributes if any. As we have a dict of
|
|
|
|
# {cls: instance}, we can override any class with the list
|
|
|
|
# of attributes provided by the user easily.
|
|
|
|
if attributes:
|
|
|
|
for a in attributes:
|
|
|
|
attr_dict[type(a)] = a
|
|
|
|
|
|
|
|
# Ensure we have a mime type, any; but it cannot be None
|
|
|
|
# 'The "octet-stream" subtype is used to indicate that a body
|
|
|
|
# contains arbitrary binary data.'
|
|
|
|
if not mime_type:
|
|
|
|
mime_type = 'application/octet-stream'
|
|
|
|
|
|
|
|
return list(attr_dict.values()), mime_type
|
|
|
|
|
|
|
|
|
2018-06-10 12:30:51 +03:00
|
|
|
def sanitize_parse_mode(mode):
|
|
|
|
"""
|
|
|
|
Converts the given parse mode into an object with
|
|
|
|
``parse`` and ``unparse`` callable properties.
|
|
|
|
"""
|
|
|
|
if not mode:
|
|
|
|
return None
|
|
|
|
|
|
|
|
if callable(mode):
|
|
|
|
class CustomMode:
|
|
|
|
@staticmethod
|
|
|
|
def unparse(text, entities):
|
|
|
|
raise NotImplementedError
|
|
|
|
|
|
|
|
CustomMode.parse = mode
|
|
|
|
return CustomMode
|
|
|
|
elif (all(hasattr(mode, x) for x in ('parse', 'unparse'))
|
|
|
|
and all(callable(x) for x in (mode.parse, mode.unparse))):
|
|
|
|
return mode
|
|
|
|
elif isinstance(mode, str):
|
|
|
|
try:
|
|
|
|
return {
|
|
|
|
'md': markdown,
|
|
|
|
'markdown': markdown,
|
|
|
|
'htm': html,
|
|
|
|
'html': html
|
|
|
|
}[mode.lower()]
|
|
|
|
except KeyError:
|
|
|
|
raise ValueError('Unknown parse mode {}'.format(mode))
|
|
|
|
else:
|
|
|
|
raise TypeError('Invalid parse mode type {}'.format(mode))
|
|
|
|
|
|
|
|
|
2018-04-27 22:10:41 +03:00
|
|
|
def get_input_location(location):
|
2018-07-21 12:59:44 +03:00
|
|
|
"""
|
|
|
|
Similar to :meth:`get_input_peer`, but for input messages.
|
|
|
|
|
|
|
|
Note that this returns a tuple ``(dc_id, location)``, the
|
|
|
|
``dc_id`` being present if known.
|
|
|
|
"""
|
2018-04-27 22:10:41 +03:00
|
|
|
try:
|
|
|
|
if location.SUBCLASS_OF_ID == 0x1523d462:
|
2018-07-21 12:59:44 +03:00
|
|
|
return None, location # crc32(b'InputFileLocation'):
|
2018-04-27 22:10:41 +03:00
|
|
|
except AttributeError:
|
|
|
|
_raise_cast_fail(location, 'InputFileLocation')
|
|
|
|
|
2018-07-22 20:26:34 +03:00
|
|
|
if isinstance(location, types.Message):
|
2018-04-27 22:10:41 +03:00
|
|
|
location = location.media
|
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(location, types.MessageMediaDocument):
|
2018-04-27 22:10:41 +03:00
|
|
|
location = location.document
|
2018-07-22 20:40:00 +03:00
|
|
|
elif isinstance(location, types.MessageMediaPhoto):
|
2018-04-27 22:10:41 +03:00
|
|
|
location = location.photo
|
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
if isinstance(location, types.Document):
|
|
|
|
return (location.dc_id, types.InputDocumentFileLocation(
|
2018-12-18 18:37:07 +03:00
|
|
|
location.id, location.access_hash,
|
|
|
|
file_reference=location.file_reference
|
|
|
|
))
|
2018-07-22 20:40:00 +03:00
|
|
|
elif isinstance(location, types.Photo):
|
2018-04-27 22:10:41 +03:00
|
|
|
try:
|
2018-07-22 20:40:00 +03:00
|
|
|
location = next(
|
|
|
|
x for x in reversed(location.sizes)
|
|
|
|
if not isinstance(x, types.PhotoSizeEmpty)
|
|
|
|
).location
|
2018-04-27 22:10:41 +03:00
|
|
|
except StopIteration:
|
|
|
|
pass
|
|
|
|
|
2018-12-18 18:37:07 +03:00
|
|
|
if isinstance(location, types.FileLocation):
|
|
|
|
return (location.dc_id, types.InputFileLocation(
|
|
|
|
location.volume_id, location.local_id, location.secret,
|
|
|
|
file_reference=location.file_reference
|
|
|
|
))
|
|
|
|
elif isinstance(location, types.FileLocationUnavailable):
|
|
|
|
raise TypeError('Unavailable location cannot be used as input')
|
2018-04-27 22:10:41 +03:00
|
|
|
|
|
|
|
_raise_cast_fail(location, 'InputFileLocation')
|
|
|
|
|
|
|
|
|
2018-06-21 17:31:03 +03:00
|
|
|
def _get_extension(file):
|
|
|
|
"""
|
|
|
|
Gets the extension for the given file, which can be either a
|
|
|
|
str or an ``open()``'ed file (which has a ``.name`` attribute).
