grep -r "https://" * > test.txt
cat test.txt | sed -e 's/.*https//' | sed "s/^/http/g"  > test.txt
cat test2.txt | sed 's/>//g' | sed 's/"//g' | sed 's/)//g' | sed 's/;//g' | sed 's/]//g' | cut -d' ' -f 1 > input.txt 

$ python3 check_url.py

#Output result
#Can access → OK
#Inaccessible → Not Found
#* However, the grep result may not be as intended, so check it.

NotFound:http://www.kernel.org/pub/linux/kernel/v5.x/linux-${PV}.tar.xz
OK:http://facebook.github.io/watchman/
...

#-*- using:utf-8 -*-
import urllib.request, urllib.error

with open('out.txt', 'w') as txt:
    txt.write("chdck result\n")

def checkURL(url):
    try:
        f = urllib.request.urlopen(url)
        f.close()
        return True
    except:
        return False

if __name__ == '__main__':

    with open("./input.txt") as f:
        for url in f:
            # print(url, end='')
            ret = checkURL(url)
            if ret == True:
                result = "OK:"
            else:
                result = "NotFound:"

            ret_text = result + url
            #ret_text = ret_text.replace('\n', '')
            print(ret_text)
            if ret != True:
                with open('out.txt', 'a') as txt:
                    txt.write(ret_text)

cat out.txt

Recommended Posts