elmeg-demo/backend/populate_links.py
fullsizemalt eb83a3b65f
Some checks are pending
Deploy Elmeg / deploy (push) Waiting to run
feat(backend): Add populate_links script
2025-12-21 01:35:55 -08:00

163 lines
5 KiB
Python

import requests
from bs4 import BeautifulSoup
from sqlmodel import Session, select
from database import engine
from models import Show
import time
import re
# El Goose API
API_BASE = "https://elgoose.net/api/v2"
SITE_BASE = "https://elgoose.net"
def get_shows_from_api():
"""Fetch all shows with their permalinks from the API"""
print("Fetching all shows from API...")
url = f"{API_BASE}/shows.json"
params = {"artist": 1, "order_by": "showdate", "direction": "DESC"} # Get all, newest first
all_shows = []
page = 1
while True:
params['page'] = page
print(f" Fetching page {page}...", end="", flush=True)
try:
resp = requests.get(url, params=params)
resp.raise_for_status()
data = resp.json()
if not data or 'data' not in data:
print(" Done.")
break
chunk = data['data']
if not chunk:
print(" Done.")
break
all_shows.extend(chunk)
print(f" Got {len(chunk)} shows.")
page += 1
if page > 50: # Safety
break
except Exception as e:
print(f" Error: {e}")
break
return all_shows
def scrape_links(permalink):
"""Scrape Bandcamp and Nugs links from an El Goose show page"""
if not permalink:
return None, None
url = f"{SITE_BASE}/setlists/{permalink}"
# Sometimes it might be at root? Try setlists/ first as per observation.
try:
# print(f" Scraping {url}...")
resp = requests.get(url, timeout=10)
if resp.status_code == 404:
# Try root
url = f"{SITE_BASE}/{permalink}"
resp = requests.get(url, timeout=10)
if resp.status_code != 200:
print(f" ❌ Failed to fetch {url}: {resp.status_code}")
return None, None
soup = BeautifulSoup(resp.text, 'html.parser')
bandcamp = None
nugs = None
# Look for links.
# Usually they are in some container or just raw <a> tags
# Pattern matching for hrefs
for a in soup.find_all('a', href=True):
href = a['href']
# Bandcamp
if 'bandcamp.com' in href:
if 'goosetheband.bandcamp.com' in href or 'bandcamp.com/album' in href:
bandcamp = href
# Nugs
if 'nugs.net' in href:
if '/goose-' in href or 'recording' in href:
nugs = href
return bandcamp, nugs
except Exception as e:
print(f" ⚠️ Scraping error: {e}")
return None, None
def main():
print("🔗 Starting Link Population Script...")
# 1. Fetch API data to get permalinks (since we didn't store them)
api_shows = get_shows_from_api()
print(f"✓ Found {len(api_shows)} shows in API.")
# Create lookup map: Date -> Permalink
# Note: API date is "YYYY-MM-DD"
date_to_permalink = {s['showdate']: s['permalink'] for s in api_shows}
with Session(engine) as session:
# 2. Get our DB shows
db_shows = session.exec(select(Show)).all()
print(f"✓ Found {len(db_shows)} shows in DB to check.")
updates = 0
for show in db_shows:
s_date = show.date.strftime("%Y-%m-%d")
permalink = date_to_permalink.get(s_date)
if not permalink:
# print(f" ⚠️ No permalink found for {s_date}")
continue
# Skip if we already have both links (optional, but good for speed)
if show.bandcamp_link and show.nugs_link:
continue
print(f"Processing {s_date}...", end="", flush=True)
bc_link, nugs_link = scrape_links(permalink)
updated = False
if bc_link and bc_link != show.bandcamp_link:
show.bandcamp_link = bc_link
updated = True
print(" [BC]", end="")
if nugs_link and nugs_link != show.nugs_link:
show.nugs_link = nugs_link
updated = True
print(" [Nugs]", end="")
if updated:
session.add(show)
updates += 1
try:
session.commit() # Commit frequently to save progress
session.refresh(show)
print("")
except Exception as e:
print(f" ❌ Save error: {e}")
else:
print(" (No new links)")
# Be nice to the server
if updated:
time.sleep(1) # Sleep only if we did work
else:
time.sleep(0.1)
print(f"\n🎉 Done! Updated {updates} shows.")
if __name__ == "__main__":
main()