Merge pull request #2 from abslimit/master

added message chunking and MD strip with links preserved
This commit is contained in:
ChronosX88 2020-09-15 00:11:02 +04:00 committed by GitHub
commit 88b4c54d31
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 71 additions and 15 deletions

View File

@ -3,6 +3,7 @@ import asyncio
import logging import logging
import os import os
import uuid import uuid
import re
import toml import toml
from mastodon import Mastodon from mastodon import Mastodon
@ -15,9 +16,18 @@ from telethon.utils import get_extension
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
class BridgeBot: class BridgeBot:
def __init__(self, cfg: dict): def __init__(self, cfg: dict):
# RegExps
self.re_md_links = re.compile(r'\[(.+)\]\((https?:\/\/[\w\d./?=#&-]+)\)')
self.re_md_bold = re.compile(r'\*\*(.+)\*\*')
self.re_md_italic = re.compile(r'__(.+)__')
self.re_md_strike = re.compile(r'~~(.+)~~')
self.re_md_mono = re.compile(r'`(.+)`')
# Config init
self.config = cfg self.config = cfg
self.mastodon_clients = {} self.mastodon_clients = {}
self.mastodon_clients_visibility = {}
self.tg_mstdn_mappings = {} self.tg_mstdn_mappings = {}
for acc in cfg["mastodon"]["accounts"]: for acc in cfg["mastodon"]["accounts"]:
mastodon_client = Mastodon( mastodon_client = Mastodon(
@ -27,7 +37,10 @@ class BridgeBot:
api_base_url=acc["api_base_url"] api_base_url=acc["api_base_url"]
) )
self.mastodon_clients[acc["name"]] = mastodon_client self.mastodon_clients[acc["name"]] = mastodon_client
try:
self.mastodon_clients_visibility[acc["name"]] = acc["visibility"]
except KeyError:
self.mastodon_clients_visibility[acc["name"]] = None
for m in cfg["mastodon"]["mappings"]: for m in cfg["mastodon"]["mappings"]:
if self.tg_mstdn_mappings.get("tg_channel_handle", None) is None: if self.tg_mstdn_mappings.get("tg_channel_handle", None) is None:
self.tg_mstdn_mappings[m["tg_channel_handle"]] = [] self.tg_mstdn_mappings[m["tg_channel_handle"]] = []
@ -56,32 +69,73 @@ class BridgeBot:
if event.message.grouped_id is not None: if event.message.grouped_id is not None:
logging.warning("Albums isn't supported yet") logging.warning("Albums isn't supported yet")
return return
logging.debug("dobbry vechur")
logging.info(f"Catched new post from telegram channel {channel.username}") logging.info(f"Catched new post from telegram channel {channel.username}")
text: str = event.message.text # Common Mastodon message limit size. Change if you increased this limit.
if event.message.forward: mstdn_post_limit = 500
logging.debug("The current post is forwarded") #full_text = event.message.raw_text
text = f"[from {event.message.forward.chat.title} (https://t.me/{event.message.forward.chat.username})]\n\n" + text full_text = event.message.text
full_text = re.sub(self.re_md_links, r'\g<1> \g<2>', full_text)
full_text = re.sub(self.re_md_bold, r'\g<1>', full_text)
full_text = re.sub(self.re_md_italic, r'\g<1>', full_text)
full_text = re.sub(self.re_md_strike, r'\g<1>', full_text)
full_text = re.sub(self.re_md_mono, r'\g<1>', full_text)
# URL of Telegram message
tg_message_url = f"[https://t.me/{channel.username}/" + str(event.message.id) + "]\n\n"
if event.message.file and not (event.message.photo or event.message.video or event.message.gif):
full_text = full_text + "\n\n[К оригинальному посту приложен файл " + event.message.file.name + "]"
# Size of full text
full_text_size = len(full_text)
# Mastodon max post size with TG message URL
mstdn_post_size = mstdn_post_limit - len(tg_message_url)
# Initial vars
long_post_tail = ''
reply_start = 0
reply_end = 0
# Post text if tg message lenght is lt mstdn post limit
post_text: str = tg_message_url + full_text[reply_start:mstdn_post_size]
# Set reply_start to non zero for future chunking and make mstdn post with continuaniton note
if full_text_size > mstdn_post_size:
long_post_tail = "\n\n[Откройте оригинальный пост по ссылке, либо прочитайте продолжение в ответах к посту.]"
mstdn_post_size = mstdn_post_size - len(long_post_tail)
reply_start = full_text.rfind(' ', reply_start, mstdn_post_size)
post_text: str = tg_message_url + full_text[0:reply_start] + long_post_tail
