Project Facebook Feed: Step by step guide to creating a feed from a public group wall in ASP.NET, Perl and PHP.

Purpose
The purpose of this project is to demonstrate how to create a feed from a public group wall on Facebook in ASP.NET, Perl and PHP.

Introduction
This page will show you how to generate an RSS (or simple XML) feed from the wall of a public group on Facebook. Originally I was planning on showing you how to do it with Yahoo! Pipes (where you can have feeds generated of all types), but found that free service to be somewhat unreliable. The code below (that you place on your website) is pretty self explanatory and built so you only need to customize the top portion (changing the head data of an RSS feed that is generated) and the name of the group.

ASP.NET 3.5 Code:

<%@ Import Namespace="System" %>
<%@ Import Namespace="System.IO" %>
<%@ Import Namespace="System.Xml" %>
<%@ Import Namespace="System.Net" %>
<script runat="server">
Dim discussionGroupPage As String = "http://www.facebook.com/PUBLIC-GROUP" ' URL to Group Wall
Dim rssCacheClear As Integer = 0 ' 1 = clear server-cache, 0 = do not clear server-cache.
' RSS Content Provider Data
Dim postLink As String = "thumbnail" ' "topic" = put link to topic in <link></link> of RSS feed, "thumbnail" = put link to thumbnail in <link></link> of RSS feed, "post" = put link to the poster's post
Dim rssDescriptionLen As Integer = 60 ' Number of characters to allow in the poster's post (description)
Dim rssIncludeHeader As Integer = 0 ' 0 = do not include RSS provider data (below), 1 = include
Dim feed_title As String = "FEED TITLE"
Dim feed_link As String = "http://www.facebook.com/PUBLIC-GROUP/"
Dim feed_description As String = "FEED DESCRIPTION"
Dim feed_language As String = "en-us"
Dim feed_pubdate As String = "20 Apr 2007 9:40:00 GMT"
Dim feed_copyright As String = Nothing
Dim feed_webmaster As String = "WEBMASTER@YOUREMAIL.COM"
' Do Not Use
Dim discussionPageData As String = Nothing
Dim crawlAgent As String = Nothing
Dim crawlError As String = Nothing
' TRAP CONNECT ERRORS IN CRAWLPAGE - SEND TO GLOBAL FOR CHECKING
Private Function crawlPage(ByVal URL As String) As String
Dim buffSize As Integer = 2048
Dim crawlOutput As String = Nothing
Dim crawlMethod As String = "GET"
Dim crawlURL As String = URL
Try
Dim myRequest As HttpWebRequest = CType(WebRequest.Create(crawlURL), HttpWebRequest)
myRequest.UserAgent = crawlAgent
myRequest.Method = crawlMethod
Dim myResponse As HttpWebResponse = CType(myRequest.GetResponse(), HttpWebResponse)
Dim streamResponse As Stream = myResponse.GetResponseStream()
Dim streamRead As New StreamReader(streamResponse)
Dim readBuff(buffSize) As [Char]
Dim lineStep As Integer = streamRead.Read(readBuff, 0, buffSize)
While lineStep > 0
Dim outputData As New [String](readBuff, 0, lineStep)
crawlOutput = crawlOutput & outputData
lineStep = streamRead.Read(readBuff, 0, buffSize)
End While
streamRead.Close()
streamResponse.Close()
myResponse.Close()
Catch ex As Exception
crawlError = Server.HtmlEncode(ex.Message)
End Try
Return (crawlOutput)
End Function
Private Sub Page_Load(ByVal sender As System.Object, ByVal e As System.EventArgs)
' Get User's Agent Data
crawlAgent = Request.UserAgent
' Querystring Data
Dim feedName As String = CStr(Request.QueryString("name"))
If Len(feedName) = 0 Then : feedName = "default" : End If
Dim maxFeedsTotalAccept As Integer = CInt(Request.QueryString("feedNumber"))
If maxFeedsTotalAccept <= 0 Then : maxFeedsTotalAccept = 10 : End If
' Do Not Use
Dim rssFeed As String = Nothing
Dim feedContent As String = Nothing
If rssCacheClear = 0 Then
' Build Fresh RSS
If HttpContext.Current.Cache(feedName) Is Nothing Then
' Load Wall Page
discussionPageData = crawlPage(discussionGroupPage)
' Filter Content
