Spaces:
Running
Running
| import logging | |
| import re | |
| from typing import Dict, Any, Optional | |
| from bs4 import BeautifulSoup | |
| from datetime import datetime, date | |
| from .horoscope_scraper import HoroscopeScraper | |
| logger = logging.getLogger(__name__) | |
| class AstrologyComScraper(HoroscopeScraper): | |
| """Scraper for Astrology.com horoscopes""" | |
| def __init__(self, timeout: int = 30): | |
| super().__init__(timeout) | |
| self.source_name = "Astrology.com" | |
| self.base_url = "https://www.astrology.com/horoscope/daily" | |
| def _format_url(self, base_url: str, sign: str, date_str: Optional[str] = None) -> str: | |
| """Format URL for astrology.com""" | |
| # For astrology.com, the format is typically: | |
| # https://www.astrology.com/horoscope/daily/[sign].html | |
| # or for specific dates: | |
| # https://www.astrology.com/horoscope/daily/[date]/[sign].html | |
| if date_str: | |
| try: | |
| # Convert YYYY-MM-DD to the format needed (YYYY-MM-DD) | |
| formatted_date = date_str | |
| return f"{base_url}/{formatted_date}/{sign.lower()}.html" | |
| except Exception as e: | |
| logger.error(f"Error formatting date: {str(e)}") | |
| # Default to current date if no date provided | |
| return f"{base_url}/{sign.lower()}.html" | |
| def _extract_prediction(self, soup: BeautifulSoup, text_content: str) -> str: | |
| """Extract horoscope prediction from astrology.com""" | |
| # Astrology.com typically has the horoscope in a div with class containing 'daily-horoscope' | |
| prediction_div = soup.select('div[class*="daily-horoscope"] p, .main-horoscope p') | |
| if prediction_div: | |
| # Join all paragraphs in the prediction div | |
| prediction = ' '.join([p.get_text().strip() for p in prediction_div]) | |
| return prediction | |
| # Fallback to generic extraction | |
| return super()._extract_prediction(soup, text_content) | |
| def _extract_date(self, soup: BeautifulSoup, url: str) -> str: | |
| """Extract horoscope date from astrology.com""" | |
| # Try to get date from URL first | |
| date_match = re.search(r'(\d{4}-\d{2}-\d{2})', url) | |
| if date_match: | |
| return date_match.group(1) | |
| # Look for date in typical location | |
| date_div = soup.select('.date-selector h2, .horoscope-date') | |
| if date_div: | |
| date_text = date_div[0].get_text().strip() | |
| # Try to parse date (format typically like "May 13, 2025") | |
| try: | |
| parsed_date = datetime.strptime(date_text, '%B %d, %Y') | |
| return parsed_date.strftime('%Y-%m-%d') | |
| except ValueError: | |
| # Try alternative format | |
| try: | |
| # Try to match month day, year pattern | |
| match = re.search(r'(\w+)\s+(\d{1,2}),?\s+(\d{4})', date_text) | |
| if match: | |
| month, day, year = match.groups() | |
| month_dict = { | |
| 'january': 1, 'february': 2, 'march': 3, 'april': 4, | |
| 'may': 5, 'june': 6, 'july': 7, 'august': 8, | |
| 'september': 9, 'october': 10, 'november': 11, 'december': 12 | |
| } | |
| month_num = month_dict.get(month.lower(), 1) | |
| parsed_date = datetime(int(year), month_num, int(day)) | |
| return parsed_date.strftime('%Y-%m-%d') | |
| except Exception: | |
| pass | |
| # Default to today's date if no date found | |
| return date.today().isoformat() |