Rss Parser in Liberty Basic

 'Download html from given 
 'URL to file on disk. 
 ' 
 'Minimum availability Internet Explorer 3.0 
 'Minimum operating systems Windows NT 4.0, Windows 95 
 ' 
 
 'check for valid URL for HTML page: 
 url$="http://rss.cnn.com/rss/cnn_travel.rss" 
 uniUrl$ = MultiByteToWideChar$(url$) 
 
 if uniUrl$ = "" then 
 print "Unable to convert URL to unicode string." 
 end 
 end if 
 
 'if result = 0, URL is valid 
 result = ValidURL(uniUrl$) 
 
 if result = 0 then 
 'download html from url 
 Cursor Hourglass 
 downloadresult = DownloadToFile(url$,"D:\Maich.Stuff\LbasicStuff\XML\temp.tmp") 
 if downloadresult <> 0 then print "Error downloading ";url$ 
 Cursor Normal 
 else 
 print "Invalid URL:"; url$ 
 end if 
 'Now opening th rss file, and binding to local var... 
 'Will be array for future multiple rss... 
 
 open "D:\Maich.Stuff\LbasicStuff\XML\temp.tmp" for input as #f 
 rss$=input$ (#f, lof(#f)) 
 close #f 
 
 'print rss$ 'print HTML from file into mainwin 
 'print : print 
 'sprint "The text above was downloaded from ";url$ 
 
 a= StripTags(rss$) 
 
 
 function StripTags(raw$) 
 'print only the tags starting with < and ending with > 
 'According to RSS 2.0 standart we have the following channel data.. 
 'First, start with rss or xml declaration, version...Then 
 'Channel 
 ' |-Title Required 
 ' |-Link Required 
 ' |-Description Required 
 ' 
 ' |-Language Optional 
 ' |-Copyright Optional 
 ' |-managingEditor Optional 
 ' |-webMaster Optional 
 ' |-pubDate Optional 
 ' |-lastBuildDate Optional 
 ' |-category Optional 
 ' |-generator Optional 
 ' |-docs Optional 
 ' |-cloud Optional 
 ' |-ttl Optional 
 ' |-image Optional--------------------------------------------- 
 ' |-rating Optional |><url></url> 
 ' |-textInput Optional |<title></title> 
 ' |-skipHours Optional |<link></link> 
 ' |-skipDays Optional |<width></width> 
 ' |<height></height> 
 ' |<description></description> 
 ' 
 ' 
 ' 
 ' 
 ' 
 ' 
 ' 
 ' Elements of items...Items are sub-elements of Channels btw... 
 'So 
 'Channel---- 
 ' |---<item> 
 ' |---<item> 
 ' |---<item> 
 ' |---<item> 
 ' |-Title 
 ' |-Link 
 ' |-Description 
 ' |-Author 
 ' |-Category 
 ' |-Comments 
 ' |-enclosure 
 ' |-guid 
 ' |-pubDate 
 ' |-source 
 'But the point is that most rss feeds doesn't follow this sequence of tags...So, first, we'll remove the tags 
 'with the information attached to them, and we'll have TAG=Content type of arrays... 
 
 channeltags$="title,link,description,language,copyright,managingeditor,webmaster,pubdate,lastbuilddate,category,generator,docs,cloud,ttl,image,rating,textinput,skiphours,skipdays," 
 itemtags$="title,link,description,author,category,comments,enclosure,guid,pubdate,source," 
 
 while tagend<len(raw$) 
 
 tagstart=instr(raw$,"<",tagend) 
 tagend=instr(raw$,">",tagstart) 
 taglen=tagend-tagstart+1 
 'print mid$(raw$,leftbrack,taglen), rightbrack 
 
 if instr(mid$(raw$,tagstart,taglen),"<channel>",0)>0 then 
 chcount=1 
 print "We found a channel! " 
 while word$(channeltags$,chcount,",")<>"" 
 
 
 if instr(lower$(raw$),"<"+word$(channeltags$,chcount,",")+">")<>0 then 
 
 tagstart=instr(lower$(raw$),"<"+word$(channeltags$,chcount,",")+">")+len("<"+word$(channeltags$,chcount,",")+">") 
 tagend=instr(lower$(raw$),"</"+word$(channeltags$,chcount,",")+">",tagstart) 
 taglen=tagend-tagstart 
 print upper$(word$(channeltags$,chcount,","));">>>>";mid$(raw$,tagstart,taglen) 
 'here, if we have image, seperately we must parse it... 
 