discussionPageData = Replace(Replace(Replace(Replace(Replace(discussionPageData, vbCrLf, ""), "\/", "/"), "\""", """"), "\n ", ""), vbCr, "")
If Len(crawlError) <= 0 Then
' Extract Content
Dim collector As String = Nothing
Dim elemLines() As String = Split(discussionPageData, ">")
Dim postBlockFound As Integer = 0
Dim postURL As String = Nothing
Dim topicTitle As String = Nothing
Dim topicTitleURL As String = Nothing
Dim postTimeStamp As String = Nothing
Dim postUserName As String = Nothing
Dim postUserThumbnail As String = Nothing
Dim postUserContent As String = Nothing
Dim groupPostData(,) As String
Dim groupPostDataSize As Integer = 0
For S As Integer = 0 To UBound(elemLines)
If postBlockFound = 7 Then
postBlockFound = 1
postTimeStamp = Replace(elemLines(S), "</a", "")
' Compensate for FB Change #1
if InStr(postTimeStamp, "class=""timestamp""", vbTextCompare) - 1 > -1 Then
postTimeStamp = Split(postTimeStamp, """")(3)
End if
' Compensate for FB code change #2
if InStr(postTimeStamp, "data-date=", vbTextCompare) - 1 > -1 Then
postTimeStamp = Split(postTimeStamp, """")(3)
End if
' Compensate for future tag markup use
if InStr(postTimeStamp, "<", vbTextCompare) - 1 > -1 OR InStr(postTimeStamp, ">", vbTextCompare) - 1 > -1 Then
postTimeStamp = ""
End if
' Save
ReDim Preserve groupPostData(6, groupPostDataSize)
groupPostData(0, groupPostDataSize) = postURL
groupPostData(1, groupPostDataSize) = feed_title
groupPostData(2, groupPostDataSize) = feed_link
groupPostData(3, groupPostDataSize) = postTimeStamp
groupPostData(4, groupPostDataSize) = postUserName
groupPostData(5, groupPostDataSize) = postUserThumbnail
groupPostData(6, groupPostDataSize) = postUserContent
groupPostDataSize = groupPostDataSize + 1
' Clear
postURL = "" : topicTitle = "" : topicTitleURL = "" : postTimeStamp = "" : postUserName = "" : postUserThumbnail = "" : postUserContent = ""
End If
If postBlockFound = 6 Then
postBlockFound = 7
End If
If postBlockFound = 5 Then
If InStr(elemLines(S), "class=""UIIntentionalStory_Time""", vbTextCompare) - 1 > -1 Then
postBlockFound = 6
End If
End If
If postBlockFound = 4 Then
If InStr(elemLines(S), "</h3", vbTextCompare) - 1 > -1 Then
If Len(collector) > 2 Then
postBlockFound = 5
postUserContent = collector : collector = ""
If Len(postUserContent) > rssDescriptionLen Then
postUserContent = Mid(postUserContent, 1, rssDescriptionLen) & "..."
if InStr(postUserContent, ""...", vbTextCompare) - 1 > -1 Then
postUserContent = Replace(postUserContent, "&quot...", ""...")
ElseIf InStr(postUserContent, "&quo...", vbTextCompare) - 1 > -1 Then
postUserContent = Replace(postUserContent, "&quo...", ""...")
ElseIf InStr(postUserContent, "&qu...", vbTextCompare) - 1 > -1 Then
postUserContent = Replace(postUserContent, "&qu...", ""...")
ElseIf InStr(postUserContent, "&q...", vbTextCompare) - 1 > -1 Then
postUserContent = Replace(postUserContent, "&q...", "...")
ElseIf InStr(postUserContent, "&...", vbTextCompare) - 1 > -1 Then
postUserContent = Replace(postUserContent, "&...", "...")
End if
End If
End If
ElseIf InStr(elemLines(S), "<form ", vbTextCompare) - 1 > -1 Then
postBlockFound = 5
postUserContent = collector
If Len(postUserContent) > rssDescriptionLen Then
postUserContent = Mid(postUserContent, 1, rssDescriptionLen) & "..."
if InStr(postUserContent, ""...", vbTextCompare) - 1 > -1 Then
postUserContent = Replace(postUserContent, "&quot...", ""...")
ElseIf InStr(postUserContent, "&quo...", vbTextCompare) - 1 > -1 Then
postUserContent = Replace(postUserContent, "&quo...", ""...")
ElseIf InStr(postUserContent, "&qu...", vbTextCompare) - 1 > -1 Then
postUserContent = Replace(postUserContent, "&qu...", ""...")
ElseIf InStr(postUserContent, "&q...", vbTextCompare) - 1 > -1 Then
postUserContent = Replace(postUserContent, "&q...", "...")
ElseIf InStr(postUserContent, "&...", vbTextCompare) - 1 > -1 Then
postUserContent = Replace(postUserContent, "&...", "...")
