File size: 6,520 Bytes
d09f6aa |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 |
# Module for utility functions (logging, caching, web fetching)
import logging
from logging.handlers import RotatingFileHandler
import sys
import hashlib
import requests
from bs4 import BeautifulSoup
from functools import lru_cache
from typing import Any, Optional
# --- Logging Setup ---
_logger_instance = None
def setup_logging():
"""Configure logging to both file and console"""
global _logger_instance
if _logger_instance:
return _logger_instance
logger = logging.getLogger("ankigen")
logger.setLevel(logging.DEBUG) # Keep debug level for the root logger
# Prevent duplicate handlers if called multiple times (though get_logger should prevent this)
if logger.hasHandlers():
logger.handlers.clear()
detailed_formatter = logging.Formatter(
"%(asctime)s - %(name)s - %(levelname)s - %(module)s:%(lineno)d - %(message)s"
)
simple_formatter = logging.Formatter("%(levelname)s: %(message)s")
file_handler = RotatingFileHandler(
"ankigen.log", maxBytes=1024 * 1024, backupCount=5
)
file_handler.setLevel(logging.DEBUG) # File handler logs everything from DEBUG up
file_handler.setFormatter(detailed_formatter)
console_handler = logging.StreamHandler(sys.stdout)
console_handler.setLevel(logging.INFO) # Console handler logs INFO and above
console_handler.setFormatter(simple_formatter)
logger.addHandler(file_handler)
logger.addHandler(console_handler)
_logger_instance = logger
return logger
def get_logger():
"""Returns the initialized logger instance."""
if _logger_instance is None:
return setup_logging()
return _logger_instance
# Initialize logger when module is loaded
logger = get_logger()
# --- Caching ---
class ResponseCache:
"""A simple cache for API responses using LRU for get operations."""
def __init__(self, maxsize=128):
# This internal method will be decorated by lru_cache
self._internal_get_from_dict = self._get_from_dict_actual
self._lru_cached_get = lru_cache(maxsize=maxsize)(self._internal_get_from_dict)
self._dict_cache = {} # Main store for set operations
def _get_from_dict_actual(self, cache_key: str):
"""Actual dictionary lookup, intended to be wrapped by lru_cache."""
logger.debug(f"Cache DICT GET: key={cache_key}")
return self._dict_cache.get(cache_key)
def get(self, prompt: str, model: str) -> Optional[Any]:
"""Retrieves an item from the cache. Uses LRU for this get path."""
cache_key = self._create_key(prompt, model)
# Use the LRU cached getter which looks up in _dict_cache
return self._lru_cached_get(cache_key)
def set(self, prompt: str, model: str, response: Any):
"""Sets an item in the cache."""
cache_key = self._create_key(prompt, model)
logger.debug(f"Cache SET: key={cache_key}, type={type(response)}")
self._dict_cache[cache_key] = response
# To make the LRU cache aware of this new item for subsequent gets:
# We can call the LRU getter so it caches it, or clear specific lru entry if updating.
# For simplicity, if a new item is set, a subsequent get will fetch and cache it via LRU.
# Or, we can "prime" the lru_cache, but that's more complex.
# Current approach: set updates _dict_cache. Next get for this key will use _lru_cached_get,
# which will fetch from _dict_cache and then be LRU-managed.
def _create_key(self, prompt: str, model: str) -> str:
"""Creates a unique MD5 hash key for caching."""
return hashlib.md5(f"{model}:{prompt}".encode("utf-8")).hexdigest()
# --- Web Content Fetching ---
def fetch_webpage_text(url: str) -> str:
"""Fetches and extracts main text content from a URL."""
logger_util = get_logger() # Use the logger from this module
try:
logger_util.info(f"Fetching content from URL: {url}")
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
}
response = requests.get(url, headers=headers, timeout=15)
response.raise_for_status()
logger_util.debug(f"Parsing HTML content for {url}")
try:
soup = BeautifulSoup(response.text, "lxml")
except ImportError: # Keep existing fallback
logger_util.warning("lxml not found, using html.parser instead.")
soup = BeautifulSoup(response.text, "html.parser")
except Exception as e: # Catch other BeautifulSoup init errors
logger_util.error(
f"BeautifulSoup initialization failed for {url}: {e}", exc_info=True
)
raise RuntimeError(f"Failed to parse HTML content for {url}.")
for script_or_style in soup(["script", "style"]):
script_or_style.extract()
main_content = soup.find("main")
if not main_content:
main_content = soup.find("article")
if main_content:
text = main_content.get_text()
logger_util.debug(f"Extracted text from <{main_content.name}> tag.")
else:
body = soup.find("body")
if body:
text = body.get_text()
logger_util.debug("Extracted text from <body> tag (fallback).")
else:
text = ""
logger_util.warning(f"Could not find <body> tag in {url}")
# Simpler text cleaning: join stripped lines
lines = (line.strip() for line in text.splitlines())
cleaned_text = "\n".join(line for line in lines if line)
if not cleaned_text:
logger_util.warning(f"Could not extract meaningful text from {url}")
return ""
logger_util.info(
f"Successfully extracted text from {url} (Length: {len(cleaned_text)} chars)"
)
return cleaned_text
except requests.exceptions.RequestException as e:
logger_util.error(f"Network error fetching URL {url}: {e}", exc_info=True)
raise ConnectionError(f"Could not fetch URL: {e}")
except Exception as e:
logger_util.error(f"Error processing URL {url}: {e}", exc_info=True)
if isinstance(e, (ValueError, ConnectionError, RuntimeError)):
raise e
else:
raise RuntimeError(
f"An unexpected error occurred while processing the URL: {e}"
)
|