Life On VM

CXXFLAGS= -I ~/boost/include/boost-1_38 -I lib/curl/include -lrt

SRCS=main.cpp 

OBJS=main.o 

TINYOBJS=lib/tinyxml/tinystr.o lib/tinyxml/tinyxml.o lib/tinyxml/tinyxmlerror.o lib/tinyxml/tinyxmlparser.o 

LIBS=~/boost/lib/libboost_regex-gcc43-mt-1_38.a /usr/local/lib/libcurl.a

all: termtweet

termtweet: $(OBJS) $(TINYOBJS)
    g++ $(CXXFLAGS) -o $@ $(OBJS) $(TINYOBJS) $(LIBS)

tinyxml: $(TINYOBJS)
    
depend: $(SRCS)
    makedepend $(SRCS)

clean:
    -rm termtweet *.o *.bak *.swp

#include <cstdio>
#include <iostream>
#include "lib/tinyxml/tinyxml.h"
#include <curl/curl.h>
#include <string>

#include <boost/regex.hpp>

using namespace std;

static int writer(char *data, size_t size, size_t nmemb,
        string *buffer)
{
    int result = 0;
    if(buffer == NULL) return result; 

    buffer->append(data, size * nmemb);
    result = size * nmemb;
    return result;
}

void extract_link(const char *s){
    string line(s);
    boost::regex pat(".* (http://.*) .*");
    boost::smatch matches;
    if(boost::regex_match(line, matches, pat))
        cout << "link: " << matches[1] << endl;
}

int main(void){
    cout << "TermTweet 0.1" << endl;
    cout << "Fetching items ..." << endl;
    
    CURL *curl;
    CURLcode res;
    string buffer;

    curl = curl_easy_init();
    if(curl){
        curl_easy_setopt(curl, CURLOPT_URL, "http://twitter.com/statuses/user_timeline/6380022.rss");
        curl_easy_setopt(curl, CURLOPT_WRITEDATA, &buffer);

        curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, writer);

        res = curl_easy_perform(curl);

        curl_easy_cleanup(curl);
    }

    if(res != CURLE_OK)
    {
        cout << "Can't get the RSS feed" << endl;
        exit(-1);
    }
    cout << "Page load completed. Parsing XML .." << endl;

    TiXmlElement *root;
    TiXmlDocument doc;
    doc.Parse(buffer.c_str());
    root = doc.FirstChildElement("rss");
    if(root != NULL){
        TiXmlElement *channel;
        channel = root->FirstChildElement("channel");
        if(channel != NULL){
            TiXmlElement *item;
            item = channel->FirstChildElement("item");
            while(item != NULL){
                TiXmlElement *title;
                title = item->FirstChildElement("title");
                if(title != NULL){
                    cout << title->GetText() << endl;
                    extract_link(title->GetText());
                }

                item = item->NextSiblingElement("item");
                cout << "----------------------------------" << endl;
            }
        }else{
            cout << "Cannot find 'channel'" << endl;
            exit(-1);
        }
    }else{
        cout << "Not an RSS" << endl;
        exit(-1);
    }
    cout << "Parse OK" << endl;
    return 0;
}

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Net;
using System.Xml;
using System.IO;
using System.Text.RegularExpressions;

namespace SharpTermTweet
{
    class Program
    {
        static void Main(string[] args)
        {
            string address = "http://twitter.com/statuses/user_timeline/6380022.rss";
            WebRequest req = WebRequest.Create(address);
            WebResponse res = req.GetResponse();

            StreamReader sr = new StreamReader(res.GetResponseStream());
            string content = sr.ReadToEnd();

            XmlDocument doc = new XmlDocument();
            doc.LoadXml(content);
            XmlNodeList list = doc.GetElementsByTagName("item");
            foreach (XmlNode node in list)
            {
                Console.WriteLine(node["title"].InnerText);
                ExtractLink(node["title"].InnerText);
                Console.WriteLine("-----------------------------");
            }
            
        }

        static void ExtractLink(string line)
        {
            Regex regex = new Regex(".* (http://[^\\s]*) .*");
            Match match = regex.Match(line);
            if(match.Groups.Count >= 2)
                Console.WriteLine("link: {0}", match.Groups[1]);
        }
    }
}