feat: add Django web app, CloudKit sync, dashboard, and game_datetime_utc export
Adds the full Django application layer on top of sportstime_parser: - core: Sport, Team, Stadium, Game models with aliases and league structure - scraper: orchestration engine, adapter, job management, Celery tasks - cloudkit: CloudKit sync client, sync state tracking, sync jobs - dashboard: staff dashboard for monitoring scrapers, sync, review queue - notifications: email reports for scrape/sync results - Docker setup for deployment (Dockerfile, docker-compose, entrypoint) Game exports now use game_datetime_utc (ISO 8601 UTC) instead of venue-local date+time strings, matching the canonical format used by the iOS app. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -2,6 +2,7 @@
|
||||
|
||||
from datetime import datetime, date
|
||||
from typing import Optional
|
||||
from zoneinfo import ZoneInfo
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
from .base import BaseScraper, RawGameData, ScrapeResult
|
||||
@@ -33,7 +34,12 @@ class NFLScraper(BaseScraper):
|
||||
Sources (in priority order):
|
||||
1. ESPN API - Most reliable for NFL
|
||||
2. Pro-Football-Reference - Complete historical data
|
||||
3. CBS Sports - Backup option
|
||||
3. CBS Sports - Backup option (not implemented)
|
||||
|
||||
Source Timezones:
|
||||
- espn: UTC - ISO 8601 format with "Z" suffix
|
||||
- pro_football_reference: Eastern Time (ET) - times displayed as "8:20PM"
|
||||
- cbs: Not implemented
|
||||
"""
|
||||
|
||||
def __init__(self, season: int, **kwargs):
|
||||
@@ -56,7 +62,7 @@ class NFLScraper(BaseScraper):
|
||||
if source == "espn":
|
||||
week = kwargs.get("week", 1)
|
||||
season_type = kwargs.get("season_type", 2) # 1=preseason, 2=regular, 3=postseason
|
||||
return f"https://site.api.espn.com/apis/site/v2/sports/football/nfl/scoreboard?seasontype={season_type}&week={week}"
|
||||
return f"https://site.api.espn.com/apis/site/v2/sports/football/nfl/scoreboard?season={self.season}&seasontype={season_type}&week={week}"
|
||||
|
||||
elif source == "pro_football_reference":
|
||||
return f"https://www.pro-football-reference.com/years/{self.season}/games.htm"
|
||||
@@ -323,6 +329,25 @@ class NFLScraper(BaseScraper):
|
||||
except ValueError:
|
||||
return None
|
||||
|
||||
# Get game start time (format: "8:20PM" or "1:00PM") - times are in ET
|
||||
time_cell = row.find("td", {"data-stat": "gametime"})
|
||||
if time_cell:
|
||||
time_text = time_cell.get_text(strip=True)
|
||||
if time_text:
|
||||
try:
|
||||
# Parse time like "8:20PM" or "1:00PM"
|
||||
# Normalize: "8:20PM" -> "8:20 PM"
|
||||
time_normalized = time_text.replace("PM", " PM").replace("AM", " AM")
|
||||
game_time = datetime.strptime(time_normalized, "%I:%M %p")
|
||||
# Combine date and time with ET timezone (Pro-Football-Reference uses ET)
|
||||
game_date = game_date.replace(
|
||||
hour=game_time.hour,
|
||||
minute=game_time.minute,
|
||||
tzinfo=ZoneInfo("America/New_York"),
|
||||
)
|
||||
except ValueError:
|
||||
self._logger.debug(f"Could not parse time: {time_text}, using midnight")
|
||||
|
||||
# Get teams
|
||||
winner_cell = row.find("td", {"data-stat": "winner"})
|
||||
loser_cell = row.find("td", {"data-stat": "loser"})
|
||||
@@ -566,6 +591,7 @@ class NFLScraper(BaseScraper):
|
||||
country=info.country,
|
||||
latitude=info.latitude,
|
||||
longitude=info.longitude,
|
||||
timezone=info.timezone,
|
||||
surface="turf", # Many NFL stadiums
|
||||
roof_type="open", # Most outdoor
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user