Hi Domingo,
> I used this two lua scripts to get/generate then:
>
> ====
>
> --local html = io.open("roseta-code.html"):read("*a")
> local base_url = "http://rosettacode.org";
> local html = io.popen("curl " .. base_url ..
> "/wiki/Category:PicoLisp"):read("*a")
>
> html = html:gsub("<h2>Pages in category
> \"PicoLisp\"</h2>.-</div></div></div><div
> class=\"printfooter\">",
> function(m)
> return m:gsub("(/wiki[^\"]+)(\" title=)" ,
> function(link, title)
> return base_url .. link .. "#PicoLisp" .. title
> end)
> end)
>
> print(html)
>
> ====
>
> ====
>
> local html = io.open("roseta-code.html"):read("*a")
> --local base_url = "http://rosettacode.org";
> --local html = io.popen("curl " .. base_url ..
> "/wiki/Category:PicoLisp"):read("*a")
>
> local code_links = html:match("<h2>Pages in
> category
> \"PicoLisp\"</h2>.-</div></div></div><div
> class=\"printfooter\">")
>
> for link, title in code_links:gmatch("href=\"([^\"]+).->([^<]+)") do
> print( string.format("-{^{%s %s}}", link, title))
> end
>
> ====
Thanks a lot!
For completeness, here is the same (if I understand your scripts correctly - I
have no idea of lua) in PicoLisp:
(in '(curl "-s" "http://rosettacode.org/wiki/Category:PicoLisp";)
(from "Pages in category \"PicoLisp\"")
(while (== "<a href=\"" (from "<a href=\"" "printfooter"))
(prin "-{\^{http://rosettacode.org"; (till "\"") "#PicoLisp ")
(from "title=\"")
(prinl (till "\"") "}}") ) )
As you see, no need for regexps, and no need for the overhead slurping the whole
stuff into memory. Just simple stream processing.
☺/ A!ex
--
UNSUBSCRIBE: mailto:[email protected]?subject=Unsubscribe