End if
End If
Else
elemLines(S) = elemLines(S) & ">"
' Filter Out Tags
Dim tmp_titleFiltered As String = Nothing
Dim flipTitleIndex As Integer = 0
For T As Integer = 0 To Len(elemLines(S))
Dim tmp_topicChar As String = Mid(elemLines(S), T + 1, 1)
If tmp_topicChar = "<" Then : flipTitleIndex = 1 : End If
If flipTitleIndex = 0 Then : tmp_titleFiltered = tmp_titleFiltered & tmp_topicChar : End If
If tmp_topicChar = ">" Then : flipTitleIndex = 0 : End If
Next
collector = collector & " " & tmp_titleFiltered
End If
End If
If postBlockFound = 3 Then
If InStr(elemLines(S), "class=""UIStory_Message""", vbTextCompare) > 0 Then : postBlockFound = 4 : End If
End If
If postBlockFound = 2 Then
postBlockFound = 3
postUserThumbnail = Split(elemLines(S), """")(3)
End If
If postBlockFound = 1 Then
If InStr(elemLines(S), "class=""UIIntentionalStory_Pic""", vbTextCompare) > 0 Then
postBlockFound = 2
postURL = Split(elemLines(S), """")(1)
Try
' UserName in href tag
postUserName = Split(elemLines(S), """")(5)
Catch ex As Exception
' UserName out of sync in a span tag
postUserName = Split(elemLines(S), """")(3)
End Try
End If
End If
If InStr(elemLines(S), "class=""minifeedwall""", vbTextCompare) > 0 And postBlockFound = 0 Then : postBlockFound = 1 : End If
Next
If groupPostDataSize > 0 Then
' Assemble Data Into RSS
Dim feedStep As Integer = 0
For R As Integer = 0 To groupPostDataSize - 1
postURL = groupPostData(0, R)
topicTitle = groupPostData(1, R)
topicTitleURL = groupPostData(2, R)
postTimeStamp = groupPostData(3, R)
postUserName = groupPostData(4, R)
postUserThumbnail = groupPostData(5, R)
postUserContent = groupPostData(6, R)
feedStep = feedStep + 1
If feedStep <= maxFeedsTotalAccept Then
feedContent = feedContent & "<item>" & vbCrLf
feedContent = feedContent & "<title>" & topicTitle & "</title>" & vbCrLf
If LCase(postLink) = "thumbnail" Then
feedContent = feedContent & "<link>" & postUserThumbnail & "</link>" & vbCrLf
ElseIf LCase(postLink) = "topic" Then
feedContent = feedContent & "<link>" & topicTitleURL & "</link>" & vbCrLf
Else
feedContent = feedContent & "<link>" & postURL & "</link>" & vbCrLf
End If
feedContent = feedContent & "<description>" & Server.HtmlEncode(postUserContent) & "</description>" & vbCrLf
feedContent = feedContent & "<author>" & Server.HtmlEncode(postUserName) & "</author>" & vbCrLf
feedContent = feedContent & "<date>" & postTimeStamp & "</date>" & vbCrLf
feedContent = feedContent & "</item>" & vbCrLf
End If
Next
Else
' Nothing Found
If Len(crawlError) <= 0 Then
feedContent = feedContent & "<item>" & vbCrLf
feedContent = feedContent & "<title>Page Found But Data Not Recognized</title>" & vbCrLf
feedContent = feedContent & "<link></link>" & vbCrLf
feedContent = feedContent & "<description>Page Found But Data Not Recognized</description>" & vbCrLf
feedContent = feedContent & "<author></author>" & vbCrLf
feedContent = feedContent & "<date>01 Jan 1900 00:00:01 GMT</date>" & vbCrLf
feedContent = feedContent & "</item>" & vbCrLf
End If
End If ' END groupPostDataSize > 0
If Len(crawlError) <= 0 Then
' Compile RSS Data
rssFeed = rssFeed & "<rss version=""2.0"">" & vbCrLf
rssFeed = rssFeed & "<channel>" & vbCrLf
If rssIncludeHeader = 1 Then
rssFeed = rssFeed & "<title>" & feed_title & "</title>" & vbCrLf
rssFeed = rssFeed & "<link>" & feed_link & "</link>" & vbCrLf
rssFeed = rssFeed & "<description>" & feed_description & "</description>" & vbCrLf
rssFeed = rssFeed & "<language>" & feed_language & "</language>" & vbCrLf
rssFeed = rssFeed & "<date>" & feed_pubdate & "</date>" & vbCrLf
rssFeed = rssFeed & "<copyright>" & feed_copyright & "</copyright>" & vbCrLf
rssFeed = rssFeed & "<webmaster>" & feed_webmaster & "</webmaster>" & vbCrLf
End If
rssFeed = rssFeed & feedContent
rssFeed = rssFeed & "</channel>" & vbCrLf
rssFeed = rssFeed & "</rss>"
' Save Into Server Cache
HttpContext.Current.Cache.Add(feedName, rssFeed, Nothing, DateTime.Now.AddDays(1), System.Web.Caching.Cache.NoSlidingExpiration, CacheItemPriority.Normal, Nothing)
End If
Else
' No Data
End If ' END Len(crawlError) <= 0
' Error With Contacting Target. Index Local RSS Copy.
If Len(crawlError) > 0 Then
Dim baseFolderName As String = feedName
Dim currentFolder As String = Server.MapPath(".")
