gcp-hockey-results/motm_app/club_scraper.py

238 lines
9.1 KiB
Python

# encoding=utf-8
"""
Club scraper for Hong Kong Hockey Association website
Fetches men's hockey clubs from https://hockey.org.hk
"""
import requests
from bs4 import BeautifulSoup
import re
class ClubScraper:
"""Scrapes club data from Hong Kong Hockey Association website"""
CLUBS_URL = "https://hockey.org.hk/Content.asp?Uid=27"
# Common club abbreviations and their full names
CLUB_ABBREVIATIONS = {
'Pak': 'Pakistan Association of HK Ltd.',
'KCC': 'Kowloon Cricket Club',
'HKFC': 'Hong Kong Football Club',
'USRC': 'United Services Recreation Club',
'Valley': 'Valley Fort Sports Club',
'SSSC': 'South China Sports Club',
'Dragons': 'Dragons Hockey Club',
'Kai Tak': 'Kai Tak Sports Club',
'RHOBA': 'Royal Hong Kong Regiment Officers and Businessmen Association',
'Elite': 'Elite Hockey Club',
'Aquila': 'Aquila Hockey Club',
'HKJ': 'Hong Kong Jockey Club',
'Sirius': 'Sirius Hockey Club',
'Shaheen': 'Shaheen Hockey Club',
'Diocesan': 'Diocesan Boys School',
'Rhino': 'Rhino Hockey Club',
'Khalsa': 'Khalsa Hockey Club',
'HKCC': 'Hong Kong Cricket Club',
'Police': 'Hong Kong Police Force',
'Recreio': 'Recreio Hockey Club',
'CSD': 'Correctional Services Department',
'Dutch': 'Dutch Hockey Club',
'HKUHC': 'Hong Kong University Hockey Club',
'Kaitiaki': 'Kaitiaki Hockey Club',
'Antlers': 'Antlers Hockey Club',
'Marcellin': 'Marcellin Hockey Club',
'Skyers': 'Skyers Hockey Club',
'JR': 'JR Hockey Club',
'IUHK': 'International University of Hong Kong',
'144U': '144 United Hockey Club',
'HKU': 'Hong Kong University',
'UBSC': 'United Brother Sports Club',
'Nanki': 'Nanki Sports Club',
'Gojra': 'Gojra Hockey Club',
'KNS': 'KNS Hockey Club',
'Hockey Clube de Macau': 'Hockey Clube de Macau'
}
def __init__(self):
self.session = requests.Session()
self.session.headers.update({
'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'
})
def fetch_clubs(self):
"""Fetch and parse clubs from the website"""
try:
response = self.session.get(self.CLUBS_URL, timeout=10)
response.raise_for_status()
return self._parse_clubs(response.text)
except requests.RequestException as e:
print(f"Error fetching clubs: {e}")
return []
def _parse_clubs(self, html_content):
"""Parse HTML content and extract club information"""
soup = BeautifulSoup(html_content, 'lxml')
clubs = []
# Look for tables or structured data containing club information
tables = soup.find_all('table')
for table in tables:
rows = table.find_all('tr')
for row in rows:
cells = row.find_all(['td', 'th'])
if len(cells) >= 2:
# Extract club name from first cell
club_name = cells[0].get_text(strip=True)
# Skip header rows and empty cells
if not club_name or club_name.lower() in ['club', 'name', 'abbreviation', 'team', 'clubs']:
continue
# Skip if it's clearly a header row
if club_name == 'Clubs' and abbreviation == 'Abbreviated Title':
continue
# Extract abbreviation if available
abbreviation = None
if len(cells) > 1:
abbreviation = cells[1].get_text(strip=True)
# Extract teams if available
teams = []
if len(cells) > 2:
teams_text = cells[2].get_text(strip=True)
# Parse teams (e.g., "A, B" or "A B")
if teams_text:
teams = [team.strip() for team in re.split(r'[,;]', teams_text) if team.strip()]
# Extract convenor if available
convenor = None
if len(cells) > 3:
convenor = cells[3].get_text(strip=True)
# Extract email if available
email = None
