public
/
mirror-checker
25
1
Fork 2
Code Issues 6 Pull Requests 1 Projects Releases Wiki Activity

Fix pycharm warnings

This commit is contained in:
Raymond Li 2021-10-03 15:56:06 -04:00
parent ccc11f07df
commit 37f2eb2877
Signed by: r389li
GPG Key ID: A014EA89B62BBB1B
2 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -4,7 +4,7 @@ This mirror status checker determines whether CSC mirror is up-to-date with upst
## How To Run
A configuration file may be provided through standard input. Without a configuration file, execute `python main.py`. By default, all of the available distributions will be checked. With a configuration file, execute `python main.py < name_of_config_file.in`, for example, `python main.py < example.in`. In this case, only the distributions listed in the configuration file will be checked.
A configuration file may be provided through standard input. Without a configuration file, execute `python main.py`. By default, all the available distributions will be checked. With a configuration file, execute `python main.py < name_of_config_file.in`, for example, `python main.py < example.in`. In this case, only the distributions listed in the configuration file will be checked.
## Resources

16
main.py
View File

@ -44,18 +44,18 @@ import datefinder # another date finding library
def checker(directory_URL, file_name):
page = requests.get(directory_URL).text
indexOfFile = page.find(file_name)
file_index = page.find(file_name)
# print(page)
# remove stray numbers (file size numbers in particular) that might interfere with date finding
segment_clean = re.sub(r'\s\d+\s', ' ', page[indexOfFile:]) # removes numbers for size
segment_clean = re.sub(r'\s\d+\w*\s', ' ', page[indexOfFile:]) # removes numbers + size unit. e.x. 50kb
segment_clean = re.sub(r'\s\d+\s', ' ', page[file_index:]) # removes numbers for size
segment_clean = re.sub(r'\s\d+\w*\s', ' ', page[file_index:]) # removes numbers + size unit. e.x. 50kb
# print(segment_clean)
# implementation using dateparser.search.search_dates
# notes: some dates don't parse correctly with this tool
# print(search_dates(page[indexOfFile:], languages=['en']))
# print(search_dates(page[indexOfFile:])[0])
# print(search_dates(page[file_index:], languages=['en']))
# print(search_dates(page[file_index:])[0])
# finds the dates in the segment after the file name
# notes: a generator will be returned by the datefinder module. I'm typecasting it to a list. Please read the note of caution provided at the bottom.
@ -64,9 +64,9 @@ def checker(directory_URL, file_name):
if len(matches) > 0:
date = matches[0] # date is of type datetime.datetime
return (date.strftime("%m/%d/%Y, %H:%M:%S"))
return date.strftime("%m/%d/%Y, %H:%M:%S")
else:
return ('No dates found')
return 'No dates found'
if __name__ == "__main__":
@ -104,7 +104,7 @@ if __name__ == "__main__":
elif data[project]["out_of_sync_since"] is None:
data[project]["out_of_sync_since"] = current_time
elif current_time - data[project]["out_of_sync_since"] \
> data[project]["out_of_sync_interval"]:
> data[project]["out_of_sync_interval"]:
print(f"Failure: {project} out-of-sync")
continue
print(f"Success: {project} up-to-date")