currentFolder = Replace(currentFolder & "\rssCache.rss")
Dim objFSO = Server.CreateObject("Scripting.FilesystemObject")
If objFSO.fileExists(currentFolder) = True Then
Dim augment = objFSO.OpenTextFile(currentFolder)
rssFeed = augment.readAll
augment.Close()
End If
End If
Else
' Use RSS From Server Cache
rssFeed = CType(HttpContext.Current.Cache(feedName), String)
End If ' END HttpContext.Current.Cache(feedName) Is Nothing
Else
' Clear Server Cache
HttpContext.Current.Cache.Remove(feedName)
' Compile RSS Data
feedContent = feedContent & "<item>" & vbCrLf
feedContent = feedContent & "<title>Server Cache Cleared</title>" & vbCrLf
feedContent = feedContent & "<link></link>" & vbCrLf
feedContent = feedContent & "<description>Server Cache Cleared</description>" & vbCrLf
feedContent = feedContent & "<author></author>" & vbCrLf
feedContent = feedContent & "<date>01 Jan 1900 00:00:01 GMT</date>" & vbCrLf
feedContent = feedContent & "</item>" & vbCrLf
rssFeed = rssFeed & "<rss version=""2.0"">" & vbCrLf
rssFeed = rssFeed & "<channel>" & vbCrLf
If rssIncludeHeader = 1 Then
rssFeed = rssFeed & "<title>" & feed_title & "</title>" & vbCrLf
rssFeed = rssFeed & "<link>" & feed_link & "</link>" & vbCrLf
rssFeed = rssFeed & "<description>" & feed_description & "</description>" & vbCrLf
rssFeed = rssFeed & "<language>" & feed_language & "</language>" & vbCrLf
rssFeed = rssFeed & "<date>" & feed_pubdate & "</date>" & vbCrLf
rssFeed = rssFeed & "<copyright>" & feed_copyright & "</copyright>" & vbCrLf
rssFeed = rssFeed & "<webmaster>" & feed_webmaster & "</webmaster>" & vbCrLf
End If
rssFeed = rssFeed & feedContent
rssFeed = rssFeed & "</channel>" & vbCrLf
rssFeed = rssFeed & "</rss>"
End If ' END rssCacheClear = 0
' Generate Output
Response.Buffer = False
If rssIncludeHeader = 1 Then
Response.ContentType = "application/rss+xml"
Else
Response.ContentType = "text/xml"
End If
Response.Write("<" & "?" & "xml version=""1.0"" encoding=""utf-8""" & "?" & ">" & vbCrLf)
Response.Write(rssFeed)
End Sub
</script>

Perl Code:

#!/usr/bin/perl -w
########################################################
# Facebook Public Group Wall RSS Generator #
########################################################
##### Declare Container For Response Stream
local our $captured_response;
##### Variable Arguments Passed Into Bot Engine
local our $port, $agent_name, $agent_method, $target_domain, $target_full_address, $request_method, $request_protocol;
##### Other
local our $captured_response, $captured_response_filtered, $record, $collectchars, $absPath, $absPathTick, $absPathQuote;
local our $rssDescriptionLen, $maxFeedsTotalAccept, $feedContent, $postLink, $rssIncludeHeader;
local our $feed_title, $feed_link, $feed_description, $feed_language, $feed_pubdate, $feed_copyright, $feed_webmaster;
##### Connection Settings
$target_domain = "www.facebook.com"; # Site to contact
$target_full_address = "/PUBLIC-GROUP"; # Full path to public group wall
$port = 80;
$agent_name = $ENV{HTTP_USER_AGENT};
$agent_method = "http-get/0.1";
$request_method = "GET";
$request_protocol = "HTTP/1.0";
##### RSS Settings
$rssDescriptionLen = 45; # Maximum number of characters to allow in the title
$maxFeedsTotalAccept = 6; # Maximum number of links to get
$postLink = "thumbnail"; # "thumbnail" - URL to thumbnail image, "topic" - URL to topic, "post" - URL to post
$rssIncludeHeader = 1; # 1 - include channel information (RSS), 0 - leave channel information out (XML)
$feed_title = "FEED TITLE";
$feed_link = "http://www.facebook.com/PUBLIC-GROUP/";
$feed_description = "FEED DESCRIPTION";
$feed_language = "en-us";
$feed_pubdate = "11 Apr 2001 01:01:00 GMT";
$feed_copyright = "WEBMASTER\@YOUREMAIL.COM";
$feed_webmaster = "";
##### Date Filter
sub translateTimeStamp() {
my $filteredTimeStamp, $tmpDate, $useMonth, $useDay, $useYear, $useHour, $useMinute, $useSeconds; $useSeconds = "00";
@tmpDate1 = (); @tmpDate2 = (); @dateSegments = (); @timeSegments = ();
# Parse Arguments Array (variables being passed into this subroutine)
my ($rawdate) = @_;
@tmpDate1 = split(/on\s/, $rawdate); @tmpDate2 = split(/\sat\s/, $tmpDate1[1]); $tmpDate2[0] =~ s/\,//g;
@dateSegments = split(/\s/, $tmpDate2[0]); $useMonth = substr($dateSegments[0], 0, 3);
if ($dateSegments[1] < 10) { $useDay = "0" . $dateSegments[1]; }
else { $useDay = $dateSegments[1]; }
$useYear = $dateSegments[2];
@timeSegments = split(/\:/, $tmpDate2[1]);
if ($timeSegments[1] =~ /am/i) { $useHour = "0" . $timeSegments[0]; }
else { $useHour = 12 + $timeSegments[0]; }
$useMinute = $timeSegments[1]; $useMinute =~ s/am//g; $useMinute =~ s/pm//g;
$filteredTimeStamp = $useDay . " " . $useMonth . " " . $useYear . " " . $useHour . ":" . $useMinute . ":" . $useSeconds . "GMT";
return $filteredTimeStamp;
}
##### The Crawler
sub botEngine() {
# Define Some Local (Private) Variables
my $remote, $data_result, $error, $volume, $datastream, $len;
# Parse Arguments Array (variables being passed into this subroutine)
my ($port, $agent_name, $agent_method, $target_domain, $target_full_address, $request_method, $request_protocol) = @_;
# Define Socket Connection
sub TCP { join("", getprotobyname('tcp')); }
sub SOCK_STREAM { 1; }
sub AF_INET { 2; }
sub PF_INET { &AF_INET; }

# Build Identification Header
@Headers = ("User-Agent:$agent_name", $agent_method);
# Resolve Domain To IP Address Using IPv4
if ($target_domain =~ /^[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+$/) { @addrs = pack('C4', split(/\./,$target_domain)); }
else { ($dummy,$dummy,$dummy,$dummy, @addrs) = gethostbyname($target_domain); }
$remote = pack("S n a4 x8", &AF_INET, $port, $addrs[0]);

# Open Socket Connection
unless (socket(S, &PF_INET, &SOCK_STREAM, &TCP)) { $error = 1; $data_result = "Socket Connection Error 1"; }