|
|
|
|
"""
|
|
|
|
if isinstance(file, str):
|
|
|
|
return os.path.splitext(file)[-1]
|
2019-02-12 13:33:06 +03:00
|
|
|
elif isinstance(file, bytes):
|
|
|
|
kind = imghdr.what(io.BytesIO(file))
|
|
|
|
return ('.' + kind) if kind else ''
|
|
|
|
elif isinstance(file, io.IOBase) and file.seekable():
|
2019-03-01 23:27:15 +03:00
|
|
|
kind = imghdr.what(file)
|
|
|
|
return ('.' + kind) if kind is not None else ''
|
2018-06-21 17:31:03 +03:00
|
|
|
elif getattr(file, 'name', None):
|
2019-02-13 14:33:11 +03:00
|
|
|
# Note: ``file.name`` works for :tl:`InputFile` and some `IOBase`
|
2018-06-21 17:31:03 +03:00
|
|
|
return _get_extension(file.name)
|
|
|
|
else:
|
|
|
|
return ''
|
|
|
|
|
|
|
|
|
2018-01-15 20:15:30 +03:00
|
|
|
def is_image(file):
|
2018-03-15 11:52:45 +03:00
|
|
|
"""
|
2018-03-23 23:40:24 +03:00
|
|
|
Returns ``True`` if the file extension looks like an image file to Telegram.
|
2018-03-15 11:52:45 +03:00
|
|
|
"""
|
2019-02-25 20:23:39 +03:00
|
|
|
match = re.match(r'\.(png|jpe?g)', _get_extension(file), re.IGNORECASE)
|
|
|
|
if match:
|
|
|
|
return True
|
|
|
|
else:
|
|
|
|
return isinstance(resolve_bot_file_id(file), types.Photo)
|
2018-02-12 12:33:51 +03:00
|
|
|
|
2018-02-19 23:03:33 +03:00
|
|
|
|
2018-06-26 17:39:22 +03:00
|
|
|
def is_gif(file):
|
|
|
|
"""
|
|
|
|
Returns ``True`` if the file extension looks like a gif file to Telegram.
|
|
|
|
"""
|
|
|
|
return re.match(r'\.gif', _get_extension(file), re.IGNORECASE)
|
|
|
|
|
|
|
|
|
2018-02-17 15:00:58 +03:00
|
|
|
def is_audio(file):
|
2018-03-23 23:40:24 +03:00
|
|
|
"""Returns ``True`` if the file extension looks like an audio file."""
|
2018-06-21 17:31:03 +03:00
|
|
|
file = 'a' + _get_extension(file)
|
|
|
|
return (mimetypes.guess_type(file)[0] or '').startswith('audio/')
|
2018-02-17 15:00:58 +03:00
|
|
|
|
|
|
|
|
2018-02-12 12:33:51 +03:00
|
|
|
def is_video(file):
|
2018-03-23 23:40:24 +03:00
|
|
|
"""Returns ``True`` if the file extension looks like a video file."""
|
2018-06-21 17:31:03 +03:00
|
|
|
file = 'a' + _get_extension(file)
|
|
|
|
return (mimetypes.guess_type(file)[0] or '').startswith('video/')
|
2018-01-15 20:15:30 +03:00
|
|
|
|
|
|
|
|
2018-02-26 16:12:21 +03:00
|
|
|
def is_list_like(obj):
|
|
|
|
"""
|
2018-03-23 23:40:24 +03:00
|
|
|
Returns ``True`` if the given object looks like a list.
