egghelp/eggheads community

Scraping a little bit of text

2009-02-23T19:38:06-04:00

Code:

package require httpsetudef flag imagesset vTimeout 10set vUrl http://imghostr.net/bind PUB - !images pImagesproc pImages {nick uhost hand channel txt} {    global vTimeout vUrl    if {[channel get $channel images]} {        set agent [::http::config -useragent "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)"]        if {![catch {set http [::http::geturl $vUrl -timeout [expr {$vTimeout * 1000}]]}]} {            switch -- [::http::status $http] {                "timeout" {putserv "PRIVMSG $channel :attempt to scrape $vUrl timed out after $vTimeout seconds"}                "error" {putserv "PRIVMSG $channel :attempt to scrape $vUrl returned error [::http::error $http]"}                "ok" {                    switch -- [::http::ncode $http] {                        200 {                            regexp -- {Currently Hosting:\(.+?)Images} [::http::data $http] -> images                            if {([info exists images]) && ([regexp -- {[0-9]+} $images])} {                                putserv "PRIVMSG $channel :$vUrl is currently hosting [string trim $images] images"                            } else {putserv "PRIVMSG $channel :the number of images hosted by $vUrl could not be found"}                        }                        default {putserv "PRIVMSG $channel :attempt to scrape $vUrl returned ncode [::http::ncode $http]"}                    }                }            }            ::http::cleanup $http        } else {putserv "PRIVMSG $channel :attempted connection to $vUrl failed"}    }    return 0}

Statistics: Posted by arfer — Mon Feb 23, 2009 7:38 pm

Scraping a little bit of text

2009-02-23T18:20:14-04:00

try:

Code:

if {![regexp -- {Currently Hosting:(.+)
} $html - s_login]} {set s_login Unknown}

Statistics: Posted by Papillon — Mon Feb 23, 2009 6:20 pm

Scraping a little bit of text

2009-02-23T16:29:27-04:00

Code:

package require httpsetudef flag serverinfovariable serverquery "http://www.imghostr.net/"variable servertimeout 10bind pub - "!imghostr" checkserverproc checkserver {nick host hand chan rest} {       # chanset catch, use .chanset #yourchan +serverinfo to enable       if {[lsearch -exact [channel info $chan] +serverinfo] == -1} { return 0 }       # browser agent       set http [::http::config -useragent "Mozilla"]       # get url with error control       catch {set http [::http::geturl "$::serverquery" -timeout [expr 1000 * $::servertimeout]]} error       # case 1, no socket       if {[string match -nocase "*couldn't open socket*" $error]} {              putserv "privmsg $chan : Cannot open socket. Try again later."              ::http::cleanup $http              return 0       }       # case 2, timeout       if { [::http::status $http] == "timeout" } {              putserv "privmsg $chan : Website has timed out. Try again later."              ::http::cleanup $http              return 0       }       # case 3, success, get html       set html [::http::data $http]       # scrape the page       if {![regexp -- {Currently Hosting:.*?
} $html - s_login]} {set s_login Unknown}       # reformat scraped information and message to irc.       puthelp "privmsg $chan :images : $s_login"       return 1}

So i done some searching and found what i think should do the job, iv added in the HTML sarounding what im wanting to show.

http://imghostr.net <-- i want the current image count: Currently Hosting ### Images.

Can anyone see where im going wrong?

Statistics: Posted by paulOr — Mon Feb 23, 2009 4:29 pm