Hi,
If anyone is interested here's is the (poorly written) python code I used to
check the download pages:
for page in downloadPages:
response = urllib.request.urlopen(page)
data = response.read()
soup = BeautifulSoup(data,'lxml')
print()
print("Checking " + page)
alllinks = soup('a')
missing = True
for link in alllinks:
if link.has_attr('href'):
href = link['href']
text = link.contents
if href.endswith('.zip') or href.endswith('.tar.gz') or
href.endswith('.tzg') or href.endswith('.msi') or href.endswith('.rpm'):
if href.startswith('http://www.apache.org/dist/') or
href.startswith('https://www.apache.org/dist/'):
print("Please change link to" + href + " to not use
http://www.apache.org/dist/ and use https://www.apache.org/dyn/closer.lua
instead")
if href.startswith('http://dist.apache.org/repos/dist/dev') or
href.startswith('https://dist.apache.org/repos/dist/dev'):
print("Please change link to " + href + " to release area
and use https://www.apache.org/dyn/closer.lua";)
if href.startswith('http://dist.apache.org/repos/dist/release')
or href.startswith('https://dist.apache.org/repos/dist/release'):
print("Please use use https://www.apache.org/dyn/closer.lua
to download releases")
if href.startswith('https://downloads.apache.org/incubator/'):
print("Please use use https://www.apache.org/dyn/closer.lua
to download releases")
if href.endswith('.sha512') or href.endswith('.asc'):
missing = False
if not href.startswith('https://www.apache.org/dist/') and not
href.startswith('https://archive.apache.org/dist'):
print("Please change link to " + href + " to go via
https://www.apache.org/dist/ or https://archive.apache.org/dist";)
if href.endswith('.sha'):
print(".sha should no longer be used")
if missing:
print("Links to signatures and hashes are missing”)
thanks,
Justin
---------------------------------------------------------------------
To unsubscribe, e-mail: general-unsubscr...@incubator.apache.org
For additional commands, e-mail: general-h...@incubator.apache.org
