osm-commerces/wiki_compare/fetch_proposals.py
2025-08-22 17:58:04 +02:00

183 lines
No EOL
6.4 KiB
Python
Executable file

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup
import json
import logging
import argparse
import os
from datetime import datetime, timedelta
# Configure logging
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(levelname)s - %(message)s'
)
logger = logging.getLogger(__name__)
# URLs for OSM Wiki proposals
VOTING_PROPOSALS_URL = "https://wiki.openstreetmap.org/wiki/Category:Proposals_with_%22Voting%22_status"
RECENT_CHANGES_URL = "https://wiki.openstreetmap.org/w/index.php?title=Special:RecentChanges&namespace=102&limit=50" # Namespace 102 is for Proposal pages
# Output file
OUTPUT_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'proposals.json')
# Cache timeout (in hours)
CACHE_TIMEOUT = 1
def should_update_cache():
"""
Check if the cache file exists and if it's older than the cache timeout
"""
if not os.path.exists(OUTPUT_FILE):
logger.info("Cache file doesn't exist, creating it")
return True
# Check file modification time
file_mtime = datetime.fromtimestamp(os.path.getmtime(OUTPUT_FILE))
now = datetime.now()
# If file is older than cache timeout, update it
if now - file_mtime > timedelta(hours=CACHE_TIMEOUT):
logger.info(f"Cache is older than {CACHE_TIMEOUT} hour(s), updating")
return True
logger.info(f"Cache is still fresh (less than {CACHE_TIMEOUT} hour(s) old)")
return False
def fetch_voting_proposals():
"""
Fetch proposals with "Voting" status from the OSM Wiki
"""
logger.info(f"Fetching voting proposals from {VOTING_PROPOSALS_URL}")
try:
response = requests.get(VOTING_PROPOSALS_URL)
response.raise_for_status()
soup = BeautifulSoup(response.text, 'html.parser')
proposals = []
# Find all links in the mw-pages section
links = soup.select('#mw-pages a')
for link in links:
# Skip category links and other non-proposal links
if 'Category:' in link.get('href', '') or 'Special:' in link.get('href', ''):
continue
proposal_title = link.text.strip()
proposal_url = 'https://wiki.openstreetmap.org' + link.get('href', '')
proposals.append({
'title': proposal_title,
'url': proposal_url,
'status': 'Voting',
'type': 'voting'
})
logger.info(f"Found {len(proposals)} voting proposals")
return proposals
except requests.exceptions.RequestException as e:
logger.error(f"Error fetching voting proposals: {e}")
return []
def fetch_recent_proposals():
"""
Fetch recently modified proposals from the OSM Wiki
"""
logger.info(f"Fetching recent changes from {RECENT_CHANGES_URL}")
try:
response = requests.get(RECENT_CHANGES_URL)
response.raise_for_status()
soup = BeautifulSoup(response.text, 'html.parser')
proposals = []
# Find all change list lines
change_lines = soup.select('.mw-changeslist .mw-changeslist-line')
for line in change_lines:
# Get the page title
title_element = line.select_one('.mw-changeslist-title')
if not title_element:
continue
page_title = title_element.text.strip()
page_url = title_element.get('href', '')
if not page_url.startswith('http'):
page_url = f"https://wiki.openstreetmap.org{page_url}"
# Get the timestamp
timestamp_element = line.select_one('.mw-changeslist-date')
timestamp = timestamp_element.text.strip() if timestamp_element else ""
# Get the user who made the change
user_element = line.select_one('.mw-userlink')
user = user_element.text.strip() if user_element else "Unknown"
# Skip if it's not a proposal page
if not page_title.startswith('Proposal:'):
continue
proposals.append({
'title': page_title,
'url': page_url,
'last_modified': timestamp,
'modified_by': user,
'type': 'recent'
})
# Limit to the 10 most recent proposals
proposals = proposals[:10]
logger.info(f"Found {len(proposals)} recently modified proposals")
return proposals
except requests.exceptions.RequestException as e:
logger.error(f"Error fetching recent proposals: {e}")
return []
def save_proposals(voting_proposals, recent_proposals):
"""
Save the proposals to a JSON file
"""
data = {
'last_updated': datetime.now().isoformat(),
'voting_proposals': voting_proposals,
'recent_proposals': recent_proposals
}
with open(OUTPUT_FILE, 'w', encoding='utf-8') as f:
json.dump(data, f, ensure_ascii=False, indent=2)
logger.info(f"Saved {len(voting_proposals)} voting proposals and {len(recent_proposals)} recent proposals to {OUTPUT_FILE}")
return OUTPUT_FILE
def main():
parser = argparse.ArgumentParser(description='Fetch OSM Wiki proposals')
parser.add_argument('--force', action='store_true', help='Force update even if cache is fresh')
parser.add_argument('--dry-run', action='store_true', help='Print results without saving to file')
args = parser.parse_args()
# Check if we should update the cache
if args.force or should_update_cache() or args.dry_run:
voting_proposals = fetch_voting_proposals()
recent_proposals = fetch_recent_proposals()
if args.dry_run:
logger.info(f"Found {len(voting_proposals)} voting proposals:")
for proposal in voting_proposals:
logger.info(f"- {proposal['title']}")
logger.info(f"Found {len(recent_proposals)} recent proposals:")
for proposal in recent_proposals:
logger.info(f"- {proposal['title']} (modified by {proposal['modified_by']} on {proposal['last_modified']})")
else:
output_file = save_proposals(voting_proposals, recent_proposals)
logger.info(f"Results saved to {output_file}")
else:
logger.info("Using cached proposals data")
if __name__ == "__main__":
main()