diff --git a/distros.json b/distros.json index 0904010..e184064 100644 --- a/distros.json +++ b/distros.json @@ -1,5 +1,10 @@ [ ["OpenBSD", "https://mirror.csclub.uwaterloo.ca/OpenBSD/", "https://ftp.openbsd.org/pub/OpenBSD/", "timestamp"], ["kernel", "http://mirror.csclub.uwaterloo.ca/kernel.org/linux/kernel/next/", "https://mirrors.edge.kernel.org/pub/linux/kernel/next/", "sha256sums.asc"], - ["debian", "http://mirror.csclub.uwaterloo.ca/debian/project/trace/", "https://ftp-master.debian.org/debian/project/trace/", "master"] + ["debian", "http://mirror.csclub.uwaterloo.ca/debian/project/trace/", "https://ftp-master.debian.org/debian/project/trace/", "master"], + ["GNU", "http://mirror.csclub.uwaterloo.ca/gnu/", "https://mirrors.kernel.org/gnu/", "mirror-updated-timestamp.txt"], + ["almalinux", "https://mirror.csclub.uwaterloo.ca/almalinux/", "https://repo.almalinux.org/almalinux/", "TIME"], + ["alpine", "https://mirror.csclub.uwaterloo.ca/alpine/", "https://dl-cdn.alpinelinux.org/alpine/", "last-updated"], + ["Apache", "https://mirror.csclub.uwaterloo.ca/apache/zzz/", "https://downloads.apache.org/zzz/", "time.txt"], + ["CentOS", "https://mirror.csclub.uwaterloo.ca/centos/", "https://vault.centos.org/", "timestamp.txt"] ] \ No newline at end of file diff --git a/main.py b/main.py index 54699db..d3602df 100644 --- a/main.py +++ b/main.py @@ -19,6 +19,7 @@ import json # import json to read distro info stored in json file import datefinder # another date finding library +# checker: gets the timestamp of the file inside the directory at the specified URL and returns it as a string def checker(directory_URL, file_name): page = requests.get(directory_URL).text indexOfFile = page.find(file_name) @@ -52,10 +53,20 @@ if __name__ == "__main__": except requests.exceptions.RequestException as err: print(f"Error: {distro.name()}\n{err}")""" + # the implementation to check timestamps in distro mirror directory: distros = json.load(open('distros.json',)) - print(distros) - + # print(distros) + for distro in distros: print(distro[0] + ":") print("CSC mirror: " + checker(distro[1], distro[3])) - print("Official distro: " + checker(distro[2], distro[3])) \ No newline at end of file + print("Official distro: " + checker(distro[2], distro[3])) + # for eclipse, i couldn't find a directory from the official website, so i decided to temporarily cheat a little bit and peek at another person's mirror for explipse + # i just realized that my method doesn't just work for scraping html directories but everything returned by a URL (websites, files storing a time) + # i think i'll put checking arch, ceph, ecplipse on hold because it's more proper to check them using as.Date(17383, origin="1970-01-01") where the date is stored in + # a file as a number, but this would require another function and me looping through different functions. i think i'll do this later + # corresponding jsons: ["Eclipse", "https://mirror.csclub.uwaterloo.ca/eclipse/", "http://eclipse.mirror.rafal.ca/", "TIME"], + # ["Ceph", "https://mirror.csclub.uwaterloo.ca/ceph/", "https://download.ceph.com/", "timestamp"], + # i don't know what to do with damnsmalllinux, it seems like an abandoned project. useful link: http://distro.ibiblio.org/damnsmall/ + # the other function is probably probing mirror status sites like this: http://mirrors.cpan.org/ + # maybe i can make a column in json that specifies the method for checking the particular mirror and that identifier will find a specific function to check the update \ No newline at end of file