# Send Request. Gather Response Stream.
if ($error == 0) {
unless (connect(S, $remote)) {
$error = 1;
$data_result = "Socket Connection Error 1 - Attempt 2";
}
if ($error == 0) {
select(S); $| = 1; select(STDOUT); $| = 1;
$request = "$request_method $target_full_address $request_protocol\r\n";
while ($#Headers > 0) { $request = $request . "$Headers[0]: $Headers[1]\r\n"; shift(@Headers); shift(@Headers); }
$request = $request . "\r\n"; print(S $request);
$volume = 1024*1024;
while ($len = sysread(S, $datastream, $volume)) { $captured_response .= $datastream; }
}
}
# Close Socket Connection.
unless (close(S)) { $data_result = "Socket Close Error 1"; }
else { $data_result = "Connection Successful"; }
# Return Status Event Response.
return $data_result;
}
$filename = "$ENV{'DOCUMENT_ROOT'}/rssDay.txt";
$dayNumber = (localtime)[7]; $foundDay = -1;
if (-e $filename) { open (FILE, "$filename"); $foundDay = ; close (FILE); }
if ($dayNumber != $foundDay) {
##### Invoke Crawler
if (length($target_domain) < 0 && length($target_full_address) > 0) {
$response = &botEngine($port, $agent_name, $agent_method, $target_domain, $target_full_address, $request_method, $request_protocol);
}
if ($response eq "Connection Successful") {
##### Filter Content
$captured_response_filtered = $captured_response;
$captured_response_filtered =~ s/\r\n//g; $captured_response_filtered =~ s/\n//g; $captured_response_filtered =~ s/\r//g;
$captured_response_filtered =~ s/\\r\\n//g;$captured_response_filtered =~ s/\\n//g; $captured_response_filtered =~ s/\\r//g;
$captured_response_filtered =~ s/\\\//\//g; $captured_response_filtered =~ s/\\"/"/g;
##### Extract Content
@lines = split(/ @groupPostData = (); $groupPostDataCount = 0;
local our $postBlockFound; $postBlockFound = 0;
local our $topicTitleURL; $topicTitleURL = "";
local our $topicTitle; $topicTitle = "";
local our $postURL; $postURL = "";
local our $postUserName; $postUserName = "";
local our $postTimeStamp; $postTimeStamp = "";
local our $postUserThumbnail; $postUserThumbnail = "";
local our $postUserContent; $postUserContent = "";
foreach $line (@lines) {
if ($postBlockFound == 7) {
if ($groupPostDataCount < $maxFeedsTotalAccept) {
$postBlockFound = 1;
$postTimeStamp = $line; $postTimeStamp =~ s/<\/a//g;
if ($postTimeStamp =~ / @tmp = split(/\"/, $line);
$postTimeStamp = $tmp[3];
}
# Gather Output
$groupPostData[$groupPostDataCount][0] = $feed_link;
$groupPostData[$groupPostDataCount][1] = $feed_title;
$groupPostData[$groupPostDataCount][2] = $postURL;
$groupPostData[$groupPostDataCount][3] = $postUserName;
$groupPostData[$groupPostDataCount][4] = $postTimeStamp;
$groupPostData[$groupPostDataCount][5] = $postUserThumbnail;
$groupPostData[$groupPostDataCount][6] = $postUserContent;
$groupPostDataCount = $groupPostDataCount + 1;
}
# Clear
$postURL = ""; $topicTitle = ""; $topicTitleURL = ""; $postTimeStamp = ""; $postUserName = "";
}
if ($postBlockFound == 6) { $postBlockFound = 7; }
if ($postBlockFound == 5) {
if ($line =~ /class=\"UIIntentionalStory\_Time\"/i) { $postBlockFound = 6; }
}
if ($postBlockFound == 4) {
$line =~ s/\\n\s//g;
