pdparker

#load beautiful soup and itertools
from bs4 import BeautifulSoup
import itertools
import re
#import URL with imitated browser
from urllib import FancyURLopener
class MyOpener(FancyURLopener):
    version = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.152 Safari/537.36'
openurl = MyOpener().open
print "sep=;"

pdparker

uni = raw_input("Please enter CRICOS ID: ")

#based on https://stockrt.github.io/p/emulating-a-browser-in-python-with-mechanize/

import mechanize
import cookielib
from bs4 import BeautifulSoup
import itertools
import re

pdparker

# Transform .Rmd files to slidy files

.SUFFIXES: .Rmd .html .md

all: Day1Part1-Introduction.md Day1Part1-Introduction.html Day1Part1-session2.md Day1Part1-session2.html \
	Day1Part1-session3.md Day1Part1-session3.html Day1Part2-session1.md Day1Part2-session1.html \
	Day1Part2-session2.md Day1Part2-session2.html

#markdown
%.md: %.Rmd

pdparker

#load beautiful soup and itertools
from bs4 import BeautifulSoup
import itertools
import re
from urllib import FancyURLopener
class MyOpener(FancyURLopener):
    version = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.152 Safari/537.36'
openurl = MyOpener().open
#If you want to use you will have to change "user=*" in the url below
url = 'http://scholar.google.com.au/citations?user=xHY4MJ8AAAAJ&hl=en'

pdparker

import itertools
import re
import string
import csv
from splinter import Browser
from bs4 import BeautifulSoup


#uni = "00219C"
uni = raw_input("")

pdparker

/* I have only tested this on Chrome but it 
prints nicely to A4 size */

@media print {
    body {
    width: 210mm;
    height: 297mm;
	}
}

pdparker

---
output:
  html_document:
    number_sections: no
    toc: no
    fig_caption: yes
    css: style.css
---

```{r titlePage, echo=FALSE, message=FALSE, warning=FALSE,results='asis'}

pdparker

/* compile using gcc digits.c -lm -o digits */

#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include <errno.h>

#define DIGITS 5

void die(const char *message){

pdparker

data <- read.csv("/Users/phparker/Dropbox/Databases/AmericanStudy.csv")

iplocation <- function(ip=""){
  response    <- readLines(paste("http://www.datasciencetoolkit.org//ip2coordinates/",ip,sep=""))
  success     <- !any(grepl("null",response))
  
  ip <- grep("[[:digit:]]*\\.[[:digit:]]*\\.[[:digit:]]*\\.[[:digit:]]*",response,value=T)
  match <- regexpr("[[:digit:]]*\\.[[:digit:]]*\\.[[:digit:]]*\\.[[:digit:]]*",ip)
  ip <- substr(ip,match,as.integer(attributes(match)[1])+match-1)
  if(success==T){

pdparker

#################################### Set up database ###########################
# - Make sure database is setup to be read,write and executable outside of sudo
# - Make sure to start mongo deamon before setting up database usr$ mongod
################################################################################

##Produces mongodb documents with the following fields:
# _id: Transcript id - used to index the files
# title: Title of the speech or interview
# primMinister: Who gave the speech in format 'Last name, First name'
# releaseDate: Given in days since 1970-01-01 as per R's default data storage