temp_file_path: str = "" temp_file_path: str = ""
# Downloading media if tg post contains it
if (event.message.photo or event.message.video or event.message.gif) and not hasattr(event.message.media, "webpage"): if (event.message.photo or event.message.video or event.message.gif) and not hasattr(event.message.media, "webpage"):
logging.debug("Post contains the media, downloading it...") logging.info("Post contains the media, downloading it...")
temp_file_name = uuid.uuid4() temp_file_name = uuid.uuid4()
temp_file_path = f"/tmp/{temp_file_name}{get_extension(event.message.media)}" temp_file_path = f"/tmp/{temp_file_name}{get_extension(event.message.media)}"
await self.tg_client.download_media(event.message.media, temp_file_path) await self.tg_client.download_media(event.message.media, temp_file_path)
# Starting to post messages
for mstdn_acc_name in self.tg_mstdn_mappings[channel.username]: for mstdn_acc_name in self.tg_mstdn_mappings[channel.username]:
if self.mastodon_clients.get(mstdn_acc_name, None) is None: if self.mastodon_clients.get(mstdn_acc_name, None) is None:
logging.error(f"{mstdn_acc_name} doesn't exists in mastodon.accounts section of config!") logging.error(f"{mstdn_acc_name} doesn't exists in mastodon.accounts section of config!")
return return
# Make current client with config
current_mastodon_client = self.mastodon_clients[mstdn_acc_name] current_mastodon_client = self.mastodon_clients[mstdn_acc_name]
current_mstdn_acc_visibility = self.mastodon_clients_visibility[mstdn_acc_name]
# Attach media if tg post contains it
if temp_file_path != "": if temp_file_path != "":
mstdn_media_meta = current_mastodon_client.media_post(temp_file_path) mstdn_media_meta = current_mastodon_client.media_post(temp_file_path)
current_mastodon_client.status_post(text, media_ids=[mstdn_media_meta])
else: else:
current_mastodon_client.toot(text) mstdn_media_meta = None
# First root mstdn post
reply_to = current_mastodon_client.status_post(post_text, media_ids=[mstdn_media_meta], visibility=current_mstdn_acc_visibility)
tg_message_url = f"[Продолжение https://t.me/{channel.username}/" + str(event.message.id) + "]\n\n"
# Chunking post into mstdn limit chunks and reply to root post
while reply_start + mstdn_post_limit < full_text_size:
reply_end = full_text.rfind(' ', reply_start, reply_start + mstdn_post_limit - len(tg_message_url))
post_text: str = tg_message_url + full_text[reply_start+1:reply_end]
reply_to = current_mastodon_client.status_post(post_text, in_reply_to_id=reply_to, visibility=current_mstdn_acc_visibility)
reply_start = reply_end
# Final chunk to reply to root post
if reply_start > 0:
post_text: str = tg_message_url + full_text[reply_start+1:full_text_size]
reply_to = current_mastodon_client.status_post(post_text, in_reply_to_id=reply_to, visibility=current_mstdn_acc_visibility)
# Delete media attach
if temp_file_path != "": if temp_file_path != "":
os.remove(temp_file_path) os.remove(temp_file_path)
if __name__ == '__main__': if __name__ == '__main__':
parser = argparse.ArgumentParser() parser = argparse.ArgumentParser()
parser.add_argument('--config', type=str, parser.add_argument('--config', type=str,

View File

@ -2,10 +2,6 @@
account_name = "ChronosX" account_name = "ChronosX"
tg_channel_handle = "ChronosX_Channel" tg_channel_handle = "ChronosX_Channel"
[[mastodon.mappings]]
account_name = "floppy"
tg_channel_handle = "netwhood_news"
[[mastodon.accounts]] [[mastodon.accounts]]
name = "ChronosX" name = "ChronosX"
client_id = "abc" client_id = "abc"
@ -13,6 +9,11 @@
access_token = "ghi" access_token = "ghi"
api_base_url = "mstdn.netwhood.online" api_base_url = "mstdn.netwhood.online"
[[mastodon.mappings]]
account_name = "floppy"
tg_channel_handle = "netwhood_news"
[[mastodon.accounts]] [[mastodon.accounts]]
name = "floppy" name = "floppy"
client_id = "abc" client_id = "abc"
@ -24,3 +25,4 @@
api_id = "123123" api_id = "123123"
api_hash = "qwerty" api_hash = "qwerty"
session_file = "/path/to/session/file" session_file = "/path/to/session/file"
channels = ['netwhood_news', 'ChronosX_Channel']