if ($line =~ /<\/h3/i) {
if (length($collector) > 2) {
$postBlockFound = 5;
$postUserContent = $collector; $collector = "";
if (length($postUserContent) > $rssDescriptionLen) { $postUserContent = substr($postUserContent, 0, $rssDescriptionLen) . "..."; }
}
}
elsif ($line =~ / $postBlockFound = 5;
$postUserContent = $collector; $collector = "";
if (length($postUserContent) > $rssDescriptionLen) { $postUserContent = substr($postUserContent, 0, $rssDescriptionLen) . "..."; }
}
else {
$line = $line . ">";
my $tmp_titleFiltered = ""; my $flipTitleIndex = 0;
for (my $step = 0; $step < length($line); $step++) {
my $tmp_topicChar = substr($line, $step, 1);
if ($tmp_topicChar eq "<") { $flipTitleIndex = 1; }
if ($flipTitleIndex == 0) { $tmp_titleFiltered = $tmp_titleFiltered . $tmp_topicChar; }
if ($tmp_topicChar eq ">") { $flipTitleIndex = 0; }
}
$collector = $collector . " " . $tmp_titleFiltered;
}
}
if ($postBlockFound == 3) {
if ($line =~ /class=\"UIStory\_Message\"/i) { $postBlockFound = 4; }
}
if ($postBlockFound == 2) {
$postBlockFound = 3;
@tmp = split(/\"/, $line);
$postUserThumbnail = $tmp[3];
}
if ($postBlockFound == 1) {
if ($line =~ /class=\"UIIntentionalStory\_Pic\"/i) {
$postBlockFound = 2;
@tmp = split(/\"/, $line);
$postURL = $tmp[1];
$postUserName = $tmp[5];
}
}
if ($line =~ /class=\"minifeedwall\"/i) { $postBlockFound = 1; }
}
##### CREATE RSS/XML
for ($x = 0; $x < $groupPostDataCount; $x++) {
$topicTitleURL = $groupPostData[$x][0];
$topicTitle = $groupPostData[$x][1];
$postURL = $groupPostData[$x][2];
$postUserName = $groupPostData[$x][3];
$postTimeStamp = $groupPostData[$x][4];
$postUserThumbnail = $groupPostData[$x][5];
$postUserContent = $groupPostData[$x][6];
$topicTitleURL =~ s/&/&/g; $postURL =~ s/&/&/g;
if (length($postUserContent) == 0) { $postUserContent = $topicTitle; }
$postUserContent =~ s/&/&/g;
$feedContent = $feedContent . "<item>\r\n";
$feedContent = $feedContent . "<title>" . $topicTitle . "</title>\r\n";
if ($postLink eq "thumbnail") { $feedContent = $feedContent . "<link>" . $postUserThumbnail . "</link>\r\n"; }
elsif ($postLink eq "topic") { $feedContent = $feedContent . "<link>" . $topicTitleURL . "</link>\r\n"; }
else { $feedContent = $feedContent . "<link>" . $postURL . "</link>\r\n"; }
$feedContent = $feedContent . "<description>" . $postUserContent . "</description>\r\n";
$feedContent = $feedContent . "<author>" . $postUserName . "</author>\r\n";
$feedContent = $feedContent . "<date>" . $postTimeStamp . "</date>\r\n";
$feedContent = $feedContent . "</item>\r\n";
}
# Save Generated Data
$filename = "$ENV{'DOCUMENT_ROOT'}/rssCopy.rss";
if (-e $filename) { chmod 0666, $filename; }
open (FILE, ">$filename");
print FILE $feedContent;
close (FILE); chmod 0644, $filename;
# Save Day Number
$filename = "$ENV{'DOCUMENT_ROOT'}/rssDay.txt";
if (-e $filename) { chmod 0666, $filename; }
open (FILE, ">$filename");
print FILE (localtime)[7];
close (FILE); chmod 0644, $filename;
} # End if $response
else {
# Error With Contacting Target. Index Local RSS Copy.
$filename = "$ENV{'DOCUMENT_ROOT'}/rssCopy.rss";
open (FILE, "$filename"); @chosen = ; close (FILE);
