forerad

commit ee68047881ac7e16ca5051a7a90abbca64efd08d
parent 597774b6e3bb876bbd585a8657b87b8681d67c51
Author: Steve Gattuso <steve@stevegattuso.me>
Date:   Mon,  6 Nov 2023 11:31:26 +0100

fix missing months

Diffstat:
M
bin/hourly-volume-rollup
 | 
7
++++---
M
forerad/scrapers/historical.py
 | 
3
++-

2 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/bin/hourly-volume-rollup b/bin/hourly-volume-rollup
@@ -58,10 +58,11 @@ def main__populate(month_str):
         year, month = utils.parse_month_str(month_str)
         archives = [a for a in archives if a.date.year == year and a.date.month == month]
 
-    # Filter out completed rollups
-    archives = [a for a in archives if not is_complete(a)]
-    utils.logger.info(f'Rolling up {len(archives)} months of data')
+    if not month_str:
+        # Filter out completed rollups
+        archives = [a for a in archives if not is_complete(a)]
 
+    utils.logger.info(f'Rolling up {len(archives)} months of data')
     [derive_rollup(a) for a in archives]
 
 
diff --git a/forerad/scrapers/historical.py b/forerad/scrapers/historical.py
@@ -11,7 +11,8 @@ from botocore import UNSIGNED
 
 import forerad.utils as utils
 
-ARCHIVE_REGEX = re.compile("^([0-9]{4})([0-9]{2})-citibike-tripdata((.zip$)|(.csv.zip$))")
+# Notice the `(i)?` - they spelled Citibike wrong in one of the archives... lol
+ARCHIVE_REGEX = re.compile("^([0-9]{4})([0-9]{2})-cit(i)?bike-tripdata((.zip$)|(.csv.zip$))")
 CACHE_DIR = pathlib.Path(__file__).parent.parent.parent / pathlib.Path('.forerad-cache')
 TRIP_BUCKET = 'tripdata'
 if not CACHE_DIR.exists():