Web scraping: Difference between revisions
Content added Content deleted
Line 982: | Line 982: | ||
I'm using the <code>Requests.jl</code> package for this solution. Note, I used a slightly different URL after finding that the one specified in the task description is deprecated (though it still works). |
I'm using the <code>Requests.jl</code> package for this solution. Note, I used a slightly different URL after finding that the one specified in the task description is deprecated (though it still works). |
||
<lang Julia>using Requests |
<lang Julia>using Requests |
||
function getusnotime() |
function getusnotime() |
||
const url = "http://tycho.usno.navy.mil/timer.pl" |
const url = "http://tycho.usno.navy.mil/timer.pl" |
||
Line 991: | Line 991: | ||
end |
end |
||
isa(s, Requests.Response) || return (s, false) |
isa(s, Requests.Response) || return (s, false) |
||
t = match(r"(?<=<BR>)(.*UTC)", readall(s)) |
t = match(r"(?<=<BR>)(.*?UTC)", readall(s)) |
||
isa(t, RegexMatch) || return ( |
isa(t, RegexMatch) || return (@sprintf("raw html:\n %s", readall(s)), false) |
||
return (t.match, true) |
return (t.match, true) |
||
end |
end |
||
(t, issuccess) = getusnotime() |
(t, issuccess) = getusnotime() |
||
if issuccess |
if issuccess |
||
println("The USNO time is ", t) |
println("The USNO time is ", t) |