foreach (@chosen) { chop $_; $feedContent = $feedContent . $_ . "\r\n"; }
}
} # End if $foundDay does not match
else {
# On current day. Use Local RSS Copy.
$filename = "$ENV{'DOCUMENT_ROOT'}/rssCopy.rss";
open (FILE, "$filename"); @chosen = ; close (FILE);
foreach (@chosen) { chop $_; $feedContent = $feedContent . $_ . "\r\n"; }
}
##### Generate RSS/XML Output
if ($rssIncludeHeader == 1) {
print "Content-type: application/rss+xml\n\n";
}
else {
print "Content-type: text/xml\n\n";
}
print "<?xml version=\"1.0\" encoding=\"utf-8\"?>\r\n";
print "<rss version=\"2.0\">\r\n";
print "<channel>\r\n";
if ($rssIncludeHeader == 1) {
print "<title>" . $feed_title . "</title>\r\n";
print "<link>" . $feed_link . "</link>\r\n";
print "<description>" . $feed_description . "</description>\r\n";
print "<language>" . $feed_language . "</language>\r\n";
print "<date>" . $feed_pubdate . "</date>\r\n";
print "<copyright>" . $feed_copyright . "</copyright>\r\n";
print "<webmaster>" . $feed_webmaster . "</webmaster>\r\n";
}
print $feedContent;
print "</channel>\r\n";
print "</rss>\r\n";
exit;

PHP Code:

<?php
/* Globals */
global $target_domain, $target_full_address, $agent_name;
global $rssDescriptionLen, $maxFeedsTotalAccept, $postLink, $rssIncludeHeader;
global $feed_title, $feed_link, $feed_description, $feed_language, $feed_pubdate, $feed_copyright, $feed_webmaster;
global $captured_response, $feedContent;
/* Connection Settings */
$target_domain = "www.facebook.com"; // Site to contact
$target_full_address = "/PUBLIC-GROUP"; // Full path to public group wall
$agent_name = $_SERVER['HTTP_USER_AGENT'];
/* RSS Settings */
$rssDescriptionLen = 45; // Maximum number of characters to allow in the description
$maxFeedsTotalAccept = 6; // Maximum number of links to get
$postLink = "thumbnail"; // "thumbnail" - URL to thumbnail image, "topic" - URL to topic, "post" - URL to post
$rssIncludeHeader = 1; // 1 - include channel information (RSS), 0 - leave channel information out (XML)
$feed_title = "FEED TITLE";
$feed_link = "http://www.facebook.com" . $target_full_address;
$feed_description = "FEED DESCRIPTION";
$feed_language = "en-us";
$feed_pubdate = "11 Apr 2001 01:01:00 GMT";
$feed_copyright = "";
$feed_webmaster = "WEBMASTER@YOUREMAIL.COM";
$captured_response = ""; $feedContent = "";
/* The Crawler */
function botEngine($tdomain, $taddress) {
global $captured_response, $agent_name; $captured_response = "";
$targetURL = "http://" . $tdomain . $taddress;
$response = ""; $ch = curl_init();
curl_setopt($ch, CURLOPT_USERAGENT, $agent_name);
curl_setopt($ch, CURLOPT_URL, $targetURL);
curl_setopt($ch, CURLOPT_FAILONERROR, true);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
curl_setopt($ch, CURLOPT_AUTOREFERER, true);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_TIMEOUT, 10);
$captured_response = curl_exec($ch);
if (!$captured_response) { $response = "Connection Failed"; }
else { $response = "Connection Successful"; }
return($response);
}
/* Begin */
$postBlockFound = 0; $topicTitleURL = ""; $topicTitle = ""; $postURL = ""; $postUserName = ""; $postTimeStamp = "";
$postUserThumbnail = ""; $postUserContent = ""; $groupPostData = array(); $groupPostDataCount = 0;
$filename = $_SERVER['DOCUMENT_ROOT'] . "/rssDay.txt";
$dayNumber = floor((time()-mktime(null,null,null,1,0,date("Y")))/86400); $foundDay = -1;
if (file_exists($filename)) { $foundDay = (int)file_get_contents($filename, true); }
if ($dayNumber != $foundDay) {
/* Grab Content */
$response = botEngine($target_domain, $target_full_address);
$captured_response_filtered = preg_replace("/(\r\n)+|(\n|\r)+/", "", $captured_response);
$captured_response_filtered = str_replace("\/", "/", $captured_response_filtered);
$captured_response_filtered = str_replace("\\\"", "\"", $captured_response_filtered);
$captured_response_filtered = str_replace("\n", "", $captured_response_filtered);
$lines = explode(">", $captured_response_filtered); $collector = "";
foreach ($lines as $line) {
if ($postBlockFound == 7) {
if ($groupPostDataCount < $maxFeedsTotalAccept) {
$postBlockFound = 1;
$postTimeStamp = $line; $postTimeStamp = str_replace("</a", "", $postTimeStamp);
if (preg_match("/class=\"timestamp\"/i", $postTimeStamp)) {
$tmp = explode("\"", $postTimeStamp); $postTimeStamp = $tmp[3];
}
// Gather Output
$groupPostData[$groupPostDataCount][0] = $feed_link;
$groupPostData[$groupPostDataCount][1] = $feed_title;
$groupPostData[$groupPostDataCount][2] = $postURL;
$groupPostData[$groupPostDataCount][3] = $postUserName;
$groupPostData[$groupPostDataCount][4] = $postTimeStamp;
$groupPostData[$groupPostDataCount][5] = $postUserThumbnail;
