From f360f1167c475c04cf5ce892feabe12eb7e99600 Mon Sep 17 00:00:00 2001 From: vvzvlad Date: Sun, 2 Feb 2025 18:51:50 +0300 Subject: [PATCH] BIG refactoring --- Dockerfile | 2 +- api_server.py | 190 +++++++++++------------------- config.py | 26 ++--- post_parser.py | 283 +++++++++++++++++++++++++++++++++++++++++++++ requirements.txt | 2 +- rss_generator.py | 131 +++++++++++++++++++++ telegram_client.py | 17 +-- 7 files changed, 494 insertions(+), 157 deletions(-) create mode 100644 post_parser.py create mode 100644 rss_generator.py diff --git a/Dockerfile b/Dockerfile index 7dddc7e..efab6d4 100644 --- a/Dockerfile +++ b/Dockerfile @@ -6,4 +6,4 @@ COPY requirements.txt . RUN pip install --no-cache-dir -r requirements.txt COPY *.py . -CMD ["uvicorn", "api_server:app", "--host", "0.0.0.0", "--port", "8000"] \ No newline at end of file +CMD ["python", "api_server.py"] \ No newline at end of file diff --git a/api_server.py b/api_server.py index b779a18..1f963a0 100644 --- a/api_server.py +++ b/api_server.py @@ -1,173 +1,113 @@ import logging -import json -import re +import os +import mimetypes from contextlib import asynccontextmanager from fastapi import FastAPI, HTTPException, Response, BackgroundTasks from fastapi.responses import HTMLResponse, FileResponse, PlainTextResponse from telegram_client import TelegramClient from config import get_settings -import mimetypes -import os +from rss_generator import generate_channel_rss from pyrogram import errors -from feedgen.feed import FeedGenerator +from post_parser import PostParser logger = logging.getLogger(__name__) client = TelegramClient() -settings = get_settings() +Config = get_settings() @asynccontextmanager async def lifespan(_: FastAPI): - # Startup await client.start() yield - # Shutdown await client.stop() -app = FastAPI( - title="PyroTg Bridge", - lifespan=lifespan -) +app = FastAPI( title="Pyrogram Bridge", lifespan=lifespan) if __name__ == "__main__": import uvicorn - uvicorn.run( "api_server:app", host=settings["api_host"], port=settings["api_port"], reload=False) + uvicorn.run("api_server:app", host=Config["api_host"], port=Config["api_port"], reload=True) @app.get("/html/{channel}/{post_id}", response_class=HTMLResponse) +@app.get("/post/html/{channel}/{post_id}", response_class=HTMLResponse) async def get_post_html(channel: str, post_id: int): try: - post = await client.get_post(channel, post_id) - if post.get("error"): - raise HTTPException( - status_code=404, - detail=post["details"] - ) - if "error" in post: - raise HTTPException(status_code=404, detail=post["details"]) - return post["html"] + parser = PostParser(client.client) + html_content = await parser.get_post(channel, post_id, 'html') + if not html_content: + raise HTTPException(status_code=404, detail="Post not found") + return html_content except Exception as e: - logger.error(f"HTML endpoint error: {str(e)}") - raise HTTPException(status_code=500, detail=str(e)) from e + error_message = f"Failed to get HTML post for channel {channel}, post_id {post_id}: {str(e)}" + logger.error(error_message) + raise HTTPException(status_code=500, detail=error_message) from e + @app.get("/json/{channel}/{post_id}") +@app.get("/post/json/{channel}/{post_id}") async def get_post(channel: str, post_id: int): try: - data = await client.get_post(channel, post_id) - if data.get("error"): - raise HTTPException( - status_code=404, - detail=data - ) - return Response( - content=json.dumps(data), - media_type="application/json" - ) + parser = PostParser(client.client) + json_content = await parser.get_post(channel, post_id, 'json') + if not json_content: + raise HTTPException(status_code=404, detail="Post not found") + return json_content except Exception as e: - logger.error(f"API error: {str(e)}") - raise HTTPException( - status_code=404, - detail={ - "error": "post_retrieval_error", - "message": str(e) - } - ) from e + error_message = f"Failed to get JSON post for channel {channel}, post_id {post_id}: {str(e)}" + logger.error(error_message) + raise HTTPException(status_code=500, detail=error_message) from e -@app.get("/status") +@app.get("/health") async def health_check(): - return { - "status": "ok", - "connected": client.client.is_connected - } + try: + me = await