|
2018-02-26 16:12:21 +03:00
|
|
|
|
2018-03-23 23:40:24 +03:00
|
|
|
Checking ``if hasattr(obj, '__iter__')`` and ignoring ``str/bytes`` is not
|
|
|
|
enough. Things like ``open()`` are also iterable (and probably many
|
2018-02-26 16:12:21 +03:00
|
|
|
other things), so just support the commonly known list-like objects.
|
|
|
|
"""
|
2018-08-03 00:00:10 +03:00
|
|
|
return isinstance(obj, (list, tuple, set, dict, GeneratorType))
|
2018-02-26 16:12:21 +03:00
|
|
|
|
|
|
|
|
2017-12-27 02:50:09 +03:00
|
|
|
def parse_phone(phone):
|
2018-03-23 23:40:24 +03:00
|
|
|
"""Parses the given phone, or returns ``None`` if it's invalid."""
|
2017-12-27 02:50:09 +03:00
|
|
|
if isinstance(phone, int):
|
|
|
|
return str(phone)
|
|
|
|
else:
|
|
|
|
phone = re.sub(r'[+()\s-]', '', str(phone))
|
|
|
|
if phone.isdigit():
|
|
|
|
return phone
|
|
|
|
|
|
|
|
|
|
|
|
def parse_username(username):
|
2018-10-06 21:20:11 +03:00
|
|
|
"""
|
|
|
|
Parses the given username or channel access hash, given
|
|
|
|
a string, username or URL. Returns a tuple consisting of
|
|
|
|
both the stripped, lowercase username and whether it is
|
|
|
|
a joinchat/ hash (in which case is not lowercase'd).
|
2018-02-19 23:03:33 +03:00
|
|
|
|
2018-10-06 21:20:11 +03:00
|
|
|
Returns ``(None, False)`` if the ``username`` or link is not valid.
|
2017-12-27 02:50:09 +03:00
|
|
|
"""
|
|
|
|
username = username.strip()
|
2018-10-06 21:20:11 +03:00
|
|
|
m = USERNAME_RE.match(username) or TG_JOIN_RE.match(username)
|
2017-12-27 02:50:09 +03:00
|
|
|
if m:
|
2018-02-19 23:03:33 +03:00
|
|
|
username = username[m.end():]
|
2017-12-27 13:54:08 +03:00
|
|
|
is_invite = bool(m.group(1))
|
2018-02-19 23:03:33 +03:00
|
|
|
if is_invite:
|
|
|
|
return username, True
|
2018-02-22 12:27:12 +03:00
|
|
|
else:
|
|
|
|
username = username.rstrip('/')
|
2018-02-19 23:03:33 +03:00
|
|
|
|
|
|
|
if VALID_USERNAME_RE.match(username):
|
2017-12-27 13:54:08 +03:00
|
|
|
return username.lower(), False
|
2018-02-19 23:03:33 +03:00
|
|
|
else:
|
|
|
|
return None, False
|
2017-12-27 02:50:09 +03:00
|
|
|
|
|
|
|
|
2018-06-07 11:46:32 +03:00
|
|
|
def get_inner_text(text, entities):
|
2018-06-03 12:53:18 +03:00
|
|
|
"""
|
2018-06-07 11:46:32 +03:00
|
|
|
Gets the inner text that's surrounded by the given entities.
|
2018-06-03 12:53:18 +03:00
|
|
|
For instance: text = 'hey!', entity = MessageEntityBold(2, 2) -> 'y!'.
|
|
|
|
|
2018-06-07 11:46:32 +03:00
|
|
|
:param text: the original text.
|
|
|
|
:param entities: the entity or entities that must be matched.
|
2018-06-03 12:53:18 +03:00
|
|
|
:return: a single result or a list of the text surrounded by the entities.
