LiveCode Forums.

Code: Select all

revBrowserNavigate tBrowserId, "http://www.ybbo.de/member/index.php"

Code: Select all

 revBrowserNavigate tBrowserId2, tRetrievedLink_1
  wait 2 seconds
revBrowserNavigate tBrowserId2, tRetrievedLink_2
  wait 2 seconds
revBrowserNavigate tBrowserId2, tRetrievedLink_3
  wait 2 seconds
revBrowserNavigate tBrowserId2, tRetrievedLink_And_So_On
  wait 2 seconds

Code: Select all

put revBrowserGet(gBrowserInstance,"htmlText") into myHtmlText

Code: Select all

put url "http://google.com" into theHTML

Code: Select all

put revBrowserGet(gBrowserInstance,"htmlText") into myHtmlText

Code: Select all

put url "http://google.com" into theHTML

Code: Select all

  put field htmlSource into theElements 
   
   split theElements by ">"
   repeat for each element thisElement in theElements
      if char 1 to 2 of thisElement = "<A" or "<a" then
      split thisElement by space
      repeat for each element thisAttribute in thisElement
         if char 1 to 4 of thisAttribute = "href" or "HREF" then
            split thisAttribute by quote
            put thisAttribute[2] & return  after theURLS
         end if
         
      end repeat
      end if
   end repeat
   
put theURLS into field "listURLS"

Code: Select all

on getMyURLs
   
   put field "tbURL" into rootURL
   
   --Remove any trailing slash
   if rootURL ends with "/"  then
      put char 1 to (the length of rootURL - 1) of rootURL into rootURL
   end if
   
   set the  itemdelimiter to return
   repeat for each item thisURL in field "listURLS"
      
      --If it's already formatted, and we've not been there, grab it.
      if thisURL begins with rootURL then
         if thisURL is not among the items of field "listMyCollectedURLS" then
            put thisURL & return after field "listMyCollectedURLS"
         end if
      end if
      
      --If it's relative, fix it, if we've not been there, grab it.
      if thisURL begins with "/"  then
         put rootURL & thisURL into newURL
         if newURL is not among the items of field "listMyCollectedURLS" then
            put newURL & return after field "listMyCollectedURLS"
         end if         
      end if    
      
      if thisURL begins with "./"  then
         put rootURL & "/" & thisURL into newURL
         if newURL is not among the items of field "listMyCollectedURLS" then
            put newURL & return after field "listMyCollectedURLS"
         end if         
      end if    
      
   end repeat
end getMyURLs

Code: Select all

function CutTo src, pat
   get offset( pat, src ) 
   if it > 0 then return char (it + number of chars in pat) to -1 of src
   else return src
end CutTo

function CopyTo src, pat
   get offset( pat, src ) - 1
   return char 1 to it of src
end CopyTo

Code: Select all

<div id="search

Code: Select all

Searches related to

Code: Select all

function CutTo src, pat
   get offset( pat, src ) 
   if it > 0 then return char (it + number of chars in pat) to -1 of src
   else return src
end CutTo

function CopyTo src, pat
   get offset( pat, src ) - 1
   return char 1 to it of src
end CopyTo

on mouseUp
   put "" into fld "links"
   put url "https://www.google.com/search?q=livecode" into xx
   put CutTo( xx, "<div id="&quote&"search" ) into xx
   put CopyTo( xx, "Searches related to" ) into xx
   repeat while "<a href=" is in xx
      put CutTo( xx, "<a href=" ) into xx
      set itemdel to quote
      put item 2 of xx into u
      if "webcache.googleusercontent.com" is not in u then
         delete char 1 to 7 of u
         put CopyTo( u, "&" ) into u
         put URLDecode( u ) into u
         put u & return after fld "links"
      end if
   end repeat
end mouseUp

Code: Select all

on mouseUp   
   put URL "http://forums.runrev.com/index.php" into temp
   findLinks temp
end mouseUp

on findLinks temp
   #a html link is like: <a href=www.google.it >
   #but it can be also a mess like: <a class='link' href="www.google.it"  color=green>
   #the correct regular expression to extract link in a tag is: (?i)href=(\"[^"]*\"|'[^']*'|[^'">\s]+)
   #unfortunately is a mess to write directly in the code, so I put it in the
   #regex property of this button
   put the regex of me into regex                  
   put "true" into test
   repeat while test is "true"
      #search and remove till find a "<a"
      put offset("<a ",temp) + 3 into tskip #note that 3 is the length o "<a "      
      if tskip > 3 then         
         delete char 1 to tskip of temp          
         #now we have a problem, the end of the link can                
         #be any of the following chars: space, ", ',>                        
         #now we have the link, but it can be sorrounded by quotes, so we remove them:         
         put matchText(temp,regex,tlink) into status
         if the first char of tlink is "'" or the first char of tlink is quote then                     
            delete first char of tlink                     
            delete last char of tlink                     
         end if             
         #now we put the link in the list of links              
         put tlink & return after ListOfLinks               
      else   
         put "false" into test            
      end if      
   end repeat
   answer ListOfLinks
end findLinks

Code: Select all

function findLinks myhtml
   local tList
   -- regex: (?msi)<a\s.*?href\s*=\s*["']?([^'">\s]+)["']?
   put the regex of me into regex
   repeat while matchChunk( myhtml,regex,pStart,pEnd)
      put 0 into tList[char pStart to pEnd of myhtml]
      delete char 1 to pEnd of myhtml
   end repeat
   return the keys of tList
end findLinks