Script to find official Debian mirrors that support HTTPS

find-https-debian-archives.py

#!/usr/bin/python

import urllib2
import re
import ssl
import sys

# # find generic mirrors
mirrors = urllib2.urlopen('http://www.debian.org/mirror/list')
https = []
for line in mirrors.readlines():
    m = re.match('.*<td valign="top"><a rel="nofollow" href="http(.*)">.*', line)
    if m:
        url = 'https' + m.group(1)
        print 'trying: ',
        print url,
        print '...',
        sys.stdout.flush()
        try:
            response=urllib2.urlopen(url, timeout=1)
            https.append(url)
            print 'success!'
        except urllib2.HTTPError as err:
            print 'HTTP error',err.code
        except urllib2.URLError as err:
            print 'fail!'
        except ssl.SSLError as err:
            print 'bad SSL!'
        except ssl.CertificateError as err:
            print 'bad certificate!'

# print 'HTTPS apt repos:'
#for url in https:
#    print url

# # find security mirrors
mirrors = urllib2.urlopen('http://www.debian.org/mirror/list-full')
securitys = []
for line in mirrors.readlines():
    m = re.match('.*</tt><br>Security updates over HTTP: <tt><a rel="nofollow" href="http(.*)">.*/debian-security/</a>.*', line)
    if m:
        url = 'https' + m.group(1)
        print 'trying: ',
        print url,
        print '...',
        sys.stdout.flush()
        try:
            response=urllib2.urlopen(url, timeout=1)
            securitys.append(url)
            print 'success!'
        except urllib2.URLError as err:
            print 'fail!'
        except ssl.SSLError as err:
            print 'bad SSL!'
        except ssl.CertificateError as err:
            print 'bad certificate!'

# print 'HTTPS security repos:'
# for url in securitys:
#     print url

# now find the CD image mirrors
mirrors = urllib2.urlopen('http://www.debian.org/CD/http-ftp/')
cds = []
for line in mirrors.readlines():
# <a rel="nofollow" href="http://mirror.easyspeedy.com/debian-cd/">HTTP</a></li>
    m = re.match('.*<a rel="nofollow" href="http(:.*)">HTTP</a></li>.*', line)
    if m:
        url = 'https' + m.group(1)
        print 'trying: ',
        print url,
        print '...',
        sys.stdout.flush()
        try:
            response=urllib2.urlopen(url, timeout=1)
            cds.append(url)
            print 'success!'
        except urllib2.HTTPError as err:
            print 'HTTP error',err.code
        except urllib2.URLError as err:
            print 'fail!'
        except ssl.SSLError as err:
            print 'bad SSL!'
        except ssl.CertificateError as err:
            print 'bad certificate!'

print 'HTTPS CD image repos:'
for url in cds:
    print url

# now write everything to a file
f = open('/tmp/https-debian-archives.txt', 'w')

f.write('HTTPS apt repos\n')
f.write('---------------\n')
for url in https:
    f.write(url + '\n')

f.write('\n\nHTTPS security repos\n')
f.write('---------------\n')
for url in securitys:
    f.write(url + '\n')

f.write('\n\nHTTPS CD image repos\n')
f.write('--------------------\n')
for url in cds:
    f.write(url + '\n')


f.close()

Updated the exception catching to catch certificate errors as some of the mirrors have dodgy certs

Also now catches HTTP errors (4**, 5**) rather than failing on broken repo links

Removed backports checks as they have been merged into the main repos