|
|
|
|
"""
|
|
|
|
text = add_surrogate(text)
|
|
|
|
result = []
|
2018-06-07 11:46:32 +03:00
|
|
|
for e in entities:
|
2018-06-03 12:53:18 +03:00
|
|
|
start = e.offset
|
|
|
|
end = e.offset + e.length
|
|
|
|
result.append(del_surrogate(text[start:end]))
|
|
|
|
|
2018-06-07 11:46:32 +03:00
|
|
|
return result
|
2018-06-03 12:53:18 +03:00
|
|
|
|
|
|
|
|
2018-08-02 13:56:40 +03:00
|
|
|
def get_peer(peer):
|
|
|
|
try:
|
2018-12-28 19:54:15 +03:00
|
|
|
if isinstance(peer, int):
|
|
|
|
pid, cls = resolve_id(peer)
|
|
|
|
return cls(pid)
|
|
|
|
elif peer.SUBCLASS_OF_ID == 0x2d45687:
|
2018-08-02 13:56:40 +03:00
|
|
|
return peer
|
|
|
|
elif isinstance(peer, (
|
|
|
|
types.contacts.ResolvedPeer, types.InputNotifyPeer,
|
|
|
|
types.TopPeer)):
|
|
|
|
return peer.peer
|
|
|
|
elif isinstance(peer, types.ChannelFull):
|
|
|
|
return types.PeerChannel(peer.id)
|
|
|
|
|
2019-01-07 18:13:37 +03:00
|
|
|
if peer.SUBCLASS_OF_ID in (0x7d7c6f86, 0xd9c7fc18):
|
|
|
|
# ChatParticipant, ChannelParticipant
|
|
|
|
return types.PeerUser(peer.user_id)
|
|
|
|
|
2018-12-15 14:23:14 +03:00
|
|
|
peer = get_input_peer(peer, allow_self=False, check_hash=False)
|
2018-08-02 13:56:40 +03:00
|
|
|
if isinstance(peer, types.InputPeerUser):
|
|
|
|
return types.PeerUser(peer.user_id)
|
|
|
|
elif isinstance(peer, types.InputPeerChat):
|
|
|
|
return types.PeerChat(peer.chat_id)
|
|
|
|
elif isinstance(peer, types.InputPeerChannel):
|
|
|
|
return types.PeerChannel(peer.channel_id)
|
|
|
|
except (AttributeError, TypeError):
|
2018-11-23 17:47:09 +03:00
|
|
|
pass
|
|
|
|
_raise_cast_fail(peer, 'Peer')
|
2018-08-02 13:56:40 +03:00
|
|
|
|
|
|
|
|
2018-07-07 13:44:05 +03:00
|
|
|
def get_peer_id(peer, add_mark=True):
|
2017-12-28 15:31:43 +03:00
|
|
|
"""
|
|
|
|
Finds the ID of the given peer, and converts it to the "bot api" format
|
|
|
|
so it the peer can be identified back. User ID is left unmodified,
|
|
|
|
chat ID is negated, and channel ID is prefixed with -100.
|
|
|
|
|
|
|
|
The original ID and the peer type class can be returned with
|
2018-03-23 23:40:24 +03:00
|
|
|
a call to :meth:`resolve_id(marked_id)`.
|
2017-10-01 14:24:04 +03:00
|
|
|
"""
|
2017-10-06 22:47:10 +03:00
|
|
|
# First we assert it's a Peer TLObject, or early return for integers
|
2018-01-19 15:00:17 +03:00
|
|
|
if isinstance(peer, int):
|
2018-07-07 13:44:05 +03:00
|
|
|
return peer if add_mark else resolve_id(peer)[0]
|
2018-01-19 15:00:17 +03:00
|
|
|
|
2018-11-23 17:58:36 +03:00
|
|
|
# Tell the user to use their client to resolve InputPeerSelf if we got one
|
|
|
|
if isinstance(peer, types.InputPeerSelf):
|
|
|
|
_raise_cast_fail(peer, 'int (you might want to use client.get_peer_id)')
|
|
|
|
|
2018-01-19 15:00:17 +03:00
|
|
|
try:
|
2018-08-02 13:56:40 +03:00
|
|
|
peer = get_peer(peer)
|
|
|
|
except TypeError:
|
2018-01-19 15:00:17 +03:00
|
|
|
_raise_cast_fail(peer, 'int')
|
2017-10-05 13:59:44 +03:00
|
|
|
|
2018-08-02 13:56:40 +03:00
|
|
|
if isinstance(peer, types.PeerUser):
|
2017-10-09 20:40:39 +03:00
|
|
|
return peer.user_id
|
2018-08-02 13:56:40 +03:00
|
|
|
elif isinstance(peer, types.PeerChat):
|
2018-03-10 14:13:17 +03:00
|
|
|
# Check in case the user mixed things up to avoid blowing up
|
|
|
|
if not (0 < peer.chat_id <= 0x7fffffff):
|
2018-07-07 13:44:05 +03:00
|
|
|
peer.chat_id = resolve_id(peer.chat_id)[0]
|
2018-03-10 14:13:17 +03:00
|
|
|
|
2018-07-07 13:44:05 +03:00
|
|
|
return -peer.chat_id if add_mark else peer.chat_id
|
2018-08-02 13:56:40 +03:00
|
|
|
else: # if isinstance(peer, types.PeerChannel):
|
2018-03-10 14:13:17 +03:00
|
|
|
# Check in case the user mixed things up to avoid blowing up
|
2018-08-02 13:56:40 +03:00
|
|
|
if not (0 < peer.channel_id <= 0x7fffffff):
|
|
|
|
peer.channel_id = resolve_id(peer.channel_id)[0]
|
|
|
|
|
|
|
|
if not add_mark:
|
|
|
|
return peer.channel_id
|
2017-10-06 22:42:04 +03:00
|
|
|
|
2018-08-02 13:56:40 +03:00
|
|
|
# Concat -100 through math tricks, .to_supergroup() on
|
|
|
|
# Madeline IDs will be strictly positive -> log works.
|
|
|
|
return -(peer.channel_id + pow(
|
|
|
|
10, math.floor(math.log10(peer.channel_id) + 3)))
|
2017-10-01 14:24:04 +03:00
|
|
|
|
|
|
|
|
|
|
|
def resolve_id(marked_id):
|
2018-03-23 23:40:24 +03:00
|
|
|
"""Given a marked ID, returns the original ID and its :tl:`Peer` type."""
|
2017-10-01 14:24:04 +03:00
|
|
|
if marked_id >= 0:
|
2018-07-22 20:40:00 +03:00
|
|
|
return marked_id, types.PeerUser
|
2017-10-01 14:24:04 +03:00
|
|
|
|
2018-05-20 13:28:57 +03:00
|
|
|
# There have been report of chat IDs being 10000xyz, which means their
|
|
|
|
# marked version is -10000xyz, which in turn looks like a channel but
|
|
|
|
# it becomes 00xyz (= xyz). Hence, we must assert that there are only
|
|
|
|
# two zeroes.
|
|
|
|
m = re.match(r'-100([^0]\d*)', str(marked_id))
|
|
|
|
if m:
|
2018-07-22 20:40:00 +03:00
|
|
|
return int(m.group(1)), types.PeerChannel
|
2017-10-01 14:24:04 +03:00
|
|
|
|
2018-07-22 20:40:00 +03:00
|
|
|
return -marked_id, types.PeerChat
|
2017-10-01 14:24:04 +03:00
|
|
|
|
|
|
|
|
2018-08-01 00:23:52 +03:00
|
|
|
def _rle_decode(data):
|
|
|
|
"""
|
|
|
|
Decodes run-length-encoded `data`.
|
|
|
|
"""
|
2018-08-02 14:47:35 +03:00
|
|
|
if not data:
|
|
|
|
return data
|
|
|
|
|
2018-08-01 00:23:52 +03:00
|
|
|
new = b''
|
|
|
|
last = b''
|
|
|
|
for cur in data:
|
|
|
|
if last == b'\0':
|
2018-08-06 18:54:07 +03:00
|
|
|
new += last * cur
|
2018-08-01 00:23:52 +03:00
|
|
|
last = b''
|
|
|
|
else:
|
|
|
|
new += last
|
2018-08-06 18:54:07 +03:00
|
|
|
last = bytes([cur])
|
2018-08-01 00:23:52 +03:00
|
|
|
|
|
|
|
return new + last
|
|
|
|
|
|
|
|
|
2018-08-06 18:54:07 +03:00
|
|
|
def _rle_encode(string):
|
|
|
|
new = b''
|
|
|
|
count = 0
|
|
|
|
for cur in string:
|
|
|
|
if not cur:
|
|
|
|
count += 1
|
|
|
|
else:
|
|
|
|
if count:
|
|
|
|
new += b'\0' + bytes([count])
|
|
|
|
count = 0
|
|
|
|
|
|
|
|
new += bytes([cur])
|
|
|
|
return new
|
|
|
|
|
|
|
|
|
2018-08-02 14:47:35 +03:00
|
|
|
def _decode_telegram_base64(string):
|
2018-08-01 00:23:52 +03:00
|
|
|
"""
|
2018-08-02 14:59:27 +03:00
|
|
|
Decodes an url-safe base64-encoded string into its bytes
|
|
|
|
by first adding the stripped necessary padding characters.