$groupPostData[$groupPostDataCount][6] = $postUserContent;
$groupPostDataCount = $groupPostDataCount + 1;
}
// Clear
$postURL = ""; $postUserName = ""; $postTimeStamp = ""; $postUserThumbnail = ""; $postUserContent = "";
}
if ($postBlockFound == 6) { $postBlockFound = 7; }
if ($postBlockFound == 5) {
if (preg_match("/class=\"UIIntentionalStory_Time\"/i", $line)) { $postBlockFound = 6; }
}
if ($postBlockFound == 4) {
$line = str_replace("\n ", "", $line);
if (preg_match("/<\/h3/i", $line)) {
if (strlen($collector) > 2) {
$postBlockFound = 5;
$postUserContent = $collector; $collector = "";
if (strlen($postUserContent) > $rssDescriptionLen) { $postUserContent = substr($postUserContent, 0, $rssDescriptionLen) . "..."; }
}
}
else if (preg_match("/<form /i", $line)) {
$postBlockFound = 5;
$postUserContent = $collector; $collector = "";
if (strlen($postUserContent) > $rssDescriptionLen) { $postUserContent = substr($postUserContent, 0, $rssDescriptionLen) . "..."; }
}
else {
$line = $line . ">";
$flipTitleIndex = 0; $tmp_titleFiltered = "";
for ($step = 0; $step < strlen($line); $step++) {
$tmp_topicChar = substr($line, $step, 1);
if ($tmp_topicChar == "<") { $flipTitleIndex = 1; }
if ($flipTitleIndex == 0) { $tmp_titleFiltered = $tmp_titleFiltered . $tmp_topicChar; }
if ($tmp_topicChar == ">") { $flipTitleIndex = 0; }
}
$collector = $collector . " " . $tmp_titleFiltered;
}
}
if ($postBlockFound == 3) {
if (preg_match("/class=\"UIStory_Message\"/i", $line)) { $postBlockFound = 4; }
}
if ($postBlockFound == 2) {
$postBlockFound = 3;
$tmp = explode("\"", $line);
$postUserThumbnail = $tmp[3];
}
if ($postBlockFound == 1) {
if (preg_match("/class=\"UIIntentionalStory_Pic\"/i", $line)) {
$postBlockFound = 2;
$tmp = explode("\"", $line);
$postURL = $tmp[1];
if (count($tmp) > 4) {
// UserName in href tag
$postUserName = $tmp[5];
}
else {
// UserName out of sync in a span tag
$postUserName = $tmp[3];
}
}
}
if (preg_match("/class=\"minifeedwall\"/i", $line)) { $postBlockFound = 1; }
}
/* Create RSS/XML */
for ($x = 0; $x < $groupPostDataCount; $x++) {
$topicTitleURL = $groupPostData[$x][0];
$topicTitle = $groupPostData[$x][1];
$postURL = $groupPostData[$x][2];
$postUserName = $groupPostData[$x][3];
$postTimeStamp = $groupPostData[$x][4];
$postUserThumbnail = $groupPostData[$x][5];
$postUserContent = $groupPostData[$x][6];
$topicTitleURL = str_replace("&", "&", $topicTitleURL); $postURL = str_replace("&", "&", $postURL);
if (strlen($postUserContent) == 0) { $postUserContent = $topicTitle; }
$postUserContent = str_replace("&", "&", $postUserContent);
$feedContent = $feedContent . "<item>\r\n";
$feedContent = $feedContent . "<title>" . $topicTitle . "</title>\r\n";
if ($postLink == "thumbnail") { $feedContent = $feedContent . "<link>" . $postUserThumbnail . "</link>\r\n"; }
else if ($postLink == "topic") { $feedContent = $feedContent . "<link>" . $topicTitleURL . "</link>\r\n"; }
else { $feedContent = $feedContent . "<link>" . $postURL . "</link>\r\n"; }
$feedContent = $feedContent . "<description>" . $postUserContent . "</description>\r\n";
$feedContent = $feedContent . "<author>" . $postUserName . "</author>\r\n";
$feedContent = $feedContent . "<date>" . $postTimeStamp . "</date>\r\n";
$feedContent = $feedContent . "</item>\r\n";
}
/* Save Generated Data */
$filename = $_SERVER['DOCUMENT_ROOT'] . "/rssCopy.txt";
if (file_exists($filename)) { /*File Found*/ }
else { /*No File*/ }
$filePointer = fopen($filename, "w");
fputs($filePointer, $feedContent);
fclose($filePointer);
/* Save Day Number */
$filename = $_SERVER['DOCUMENT_ROOT'] . "/rssDay.txt";
if (file_exists($filename)) { /*File Found*/ }
else { /*No File*/ }
$filePointer = fopen($filename, "w");
fputs($filePointer, $dayNumber);
fclose($filePointer);
}
else {
/* On current day. Use Local RSS Copy. */
$filename = $_SERVER['DOCUMENT_ROOT'] . "/rssCopy.txt";
$feedContent = file_get_contents($filename, true);
}
/* Generate RSS/XML Output */
if ($rssIncludeHeader == 1) {
header("Content-type: application/rss+xml");
}
else {
header("Content-type: text/xml");
}
print "<" . "?" . "xml version=\"1.0\" encoding=\"utf-8\"" . "?" . ">\r\n";
print "<rss version=\"2.0\">\r\n";
print "<channel>\r\n";
if ($rssIncludeHeader == 1) {
print "<title>" . $feed_title . "</title>\r\n";
print "<link>" . $feed_link . "</link>\r\n";
print "<description>" . $feed_description . "</description>\r\n";
print "<language>" . $feed_language . "</language>\r\n";
print "<date>" . $feed_pubdate . "</date>\r\n";
print "<copyright>" . $feed_copyright . "</copyright>\r\n";
print "<webmaster>" . $feed_webmaster . "</webmaster>\r\n";
}
print $feedContent;
print "</channel>\r\n";
print "</rss>\r\n";
exit;
?>