client.client.get_me() + return { + "status": "ok", + "tg_connected": client.client.is_connected, + "tg_name": me.username, + "tg_id": me.id, + "tg_phone": me.phone_number, + "tg_first_name": me.first_name, + "tg_last_name": me.last_name, + } + except Exception as e: + error_message = f"Failed to get health check: {str(e)}" + logger.error(error_message) + raise HTTPException(status_code=500, detail=error_message) from e @app.get("/media/{file_id}") -async def get_media( - file_id: str, - background_tasks: BackgroundTasks, - response: Response -): +async def get_media(file_id: str, background_tasks: BackgroundTasks): try: - file_path = await client.download_media_file(file_id) + file_path = await client.download_media_file(file_id) + logger.info(f"Downloaded media file {file_id} to {file_path}") + if not os.path.exists(file_path): raise HTTPException(status_code=404, detail="Temporary file not found") - # Additional safety checks - if not os.path.exists(file_path): - raise HTTPException(status_code=404, detail="Temporary file not found") + media_type, _ = mimetypes.guess_type(file_path) # Determine media type from file extension + if not media_type: media_type = "application/octet-stream" - # Determine media type from file extension - media_type, _ = mimetypes.guess_type(file_path) - if not media_type: - media_type = "application/octet-stream" - - # Add cleanup task background_tasks.add_task(lambda: os.remove(file_path) if os.path.exists(file_path) else None) - return FileResponse( - path=file_path, - media_type=media_type, - headers={ - "Content-Disposition": f"inline; filename={os.path.basename(file_path)}" - } - ) - + headers = { "Content-Disposition": f"inline; filename={os.path.basename(file_path)}" } + return FileResponse( path=file_path, media_type=media_type, headers=headers) except HTTPException: - # Пробрасываем уже сформированные HTTPException как есть raise except errors.RPCError as e: logger.error(f"Media request RPC error {file_id}: {type(e).__name__} - {str(e)}") - raise HTTPException(status_code=404, detail="File not found in Telegram") + raise HTTPException(status_code=404, detail="File not found in Telegram") from e except Exception as e: - logger.error(f"Media request failed {file_id}: {type(e).__name__} - {str(e)}") - raise HTTPException( - status_code=500, - detail=f"Internal server error: {str(e)}" - ) + error_message = f"Failed to get media for file_id {file_id}: {str(e)}" + logger.error(error_message) + raise HTTPException(status_code=500, detail=error_message) from e -@app.get("/rss/{channel}", response_class=PlainTextResponse) -async def get_rss_feed(channel: str): +@app.get("/rss/{channel}", response_class=Response) +async def get_rss_feed(channel: str, limit: int = 20): try: - # Get last 20 posts - posts = await client.get_channel_posts(channel, limit=20) - - # Create FeedGenerator - fg = FeedGenerator() - channel_title = posts[0].get('channel_title', channel) if posts else channel - channel_icon = posts[0].get('channel_icon', '') if posts else '' - - fg.title(channel_title) - fg.link(href=f"https://t.me/{channel}", rel='alternate') - fg.description(f'Telegram channel {channel} RSS feed') - fg.language('ru-ru') - - if channel_icon: - fg.logo(f"{settings['pyrogram_bridge_url']}/media/{channel_icon}") - fg.icon(f"{settings['pyrogram_bridge_url']}/media/{channel_icon}") - - # Add channel metadata - fg.id(f"{settings['pyrogram_bridge_url']}/rss/{channel}") - fg.link(href=f"{settings['pyrogram_bridge_url']}/rss/{channel}", rel='self', type='application/rss+xml') - - # Add posts - for post in posts: - fe = fg.add_entry() - fe.id(f"{settings['pyrogram_bridge_url']}/html/{channel}/{post['id']}") - fe.title(post['title']) - fe.link(href=f"https://t.me/{channel}/{post['id']}") - fe.pubDate(post['date'].astimezone(tz=None)) - fe.description(f"") - fe.content(content=post['html'], type='CDATA') - - # Add media enclosures - for media in post.get('media', []): - if media.get('url'): - fe.enclosure( - url=f"{settings['pyrogram_bridge_url']}/media/{media['url']}", - type=media.get('type', 'image/jpeg'), - length=str(media.get('size', 0)) - ) - - # Generate RSS - rss = fg.rss_str(pretty=True) - return Response(content=rss, media_type="application/xml") - + rss_content = await