|
2018-08-01 00:23:52 +03:00
|
|
|
|
2018-08-02 14:47:35 +03:00
|
|
|
This is the way Telegram shares binary data as strings,
|
|
|
|
such as Bot API-style file IDs or invite links.
|
|
|
|
|
2018-08-02 14:59:27 +03:00
|
|
|
Returns ``None`` if the input string was not valid.
|
|
|
|
"""
|
2018-08-01 00:23:52 +03:00
|
|
|
try:
|
2018-08-02 14:59:27 +03:00
|
|
|
return base64.urlsafe_b64decode(string + '=' * (len(string) % 4))
|
|
|
|
except (binascii.Error, ValueError, TypeError):
|
|
|
|
return None # not valid base64, not valid ascii, not a string
|
2018-08-01 00:23:52 +03:00
|
|
|
|
2018-08-02 14:47:35 +03:00
|
|
|
|
2018-08-06 18:54:07 +03:00
|
|
|
def _encode_telegram_base64(string):
|
|
|
|
"""
|
|
|
|
Inverse for `_decode_telegram_base64`.
|
|
|
|
"""
|
|
|
|
try:
|
|
|
|
return base64.urlsafe_b64encode(string).rstrip(b'=').decode('ascii')
|
|
|
|
except (binascii.Error, ValueError, TypeError):
|
|
|
|
return None # not valid base64, not valid ascii, not a string
|
|
|
|
|
|
|
|
|
2018-08-02 14:47:35 +03:00
|
|
|
def resolve_bot_file_id(file_id):
|
|
|
|
"""
|
|
|
|
Given a Bot API-style `file_id`, returns the media it represents.
|
|
|
|
If the `file_id` is not valid, ``None`` is returned instead.
|
|
|
|
|
|
|
|
Note that the `file_id` does not have information such as image
|
|
|
|
dimensions or file size, so these will be zero if present.
|
|
|
|
|
|
|
|
For thumbnails, the photo ID and hash will always be zero.
|
|
|
|
"""
|
|
|
|
data = _rle_decode(_decode_telegram_base64(file_id))
|
|
|
|
if not data or data[-1] == b'\x02':
|
2018-08-01 00:23:52 +03:00
|
|
|
return None
|
|
|
|
|
|
|
|
data = data[:-1]
|
|
|
|
if len(data) == 24:
|
|
|
|
file_type, dc_id, media_id, access_hash = struct.unpack('<iiqq', data)
|
2019-02-13 11:16:34 +03:00
|
|
|
|
|
|
|
if not (1 <= dc_id <= 5):
