jeremy/noaa-goes-visualization
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Added error file handling to puller_fits

Browse source
This commit is contained in:
Jeremy Karst 2024-05-29 13:48:59 -04:00
parent 1bd543c64d
commit e1b764cfa1
1 changed files with 10 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
puller_fits.py
View file

@ -15,7 +15,7 @@ directory_url = r"https://data.ngdc.noaa.gov/platforms/solar-space-observing-sat
stored_images_dir = r"..\Data" stored_images_dir = r"..\Data"
# directory_url = r"https://data.ngdc.noaa.gov/platforms/solar-space-observing-satellites/goes/goes16/l2/data/suvi-l2-ci094/" # directory_url = r"https://data.ngdc.noaa.gov/platforms/solar-space-observing-satellites/goes/goes16/l2/data/suvi-l2-ci094/"
# stored_images_dir = r"Z:\NOAA GOES Data\Data\goes16\l2\suvi-l2-ci094" # stored_images_dir = r"Z:\NOAA GOES Data\Data\goes16\l2\suvi-l2-ci094"
ignore_folder_names = ["l1b", "goes17", "2017", "2018", "2019", "2020", "2021", "2022"] ignore_folder_names = ["l1b", "goes17", "2017", "2018", "2019", "2020", "2021", "2022", "2023"]
file_database_path = r"..\file_database.json" file_database_path = r"..\file_database.json"
fetch_interval = 0 # 60*60 fetch_interval = 0 # 60*60
nworkers = 8 nworkers = 8
@ -139,9 +139,14 @@ if __name__ == "__main__":
if (not (l in file_info_cache)) or t > file_info_cache[l]: if (not (l in file_info_cache)) or t > file_info_cache[l]:
if filepath.endswith(".fits"): if filepath.endswith(".fits"):
filepath2 = filepath.split(".fits")[0] + "_f.fits" # also look for the filtered version of the file filepath2 = filepath.split(".fits")[0] + "_f.fits" # also look for the filtered version of the file
if os.path.exists(filepath2): # If the unfiltered filename exists, that case will be handled in the alternative code path in if os.path.exists(filepath): filepath3 = filepath.split(".fits")[0] + "_e.fits" # also look for the error version of the file
if os.path.exists(filepath2) or os.path.exists(filepath3): # If the unfiltered filename exists, that case will be handled in the alternative code path in if os.path.exists(filepath):
if l in file_info_cache: # If we have record of this file, it must be out of date, delete it and download the new version. if l in file_info_cache: # If we have record of this file, it must be out of date, delete it and download the new version.
try:
os.remove(filepath2) os.remove(filepath2)
os.remove(filepath3)
except:
pass
else: # If we have no record of this file, update the file info cache and don't redownload else: # If we have no record of this file, update the file info cache and don't redownload
file_info_cache[l] = t file_info_cache[l] = t
already_had_image_count += 1 already_had_image_count += 1
@ -161,7 +166,8 @@ if __name__ == "__main__":
already_had_image_count += 1 already_had_image_count += 1
elif filepath.endswith(".fits"): elif filepath.endswith(".fits"):
filepath2 = filepath.split(".fits")[0] + "_f.fits" # also look for the filtered version of the file filepath2 = filepath.split(".fits")[0] + "_f.fits" # also look for the filtered version of the file
if os.path.exists(filepath2): filepath3 = filepath.split(".fits")[0] + "_e.fits" # also look for the error version of the file
if os.path.exists(filepath2) or os.path.exists(filepath3):
already_had_image_count += 1 already_had_image_count += 1
else: # We could not find the file on disk, queue for redownload else: # We could not find the file on disk, queue for redownload
work_queue.put((l, filepath, t)) work_queue.put((l, filepath, t))