generate_channel_rss(channel, client=client.client, limit=limit) + return Response(content=rss_content, media_type="application/xml") + except ValueError as e: + error_message = f"Invalid parameters for RSS feed generation: {str(e)}" + logger.error(error_message) + raise HTTPException(status_code=400, detail=error_message) from e except Exception as e: - logger.error(f"RSS generation error: {str(e)}") - raise HTTPException(status_code=500, detail="RSS feed generation failed") \ No newline at end of file + error_message = f"Failed to generate RSS feed for channel {channel}: {str(e)}" + logger.error(error_message) + raise HTTPException(status_code=500, detail=error_message) from e diff --git a/config.py b/config.py index 8e8a3bb..30dd9ea 100644 --- a/config.py +++ b/config.py @@ -1,22 +1,14 @@ import os -TG_API_ID = int(os.getenv("TG_API_ID")) -TG_API_HASH = os.getenv("TG_API_HASH") -SESSION_PATH = os.getenv("SESSION_PATH", "session.file") or "session.file" -API_HOST = os.getenv("API_HOST", "0.0.0.0") -API_PORT = int(os.getenv("API_PORT") or 8000) -REQUEST_TIMEOUT = int(os.getenv("REQUEST_TIMEOUT") or 30) -SESSION_STRING = os.getenv("TG_SESSION_STRING", "") - def get_settings(): return { - "tg_api_id": TG_API_ID, - "tg_api_hash": TG_API_HASH, - "session_path": SESSION_PATH, - "api_host": API_HOST, - "api_port": API_PORT, - "request_timeout": REQUEST_TIMEOUT, - "session_string": SESSION_STRING, + "tg_api_id": int(os.getenv("TG_API_ID")), + "tg_api_hash": os.getenv("TG_API_HASH"), + "session_path": os.getenv("SESSION_PATH", "session.file") or "session.file", + "api_host": os.getenv("API_HOST", "0.0.0.0"), + "api_port": int(os.getenv("API_PORT") or 8000), + "session_string": os.getenv("TG_SESSION_STRING", ""), "pyrogram_bridge_url": os.getenv("PYROGRAM_BRIDGE_URL", ""), - "log_level": os.getenv("LOG_LEVEL", "INFO") - } \ No newline at end of file + "log_level": os.getenv("LOG_LEVEL", "INFO"), + "debug": os.getenv("DEBUG", "False") == "True" + } diff --git a/post_parser.py b/post_parser.py new file mode 100644 index 0000000..b087c6c --- /dev/null +++ b/post_parser.py @@ -0,0 +1,283 @@ +import logging +import copy +import re +from datetime import datetime +from typing import Union, Dict, Any, List, Optional +from pyrogram.types import Message +from pyrogram.enums import MessageMediaType +from config import get_settings + +Config = get_settings() + +logger = logging.getLogger(__name__) + +#tests +#http://127.0.0.1:8000/post/html/DragorWW_space/114 — video +#http://127.0.0.1:8000/post/html/DragorWW_space/20 - many photos +#http://127.0.0.1:8000/post/html/DragorWW_space/58 - photos+video +#http://127.0.0.1:8000/post/html/DragorWW_space/44 - poll +#http://127.0.0.1:8000/post/html/DragorWW_space/46 - photo +#http://127.0.0.1:8000/post/html/DragorWW_space/49, http://127.0.0.1:8000/post/html/DragorWW_space/63 — webpage +#http://127.0.0.1:8000/post/html/deckru/826 - animation +#http://127.0.0.1:8000/post/html/DragorWW_space/61 — links +#http://127.0.0.1:8000/post/html/theyforcedme/3577 - video note +#http://127.0.0.1:8000/post/html/theyforcedme/3572 - audio +#http://127.0.0.1:8000/post/html/theyforcedme/3558 audio-note +#http://127.0.0.1:8000/html/vvzvlad_lytdybr/426 - sticker + +class PostParser: + def __init__(self, client): + self.client = client + + def _debug_message(self, message: Message) -> Message: + if Config["debug"]: + debug_message = copy.deepcopy(message) + debug_message.sender_chat = None + debug_message.caption_entities = None + debug_message.reactions = None + debug_message.entities = None + print(debug_message) + return + + async def get_post(self, channel: str, post_id: int, output_type: str = 'json') -> Union[str, Dict[Any, Any]]: + try: + message = await self.client.get_messages(channel, post_id) + + self._debug_message(message) + + if not message: + logger.error(f"post_not_found: channel {channel}, post_id {post_id}") + return None + + if output_type == 'html': + return self._format_html(message) + elif output_type == 'json': + return self._format_json(message) + else: + logger.error(f"Invalid output type: {output_type}") + return None + + except Exception as e: + logger.error(f"post_parsing_error: channel {channel}, post_id {post_id}, error {str(e)}") + raise + + def _format_json(self, message: Message, naked: bool = False) -> Dict[Any, Any]: + html_content = self._format_html(message, naked=naked) + result = { + 'channel': message.chat.username, + 'message_id': message.id, + 'date': datetime.timestamp(message.date), + 'text': message.text or message.caption or '', + 'html': html_content, + 'title': self._generate_title(message), + 'author': self._get_author_info(message), + 'views': message.views, + } + + if message.media_group_id: + result['media_group_id'] = message.media_group_id + + return result + + def _get_author_info(self, message: Message) -> str: + if message.sender_chat: + title = getattr(message.sender_chat, 'title', '').strip() + username = getattr(message.sender_chat, 'username', '').strip() + return f"{title} by @{username}" if username else title + elif message.from_user: + first = getattr(message.from_user, 'first_name', '').strip() + last = getattr(message.from_user, 'last_name', '').strip() + username = getattr(message.from_user, 'username', '').strip() + name = ' '.join(filter(None, [first, last])) + return f"{name} by @{username}" if username else name + return "Unknown author" + + def _generate_title(self, message: Message) -> str: + text = message.text or message.caption or '' + if not text: + if message.media == MessageMediaType.PHOTO: return "📷 Photo" + elif message.media == MessageMediaType.VIDEO: return "🎥 Video" + elif message.media == MessageMediaType.ANIMATION: return "🎞 GIF" + elif message.media == MessageMediaType.AUDIO: return "🎵 Audio" + elif message.media == MessageMediaType.VOICE: return "🎤 Voice message" + elif message.media == MessageMediaType.VIDEO_NOTE: return "🎥 Video message" + elif message.media == MessageMediaType.STICKER: return "🎯 Sticker" + return "📷 Media post" + + # Remove URLs + text = re.sub(r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', '', text) + # Remove HTML tags + text = re.sub('<[^<]+?>', '', text) + # Remove multiple spaces and empty lines + text = '\n'.join(line.strip() for line in text.split('\n') if line.strip()) + + # Get first non-empty line + first_line = text.split('\n')[0] if text else "" + + max_length = 100 + if len(first_line) <= max_length: + return first_line.strip() + + # Cut to last space + trimmed = first_line[:max_length] + last_space = trimmed.rfind(' ') + if last_space > 0: + trimmed = trimmed[:last_space] + + return f"{trimmed.strip()}..." if trimmed else "" + + def _format_html(self, message: Message, naked: bool = False) -> str: + text = message.text.html if message.text else message.caption.html if message.caption else '' + text = text.replace('\n', '
') + html_content = [] + + if poll := getattr(message, "poll", None): # Poll formatting + if poll_html := self._format_poll(poll): + html_content.append(poll_html) + + base_url = Config['pyrogram_bridge_url'] + if message.media: + file_id = self._get_file_id(message) + if file_id: + html_content.append(f'
') + if message.media in [MessageMediaType.PHOTO, MessageMediaType.DOCUMENT]: + html_content.append(f'Media content') + elif message.media == MessageMediaType.VIDEO: + html_content.append(f'') + elif message.media == MessageMediaType.ANIMATION: + html_content.append(f'') + elif message.media == MessageMediaType.VIDEO_NOTE: + html_content.append(f'') + elif message.media == MessageMediaType.AUDIO: + mime_type = getattr(message.audio, 'mime_type', 'audio/mpeg') + html_content.append(f'') + elif message.media == MessageMediaType.VOICE: + mime_type = getattr(message.voice, 'mime_type', 'audio/ogg') + html_content.append(f'') + elif message.media == MessageMediaType.STICKER: + emoji = getattr(message.sticker, 'emoji', '') + html_content.append(f'Sticker {emoji}') + html_content.append('
') + + + if webpage := getattr(message, "web_page", None): # Web page preview + if webpage_html := self._format_webpage(webpage): + html_content.append(webpage_html) + + if text: # Message text + html_content.append(f'
{text}
') + + if not naked: + if reactions_views_html := self._format_reactions_and_views(message): # Add reactions and views + html_content.append(reactions_views_html) + + if not naked: + html = self._wrap_html(html_content) + else: + html = '\n'.join(html_content) + + return html + + def _format_webpage(self, webpage) -> Union[str, None]: + base_url = Config['pyrogram_bridge_url'] + try: + if photo := getattr(webpage, "photo", None): + if file_id := getattr(photo, "file_id", None): + return ( + f'