|
|
|
|
# Valid `file_id`'s must have valid DC IDs. Since this method is
|
|
|
|
# called when sending a file and the user may have entered a path
|
|
|
|
# they believe is correct but the file doesn't exist, this method
|
|
|
|
# may detect a path as "valid" bot `file_id` even when it's not.
|
|
|
|
# By checking the `dc_id`, we greatly reduce the chances of this
|
|
|
|
# happening.
|
|
|
|
return None
|
|
|
|
|
2018-08-01 00:23:52 +03:00
|
|
|
attributes = []
|
|
|
|
if file_type == 3 or file_type == 9:
|
|
|
|
attributes.append(types.DocumentAttributeAudio(
|
|
|
|
duration=0,
|
|
|
|
voice=file_type == 3
|
|
|
|
))
|
|
|
|
elif file_type == 4 or file_type == 13:
|
|
|
|
attributes.append(types.DocumentAttributeVideo(
|
|
|
|
duration=0,
|
|
|
|
w=0,
|
|
|
|
h=0,
|
|
|
|
round_message=file_type == 13
|
|
|
|
))
|
|
|
|
# elif file_type == 5: # other, cannot know which
|
|
|
|
elif file_type == 8:
|
|
|
|
attributes.append(types.DocumentAttributeSticker(
|
|
|
|
alt='',
|
|
|
|
stickerset=types.InputStickerSetEmpty()
|
|
|
|
))
|
|
|
|
elif file_type == 10:
|
|
|
|
attributes.append(types.DocumentAttributeAnimated())
|
|
|
|
|
|
|
|
return types.Document(
|
|
|
|
id=media_id,
|
|
|
|
access_hash=access_hash,
|
|
|
|
date=None,
|
|
|
|
mime_type='',
|
|
|
|
size=0,
|
2019-02-03 02:14:39 +03:00
|
|
|
thumbs=None,
|
2018-08-01 00:23:52 +03:00
|
|
|
dc_id=dc_id,
|
2018-12-18 18:37:07 +03:00
|
|
|
attributes=attributes,
|
|
|
|
file_reference=b''
|
2018-08-01 00:23:52 +03:00
|
|
|
)
|
|
|
|
elif len(data) == 44:
|
|
|
|
(file_type, dc_id, media_id, access_hash,
|
|
|
|
volume_id, secret, local_id) = struct.unpack('<iiqqqqi', data)
|
|
|
|
|
2019-02-13 11:16:34 +03:00
|
|
|
if not (1 <= dc_id <= 5):
|
|
|
|
return None
|
|
|
|
|
2018-08-01 00:23:52 +03:00
|
|
|
# Thumbnails (small) always have ID 0; otherwise size 'x'
|
|
|
|
photo_size = 's' if media_id or access_hash else 'x'
|
|
|
|
return types.Photo(id=media_id, access_hash=access_hash, sizes=[
|
|
|
|
types.PhotoSize(photo_size, location=types.FileLocation(
|
|
|
|
dc_id=dc_id,
|
|
|
|
volume_id=volume_id,
|
|
|
|
secret=secret,
|
2019-01-13 22:40:51 +03:00
|
|
|
local_id=local_id,
|
|
|
|
file_reference=b''
|
2018-08-01 00:23:52 +03:00
|
|
|
), w=0, h=0, size=0)
|
2019-01-13 22:38:16 +03:00
|
|
|
], file_reference=b'', date=None)
|
2018-08-01 00:23:52 +03:00
|
|
|
|
|
|
|
|
2018-08-06 18:54:07 +03:00
|
|
|
def pack_bot_file_id(file):
|
|
|
|
"""
|
|
|
|
Inverse operation for `resolve_bot_file_id`.
|
|
|
|
|
|
|
|
The only parameters this method will accept are :tl:`Document` and
|
|
|
|
:tl:`Photo`, and it will return a variable-length ``file_id`` string.
|
|
|
|
|
|
|
|
If an invalid parameter is given, it will ``return None``.
|
|
|
|
"""
|
2019-02-10 14:30:20 +03:00
|
|
|
if isinstance(file, types.MessageMediaDocument):
|
|
|
|
file = file.document
|
|
|
|
elif isinstance(file, types.MessageMediaPhoto):
|
|
|
|
file = file.photo
|
|
|
|
|
2018-08-06 18:54:07 +03:00
|
|
|
if isinstance(file, types.Document):
|
|
|
|
file_type = 5
|
|
|
|
for attribute in file.attributes:
|
|
|
|
if isinstance(attribute, types.DocumentAttributeAudio):
|
|
|
|
file_type = 3 if attribute.voice else 9
|
|
|
|
elif isinstance(attribute, types.DocumentAttributeVideo):
|
|
|
|
file_type = 13 if attribute.round_message else 4
|
|
|
|
elif isinstance(attribute, types.DocumentAttributeSticker):
|
|
|
|
file_type = 8
|
|
|
|
elif isinstance(attribute, types.DocumentAttributeAnimated):
|
|
|
|
file_type = 10
|
|
|
|
else:
|
|
|
|
continue
|
|
|
|
break
|
|
|
|
|
|
|
|
return _encode_telegram_base64(_rle_encode(struct.pack(
|
|
|
|
'<iiqqb', file_type, file.dc_id, file.id, file.access_hash, 2)))
|
|
|
|
|
|
|
|
elif isinstance(file, types.Photo):
|
|
|
|
size = next((x for x in reversed(file.sizes) if isinstance(
|
|
|
|
x, (types.PhotoSize, types.PhotoCachedSize))), None)
|
|
|
|
|
|
|
|
if not size or not isinstance(size.location, types.FileLocation):
|
|
|
|
return None
|
|
|
|
|
|
|
|
size = size.location
|
|
|
|
return _encode_telegram_base64(_rle_encode(struct.pack(
|
|
|
|
'<iiqqqqib', 2, size.dc_id, file.id, file.access_hash,
|
|
|
|
size.volume_id, size.secret, size.local_id, 2
|
|
|
|
)))
|
|
|
|
else:
|
|
|
|
return None
|
|
|
|
|
|
|
|
|
2018-08-02 14:47:35 +03:00
|
|
|
def resolve_invite_link(link):
|
|
|
|
"""
|
|
|
|
Resolves the given invite link. Returns a tuple of
|
2018-08-02 14:59:27 +03:00
|
|
|
``(link creator user id, global chat id, random int)``.
