Btibert3

## help
#http://stackoverflow.com/questions/1395528/scraping-html-tables-into-r-data-frames-using-the-xml-package

### load the libraries
library(RCurl)
library(XML)

## URL
URL.1 <- "http://www.kiplinger.com/tools/privatecolleges/index.php?table=prv_univ"
URL.2 <- "http://www.kiplinger.com/tools/privatecolleges/index.php?table=lib_arts"

Btibert3

###############################################################################
# Author: @BrockTibert
#
# Used: R Version 2.12.1, Windows 7 Pro, StatET Plugin for Eclipse
#
#
###############################################################################

#-----------------------------------------------------------------------
# set up script level basics

Btibert3

---
# My First Slide

Btibert3

user_credentials <- function() {
 # capture the user name
 U <- readline("Account username: ")
 # capture the password
 P <- readline("Account password: ")
 # return the data as a list
 return(list(U,P)) 
}

Btibert3

## load the packages
require(XML)
require(RCurl)
require(rjson)
require(plyr)

## will create a request to the twitter search API - returns JSON
## https://dev.twitter.com/docs/api/1/get/search
## max combo can be 1500 tweets (100*15 pages)
## API limit = 150 requests / hour for requests that are not authenticated

Btibert3

> require(devtools)
Loading required package: devtools
Warning message:
package ‘devtools’ was built under R version 2.15.2 
> install_github("slidify", "ramnathv")
Installing github repo(s) slidify/master from ramnathv
Installing slidify.zip from https://api.github.com/repos/ramnathv/slidify/zipball/master
Installing slidify
Installing dependencies for slidify:
yaml

Btibert3

## act to sat concordance chart
## http://www.act.org/aap/concordance/pdf/reference.pdf
act <- (36:11)
sat <- c(1600, 1560, 1510,  1460, 1420, 1380, 1340, 1300, 1260, 1220, 1190,
         1150, 1110, 1070, 1030, 990, 950, 910, 870, 830, 790, 740, 690, 640,
         590, 530)
act2sat <- data.frame(act, sat)

Btibert3

This works as expected

```{r}
library(rjson)
# comment
2+2
```
This doesn't print properly

```{r, eval=FALSE}

Btibert3

#! /bin/bash
# remove the lines below here before running------
# Example 7: connect into the twitter firehouse - best approach is to use Command Line - run in Ubuntu 11.10
#      Attempted to do this within R, but different approaches proved computing resources get consumed at incredible rate
# need to make this file executable from a command line in a linux-type environment (run in Ubuntu) by chmod 755
# saves datafile every hour (closes curl, reopens curl) from the twitter sample firehouse, raw json, should be able to process raw data in R and elsewhere
# If you're already in the directory containing the file you could just type: ./filename.sh and press Enter.

while true; do
    curl -s -m 3600 -u twitterusername:twitterpassword https://stream.twitter.com/1/statuses/sample.json -o "twtstream_$(date +%Y%m%d%H).txt"

Btibert3

###############################################################################
## Use R to scrape the US News College List and look at yield distribution
## @brocktibert
## jan 2013
###############################################################################


## load the necessary packages
require(XML)
require(RCurl)