' + f'' + f'' + f'
' + ) + return None + except Exception as e: + logger.error(f"webpage_parsing_error: url {getattr(webpage, 'url', 'unknown')}, error {str(e)}") + return None + + def _wrap_html(self, html_content: list) -> str: + struct = [ + '', '', + '', '', '', + '', *html_content, '', + '' + ] + html_content = '\n'.join(struct) + return html_content + + def _format_reactions_and_views(self, message: Message) -> Union[str, None]: + try: + html_parts = [] + + if reactions := getattr(message, "reactions", None): + reactions_html = '' + for reaction in reactions.reactions: + reactions_html += f'{reaction.emoji} {reaction.count} ' + html_parts.append(reactions_html) + + if views := getattr(message, "views", None): + views_html = f'(Views: {views})' + html_parts.append(views_html) + + return ' '.join(html_parts) if html_parts else None + + except Exception as e: + logger.error(f"reactions_views_parsing_error: {str(e)}") + return None + + def _format_poll(self, poll) -> str: + try: + poll_text = f"📊 Poll: {poll.question}\n" + if hasattr(poll, "options") and poll.options: + for i, option in enumerate(poll.options, 1): + poll_text += f"{i}. {getattr(option, 'text', '')}\n" + poll_text += "\n→ Vote in Telegram 🔗\n" + return f'
{poll_text.replace(chr(10), "
")}
' + except Exception as e: + logger.error(f"poll_parsing_error: {str(e)}") + return '
[Error displaying poll]
' + + def _get_file_id(self, message: Message) -> Union[str, None]: + try: + media_mapping = { + MessageMediaType.PHOTO: lambda m: m.photo.file_id, + MessageMediaType.VIDEO: lambda m: m.video.file_id, + MessageMediaType.DOCUMENT: lambda m: m.document.file_id, + MessageMediaType.AUDIO: lambda m: m.audio.file_id, + MessageMediaType.VOICE: lambda m: m.voice.file_id, + MessageMediaType.VIDEO_NOTE: lambda m: m.video_note.file_id, + MessageMediaType.ANIMATION: lambda m: m.animation.file_id, + MessageMediaType.STICKER: lambda m: m.sticker.file_id + } + + if message.media in media_mapping: + return media_mapping[message.media](message) + + return None + + except Exception as e: + logger.error(f"file_id_extraction_error: media_type {message.media}, error {str(e)}") + return None + + async def get_recent_posts(self, channel: str, limit: int = 20) -> List[Dict[Any, Any]]: + """ + Get recent posts from channel + """ + try: + messages = [] + async for message in self.client.get_chat_history(channel, limit=limit): + try: + post = await self.get_post(channel, message.id, output_type='json') + if post: + messages.append(post) + except Exception as e: + logger.error(f"message_processing_error: channel {channel}, message_id {message.id}, error {str(e)}") + continue + + return messages + + except Exception as e: + logger.error(f"recent_posts_error: channel {channel}, error {str(e)}") + raise + + def format_message_for_feed(self, message: Message, naked: bool = False) -> Dict[Any, Any]: + return self._format_json(message, naked=naked) diff --git a/requirements.txt b/requirements.txt index 49a5239..9941ce7 100644 --- a/requirements.txt +++ b/requirements.txt @@ -4,5 +4,5 @@ python-multipart kurigram tgcrypto pillow -feedgen +feedgen>=0.9.0 python-dateutil \ No newline at end of file diff --git a/rss_generator.py b/rss_generator.py new file mode 100644 index 0000000..7430c4b --- /dev/null +++ b/rss_generator.py @@ -0,0 +1,131 @@ +import logging +from feedgen.feed import FeedGenerator +from datetime import datetime, timezone +from typing import Optional +from post_parser import PostParser +from config import get_settings +from pyrogram import Client + +Config = get_settings() + +logger = logging.getLogger(__name__) + +async def generate_channel_rss(channel: str, post_parser: Optional[PostParser] = None, client = None, limit: int = 20) -> str: + """ + Generate RSS feed for channel using actual messages + Args: + channel: Telegram channel name + post_parser: Optional PostParser instance. If not provided, will create new one + client: Telegram client instance + limit: Maximum number of posts to include in the RSS feed + Returns: + RSS feed as string in XML format + """ + if limit < 1: + raise ValueError(f"limit must be positive, got {limit}") + if limit > 100: + raise ValueError(f"limit cannot exceed 100, got {limit}") + + try: + if post_parser is None: + post_parser = PostParser(client=client) + + fg = FeedGenerator() + fg.load_extension('dc') + base_url = Config['pyrogram_bridge_url'] + + # Get channel info + channel_info = await post_parser.client.get_chat(channel) + channel_title = channel_info.title or f"Telegram: {channel}" + channel_icon = getattr(channel_info.photo, 'small_file_id', None) if channel_info.photo else None + + # Set feed metadata + fg.title(channel_title) + fg.link(href=f"https://t.me/{channel}", rel='alternate') + fg.description(f'Telegram channel {channel} RSS feed') + fg.language('ru') + fg.dc.dc_creator(f"{channel_title} by {channel}") + + if channel_icon: + fg.logo(f"{base_url}/media/{channel_icon}") + fg.icon(f"{base_url}/media/{channel_icon}") + + fg.id(f"{base_url}/rss/{channel}") + + # First collect all posts + posts = [] + media_groups = {} + + async for message in post_parser.client.get_chat_history(channel, limit=limit): + try: + if message.media_group_id: + naked = True + else: + naked = False + post = post_parser.format_message_for_feed(message, naked=naked) + if not post: + continue + + if post.get('media_group_id'): + if post['media_group_id'] not in media_groups: + media_groups[post['media_group_id']] = [] + media_groups[post['media_group_id']].append(post) + else: + posts.append(post) + + except Exception as e: + logger.error(f"feed_entry_error: channel {channel}, message_id {message.id}, error {str(e)}") + continue + + # Merge media groups + for group_id, group_posts in media_groups.items(): + if not group_posts: + continue + + # Find post with most meaningful title + main_post = group_posts[0] + for post in group_posts: + current_title = post.get('title', '') + if current_title and current_title not in ['📷 Photo', '📹 Video', '📄 Document']: + main_post = post + break + + merged_post = main_post.copy() + merged_html = [] + + for post in group_posts: + merged_html.append(post['html']) + + merged_post['html'] = '\n'.join(merged_html) + posts.append(merged_post) + + # Sort posts by date + posts.sort(key=lambda x: x['date'], reverse=True) + + # Generate feed entries + for post in posts: + fe = fg.add_entry() + fe.title(post.get('title', 'Untitled post')) + + post_link = f"https://t.me/{channel}/{post['message_id']}" + fe.link(href=post_link) + + html_content = post.get('html', '') + fe.description(f"") + fe.content(content=html_content, type='CDATA') + + pub_date = datetime.fromtimestamp(post['date'], tz=timezone.utc) + fe.pubDate(pub_date) + fe.guid(post_link, permalink=True) + + if post.get('author'): + fe.author(name="", email=post['author']) + + rss_feed = fg.rss_str(pretty=True) + if isinstance(rss_feed, bytes): + return rss_feed.decode('utf-8') + return rss_feed + + except Exception as e: + logger.error(f"rss_generation_error: channel {channel}, error {str(e)}") + raise \ No newline at end of file diff --git a/telegram_client.py b/telegram_client.py index b812c20..61abddc 100644 --- a/telegram_client.py +++ b/telegram_client.py @@ -6,19 +6,6 @@ import os import re -#tests -#http://127.0.0.1:8000/html/DragorWW_space/114 — video -#http://127.0.0.1:8000/html/DragorWW_space/20 - many photos -#http://127.0.0.1:8000/html/DragorWW_space/58 - photos+video -#http://127.0.0.1:8000/html/DragorWW_space/44 - poll -#http://127.0.0.1:8000/html/DragorWW_space/46 - photo -#http://127.0.0.1:8000/html/DragorWW_space/49, http://127.0.0.1:8000/html/DragorWW_space/63 — webpage -#http://127.0.0.1:8000/html/deckru/826 - animation -#http://127.0.0.1:8000/html/DragorWW_space/61 — links -#http://127.0.0.1:8000/html/theyforcedme/3577 - video note -#http://127.0.0.1:8000/html/theyforcedme/3572 - audio -#http://127.0.0.1:8000/html/theyforcedme/3558 audio-note - logger = logging.getLogger(__name__) settings = get_settings() @@ -323,6 +310,10 @@ class TelegramClient: # Trim and remove HTML tags clean_line = re.sub('<[^<]+?>', '', first_line) + # Check if message contains only reactions + if re.match(r'^Reactions: ', clean_line): + return "📷 Media post" + max_length = 65 if len(clean_line) <= max_length: return clean_line.strip()