|
2018-08-02 14:47:35 +03:00
|
|
|
|
2018-08-02 14:59:27 +03:00
|
|
|
Note that for broadcast channels, the link creator
|
|
|
|
user ID will be zero to protect their identity.
|
|
|
|
Normal chats and megagroup channels will have such ID.
|
2018-08-02 14:47:35 +03:00
|
|
|
|
|
|
|
Note that the chat ID may not be accurate for chats
|
|
|
|
with a link that were upgraded to megagroup, since
|
2018-08-02 14:59:27 +03:00
|
|
|
the link can remain the same, but the chat ID will
|
|
|
|
be correct once a new link is generated.
|
2018-08-02 14:47:35 +03:00
|
|
|
"""
|
|
|
|
link_hash, is_link = parse_username(link)
|
|
|
|
if not is_link:
|
|
|
|
# Perhaps the user passed the link hash directly
|
|
|
|
link_hash = link
|
|
|
|
|
|
|
|
try:
|
|
|
|
return struct.unpack('>LLQ', _decode_telegram_base64(link_hash))
|
|
|
|
except (struct.error, TypeError):
|
|
|
|
return None, None, None
|
|
|
|
|
|
|
|
|
2018-09-19 15:22:35 +03:00
|
|
|
def resolve_inline_message_id(inline_msg_id):
|
|
|
|
"""
|
|
|
|
Resolves an inline message ID. Returns a tuple of
|
|
|
|
``(message id, peer, dc id, access hash)``
|
|
|
|
|
|
|
|
The ``peer`` may either be a :tl:`PeerUser` referencing
|
|
|
|
the user who sent the message via the bot in a private
|
|
|
|
conversation or small group chat, or a :tl:`PeerChannel`
|
|
|
|
if the message was sent in a channel.
|
|
|
|
|
|
|
|
The ``access_hash`` does not have any use yet.
|
|
|
|
"""
|
|
|
|
try:
|
|
|
|
dc_id, message_id, pid, access_hash = \
|
|
|
|
struct.unpack('<iiiq', _decode_telegram_base64(inline_msg_id))
|
|
|
|
peer = types.PeerChannel(-pid) if pid < 0 else types.PeerUser(pid)
|
|
|
|
return message_id, peer, dc_id, access_hash
|
|
|
|
except (struct.error, TypeError):
|
|
|
|
return None, None, None, None
|
|
|
|
|
|
|
|
|
2017-05-21 14:59:16 +03:00
|
|
|
def get_appropriated_part_size(file_size):
|
2018-03-23 23:40:24 +03:00
|
|
|
"""
|
|
|
|
Gets the appropriated part size when uploading or downloading files,
|
|
|
|
given an initial file size.
|
|
|
|
"""
|
2017-10-09 14:19:03 +03:00
|
|
|
if file_size <= 104857600: # 100MB
|
2016-10-09 13:57:38 +03:00
|
|
|
return 128
|
|
|
|
if file_size <= 786432000: # 750MB
|
|
|
|
return 256
|
|
|
|
if file_size <= 1572864000: # 1500MB
|
|
|
|
return 512
|
|
|
|
|
|
|
|
raise ValueError('File size too large')
|
2018-10-05 21:25:49 +03:00
|
|
|
|
|
|
|
|
|
|
|
class AsyncClassWrapper:
|
|
|
|
def __init__(self, wrapped):
|
|
|
|
self.wrapped = wrapped
|
|
|
|
|
|
|
|
def __getattr__(self, item):
|
|
|
|
w = getattr(self.wrapped, item)
|
|
|
|
async def wrapper(*args, **kwargs):
|
|
|
|
val = w(*args, **kwargs)
|
|
|
|
return await val if inspect.isawaitable(val) else val
|
|
|
|
|
|
|
|
if callable(w):
|
|
|
|
return wrapper
|
|
|
|
elif isinstance(w, property):
|
|
|
|
return w.fget(self.wrapped)
|
|
|
|
else:
|
|
|
|
return w
|