 end if 
 chcount=chcount+1 
 wend 
 'Upto here, everything is working fine...Missing parts are GUID and media...image tag should be parsed independent... 
 filepos=instr(raw$,"<item>") 
 
 while instr(raw$,"<item>")<>0'Loop until there are no items left... 
 'since channel is finished, cut the raw$ to only size of items... 
 currentitem$=mid$(raw$,filepos-1,instr(raw$,"</item>")) 
 raw$=right$(raw$,len(raw$)-instr(raw$,"/item>")) 
 itemcount=1 
 print "New item!" 
 while word$(itemtags$,itemcount,",")<>"" 
 
 if instr(lower$(currentitem$),"<"+word$(itemtags$,itemcount,",")+">")<>0 then 
 tagstart=instr(lower$(currentitem$),"<"+word$(itemtags$,itemcount,",")+">")+len("<"+word$(itemtags$,itemcount,",")+">") 
 tagend=instr(lower$(currentitem$),"</"+word$(itemtags$,itemcount,",")+">",tagstart) 
 taglen=tagend-tagstart 
 print upper$(word$(itemtags$,itemcount,","));">>>>";mid$(currentitem$,tagstart,taglen) 
 ' print tagstart,tagend,taglen 
 end if 
 itemcount=itemcount+1 
 filepos=1 
 wend'single item 
 wend'whole items... 
 
 end if 'channel end if... 
 
 
 
 wend 
 
 'Upto here, everything is working fine...Missing parts are GUID and media 
 End Function 
 
 
 Function lowercase (string$) 
 lowercase$=lower$(string$) 
 End Function 
 
 
 
 Function DownloadToFile(urlfile$, localfile$) 
 open "URLmon" for dll as #url 
 calldll #url, "URLDownloadToFileA",_ 
 0 as long,_ 'null 
 urlfile$ as ptr,_ 'url to download 
 localfile$ as ptr,_ 'save file name 
 0 as long,_ 'reserved, must be 0 
 0 as long,_ 'callback address, can be 0 
 DownloadToFile as ulong '0=success 
 close #url 
 end function 
 
 Function ValidURL(urlfile$) 
 open "URLmon" for dll as #url 
 calldll #url, "IsValidURL",_ 
 0 as long,_ 'ignored, must be 0 
 urlfile$ as ptr,_ 'urlfile to check 
 0 as ulong,_ 'ignored, must be 0 
 ValidURL as long 
 close #url 
 end function 
 
 
 function MultiByteToWideChar$(String$) 
 'converts any string into unicode 
 CodePage = 0 : dwFlags = 0 
 cchMultiByte = -1 
 lpMultiByteStr$ = String$ 
 cchWideChar = len(String$) * 3 
 lpWideCharStr$ = space$(cchWideChar) 
 
 calldll #kernel32, "MultiByteToWideChar", _ 
 CodePage as ulong, _ 'CP_ACP=0, ansi code page 
 dwFlags as ulong, _ 'use 0, flags for character translation 
 lpMultiByteStr$ as ptr,_'the ascii string to convert 
 cchMultiByte as long, _ 'len of string, -1 for null-terminated string 
 lpWideCharStr$ as ptr, _'buffer for returned ansi string 
 cchWideChar as long, _ 'size in wide characters of string buffer 
 result as long 'returns number of wide characters written to buffer 
 
 if result = 0 then 
 MultiByteToWideChar$ = "" 
 else 
 MultiByteToWideChar$ = left$(lpWideCharStr$, result * 2) 
 end if 
 end function