vvzvlad/pyrogram-bridge
1
0
Fork 0
Code Issues 6 Pull Requests Actions 8 Packages Projects Releases Wiki Activity

Refactor PostParser: Improve code style and method visibility

Browse Source
This commit is contained in:
vvzvlad
2025-02-09 06:04:01 +03:00
parent 10434bbbd3
commit 7c9fd859d7
3 changed files with 25 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files
api_server.py
+5 -3
View File
@@ -541,11 +541,13 @@ async def get_rss_feed(channel: str, token: str | None = None, limit: int = 50,
raise HTTPException(status_code=400, detail=error_message) from e
except errors.FloodWait as e:
wait_time = e.value
random_additional_wait = random.uniform(0, wait_time * 1.5)
random_additional_wait = random.uniform(0, wait_time * 2.5)
total_wait_time = wait_time + random_additional_wait
logger.warning(f"FloodWait detected for channel {channel}, waiting {total_wait_time:.1f} seconds (base: {wait_time}s, random: {random_additional_wait:.1f}s)")
if total_wait_time > 190: total_wait_time = 190
logger.warning(f"TG FloodWait for channel {channel}, waiting {total_wait_time:.1f} seconds (base: {wait_time}s, random: {random_additional_wait:.1f}s)")
await asyncio.sleep(total_wait_time)
logger.info(f"FloodWait finished for channel {channel}, retrying RSS feed generation")
logger.info(f"TG FloodWait finished for channel {channel}, retrying RSS feed generation")
continue
except Exception as e:
error_message = f"Failed to generate RSS feed for channel {channel}: {str(e)}"
post_parser.py
+15 -36
View File
@@ -68,7 +68,7 @@ class PostParser:
print(debug_message)
return
def channel_name_prepare(self, channel: str):
def _channel_name_prepare(self, channel: str):
if isinstance(channel, str) and channel.startswith('-100'): # Convert numeric channel ID to int
channel_id = int(channel)
return channel_id
@@ -78,7 +78,7 @@ class PostParser:
async def get_post(self, channel: str, post_id: int, output_type: str = 'json') -> Union[str, Dict[Any, Any]]:
print(f"Getting post {channel}, {post_id}")
try:
channel = self.channel_name_prepare(channel)
channel = self._channel_name_prepare(channel)
message = await self.client.get_messages(channel, post_id)
self._debug_message(message)
@@ -123,14 +123,14 @@ class PostParser:
return "✨ Channel created"
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"
elif message.media == MessageMediaType.POLL: return "📊 Poll"
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"
elif message.media == MessageMediaType.POLL: return "📊 Poll"
return "📷 Media post"
# Remove URLs
@@ -213,14 +213,14 @@ class PostParser:
if re.search(r'(?i)\bдонат\w*\b', message_text):
flags.append("donat")
# Check if the post's reactions contain more than 5 clown emojis (🤡).
# Check if the post's reactions contain more clown emojis (🤡).
if getattr(message, "reactions", None):
for reaction in message.reactions.reactions:
if reaction.emoji == "🤡" and reaction.count >= 30:
flags.append("clown")
break
# Check if the post's reactions contain more than 5 poo emojis (💩).
# Check if the post's reactions contain more poo emojis (💩).
if getattr(message, "reactions", None):
for reaction in message.reactions.reactions:
if reaction.emoji == "💩" and reaction.count >= 30:
@@ -323,10 +323,8 @@ class PostParser:
def _generate_html_header(self, message: Message) -> str:
content_header = []
# Add forwarded from or reply info if present
if forward_html := self._format_forward_info(message):
content_header.append(forward_html)
elif reply_html := self._format_reply_info(message):
content_header.append(reply_html)
if forward_html := self._format_forward_info(message): content_header.append(forward_html)
elif reply_html := self._format_reply_info(message): content_header.append(reply_html)
html_header = '\n'.join(content_header)
html_header = self._sanitize_html(html_header)
return html_header
@@ -533,24 +531,6 @@ class PostParser:
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]]:
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 _save_media_file_ids(self, message: Message) -> None:
try:
file_data = {
@@ -567,8 +547,7 @@ class PostParser:
if message.media:
# Skip large videos - they shouldn't be cached permanently
if message.video and message.video.file_size > 100 * 1024 * 1024:
return
if message.video and message.video.file_size > 100 * 1024 * 1024: return
if message.photo: file_data['file_unique_id'] = message.photo.file_unique_id
elif message.video: file_data['file_unique_id'] = message.video.file_unique_id
rss_generator.py
+5 -13
View File
@@ -4,7 +4,6 @@ from typing import Optional
from feedgen.feed import FeedGenerator
from post_parser import PostParser
from config import get_settings
from bs4 import BeautifulSoup
Config = get_settings()
@@ -69,8 +68,7 @@ async def render_messages_groups(messages_groups, post_parser, exclude_flags: st
for group in messages_groups:
try:
if len(group) == 1:
# Single message - simple case
if len(group) == 1: # Single message - simple case
message_data = post_parser.process_message(group[0])
html_parts = [
f'<div class="message-header">{message_data["html"]["header"]}</div>',
@@ -87,12 +85,9 @@ async def render_messages_groups(messages_groups, post_parser, exclude_flags: st
'author': message_data['author'],
'flags': message_data['flags']
})
else:
# Multiple messages in group - need to merge
else: # Multiple messages in group - need to merge
processed_messages = [post_parser.process_message(msg) for msg in group]
# Find main message (one with text)
main_message = next(
main_message = next( # Find main message (one with text)
(msg for msg in processed_messages if msg['text']),
processed_messages[0] # fallback to first if none has text
)
@@ -247,11 +242,8 @@ async def generate_channel_html(channel: str, post_parser: Optional[PostParser]
base_url = Config['pyrogram_bridge_url']
try:
channel_id = channel
if isinstance(channel, str) and channel.startswith('-100'):
channel_id = int(channel)
channel_info = await post_parser.client.get_chat(channel_id)
channel = post_parser.channel_name_prepare(channel)
channel_info = await post_parser.client.get_chat(channel)
channel_username = post_parser.get_channel_username(channel_info)
if not channel_username:
return create_error_feed(channel, base_url)