if len(cells) > 4:
email = cells[4].get_text(strip=True)
club_data = {
'name': club_name,
'abbreviation': abbreviation,
'teams': teams,
'convenor': convenor,
'email': email
}
clubs.append(club_data)
# If no structured data found, try to extract from text content
if not clubs:
clubs = self._extract_clubs_from_text(html_content)
return clubs
def _extract_clubs_from_text(self, html_content):
"""Extract club names from text content if no structured data found"""
soup = BeautifulSoup(html_content, 'lxml')
clubs = []
# Look for common patterns in text
text_content = soup.get_text()
# Extract known club names from the text
for abbreviation, full_name in self.CLUB_ABBREVIATIONS.items():
if abbreviation in text_content or full_name in text_content:
clubs.append({
'name': full_name,
'abbreviation': abbreviation,
'teams': [],
'convenor': None,
'email': None
})
return clubs
def get_clubs_with_abbreviations(self):
"""Get clubs with proper abbreviation handling"""
clubs = self.fetch_clubs()
# Process clubs to handle abbreviations
processed_clubs = []
for club in clubs:
name = club['name']
abbreviation = club.get('abbreviation', '')
# If we have an abbreviation, check if it's in our mapping
if abbreviation and abbreviation in self.CLUB_ABBREVIATIONS:
full_name = self.CLUB_ABBREVIATIONS[abbreviation]
processed_club = club.copy()
processed_club['name'] = full_name
processed_club['abbreviation'] = abbreviation
processed_clubs.append(processed_club)
elif name in self.CLUB_ABBREVIATIONS.values():
# If the name is already a full name, find its abbreviation
for abbr, full in self.CLUB_ABBREVIATIONS.items():
if full == name:
processed_club = club.copy()
processed_club['abbreviation'] = abbr
processed_clubs.append(processed_club)
break
else:
# Keep as-is if no mapping found
processed_clubs.append(club)
return processed_clubs
def get_club_logo_url(self, club_name):
"""Generate a logo URL for a club (placeholder implementation)"""
# This could be enhanced to fetch actual logos from the website
# For now, return a placeholder
club_slug = club_name.lower().replace(' ', '_').replace('.', '').replace(',', '')
return f"/static/images/clubs/{club_slug}_logo.png"
def get_hk_hockey_clubs():
"""Convenience function to get Hong Kong hockey clubs"""
scraper = ClubScraper()
return scraper.get_clubs_with_abbreviations()
def expand_club_abbreviation(abbreviation):
"""Expand a club abbreviation to its full name"""
return ClubScraper.CLUB_ABBREVIATIONS.get(abbreviation, abbreviation)
if __name__ == "__main__":
# Test the scraper
print("Testing Hong Kong Hockey Club Scraper...")
print("=" * 60)
scraper = ClubScraper()
print("\nFetching clubs from Hockey Hong Kong website...")
clubs = scraper.get_clubs_with_abbreviations()
if clubs:
print(f"\nFound {len(clubs)} clubs:")
for i, club in enumerate(clubs, 1):
print(f"\n{i}. {club['name']}")
if club.get('abbreviation'):
print(f" Abbreviation: {club['abbreviation']}")
if club.get('teams'):
print(f" Teams: {', '.join(club['teams'])}")
if club.get('convenor'):
print(f" Convenor: {club['convenor']}")
if club.get('email'):
print(f" Email: {club['email']}")
else:
print("\nNo clubs found. This might be due to website structure changes.")
print("Using fallback club list...")
# Fallback to known clubs
for abbreviation, full_name in scraper.CLUB_ABBREVIATIONS.items():
print(f"- {full_name} ({abbreviation})")
print("\n" + "=" * 60)