Split GWR advance ticket code into own file

agenda/__init__.py

@@ -2,7 +2,6 @@ import configparser
 import json
 import operator
 import os
-import re
 import typing
 import warnings
 from datetime import date, datetime, time, timedelta, timezone
@@ -26,7 +25,7 @@ from dateutil.relativedelta import FR, SA, relativedelta
 
 from agenda import thespacedevs
 
-from . import waste_schedule
+from . import gwr, waste_schedule
 from .types import Event
 
 warnings.simplefilter(action="ignore", category=FutureWarning)
@@ -74,43 +73,6 @@ event_type_color_map = {
 }
 
 
-def extract_weekday_date(html: str) -> date | None:
-    """Furthest date of GWR advance ticket booking."""
-    # Compile a regular expression pattern to match the relevant table row
-    pattern = re.compile(
-        r"<tr>\s*<td>Weekdays</td>\s*<td>(.*?)</td>\s*</tr>", re.DOTALL
-    )
-
-    # Search the HTML for the pattern
-    if not (match := pattern.search(html)):
-        return None
-    date_str = match.group(1)
-
-    # If the year is missing, use the current year
-    if not date_str[-1].isdigit():
-        date_str += f" {date.today().year}"
-
-    return datetime.strptime(date_str, "%A %d %B %Y").date()
-
-
-def get_gwr_advance_tickets_page_html(ttl: int = 3600) -> str:
-    """Get advance-tickets web page HTML with cache."""
-    filename = os.path.join(data_dir, "advance-tickets.html")
-    url = "https://www.gwr.com/your-tickets/choosing-your-ticket/advance-tickets"
-    mtime = os.path.getmtime(filename) if os.path.exists(filename) else 0
-    if (unixtime() - mtime) < ttl:  # use cache
-        return open(filename).read()
-    r = requests.get(url)
-    open(filename, "w").write(r.text)
-    return r.text
-
-
-def find_gwr_advance_ticket_date() -> date | None:
-    """Get GWR advance tickets date with cache."""
-    html = get_gwr_advance_tickets_page_html()
-    return extract_weekday_date(html)
-
-
 def next_uk_mothers_day(input_date: date) -> date:
     """Calculate the date of the next UK Mother's Day from the current date."""
     current_year = input_date.year
@@ -726,7 +688,7 @@ def get_data(now: datetime) -> typing.Mapping[str, str | object]:
         "fathers_day": next_uk_fathers_day(today),
         "uk_financial_year_end": uk_financial_year_end(today),
         "xmas_last_posting_dates": xmas_last_posting_dates,
-        "gwr_advance_tickets": find_gwr_advance_ticket_date(),
+        "gwr_advance_tickets": gwr.advance_ticket_date(data_dir),
         "critical_mass": critical_mass(today),
         "market": (
             windmill_hill_market_days(today)

agenda/gwr.py

@@ -0,0 +1,45 @@
+"""Check GWR for advance ticket booking date."""
+
+import os
+import re
+from datetime import date, datetime
+from time import time
+
+import requests
+
+
+def extract_weekday_date(html: str) -> date | None:
+    """Furthest date of GWR advance ticket booking."""
+    # Compile a regular expression pattern to match the relevant table row
+    pattern = re.compile(
+        r"<tr>\s*<td>Weekdays</td>\s*<td>(.*?)</td>\s*</tr>", re.DOTALL
+    )
+
+    # Search the HTML for the pattern
+    if not (match := pattern.search(html)):
+        return None
+    date_str = match.group(1)
+
+    # If the year is missing, use the current year
+    if not date_str[-1].isdigit():
+        date_str += f" {date.today().year}"
+
+    return datetime.strptime(date_str, "%A %d %B %Y").date()
+
+
+def advance_tickets_page_html(data_dir: str, ttl: int = 3600) -> str:
+    """Get advance-tickets web page HTML with cache."""
+    filename = os.path.join(data_dir, "advance-tickets.html")
+    url = "https://www.gwr.com/your-tickets/choosing-your-ticket/advance-tickets"
+    mtime = os.path.getmtime(filename) if os.path.exists(filename) else 0
+    if (time() - mtime) < ttl:  # use cache
+        return open(filename).read()
+    r = requests.get(url)
+    open(filename, "w").write(r.text)
+    return r.text
+
+
+def advance_ticket_date(data_dir: str) -> date | None:
+    """Get GWR advance tickets date with cache."""
+    html = advance_tickets_page_html(data_dir)
+    return extract_weekday_date(html)