You want to get users of your R script as close to the data used for analysis as you can, but download.file() isn't going to cut it. There's no obvious direct link to the CSV and what you're left with is an anchor tag backed by a javascript function.
So, we need to click this element to initiate a download.
Enter RSelenium, an R package that interfaces with the browser driving selenium.
First, get curl and java.
| #!/bin/bash | |
| # Description: | |
| # Adds a game to your retropie NES called 'Feeling Lucky' which launches a random game from your collection | |
| # INSTALL: Point your nes launcher in /etc/emulationstation/es_systems.cfg | |
| # to this script. (e.g. /home/pi/NES_feeling_lucky.sh %ROM%) | |
| flag="$HOME/RetroPie/roms/nes/Feeling Lucky.nes" |
| library(poweRlaw) | |
| # csv is just a dump from the breach website with a filter applied for Hacking/IT Incidents and the date range. | |
| hhs.data <- read.csv("~/Downloads/hhs_hacking_01012010thru12312015.csv", header = T, stringsAsFactors = FALSE) | |
| hhs.data <- hhs.data[!is.na(hhs.data$Individuals.Affected),] | |
| hhs.data$Date.Submitted <- strptime(hhs.data$Breach.Submission.Date, "%m/%d/%Y") | |
| hhs.data <- subset(hhs.data, Date.Submitted > "2010-01-01" & Date.Submitted < "2015-01-01") | |
| m <- displ$new(hhs.data$Individuals.Affected) | |
| m$setXmin(estimate_xmin(m)) | |
| m$setPars(estimate_pars(m)) |
| library(rvest) | |
| winners <- read_html("https://www.bigtexan.com/72oz-hall-fame/") | |
| count <- winners %>% | |
| html_nodes(xpath = '//*[@id="post-371"]/div/div[3]/div/div/div/table/tbody//tr/td[1]') %>% | |
| html_text() | |
| date <- winners %>% | |
| html_nodes(xpath = '//*[@id="post-371"]/div/div[3]/div/div/div/table/tbody//tr/td[2]') %>% |
| library(gsubfn) | |
| library(magrittr) | |
| big.texan.recordbook <- read.csv("/bigtexan.csv", stringsAsFactors = FALSE) | |
| # Fixing dates that arent't. | |
| # > grep("[0-9]{1,2}/[0-9]{1,2}/[0-9]{1,2}", big.texan.recordbook$date, value = TRUE, invert = TRUE) | |
| # [1] "*1965" "*1966" "*1968" "*1972" "*1972" "1/??/98" "8/??/2004" | |
| # [8] "4/?/10" "101 4/5" " " "7/210/15" " " |
| #!/usr/local/bin/ruby | |
| # Must have ruby later ruby to use Dir.children() | |
| require 'date' | |
| require 'shellwords' | |
| origin_folder = '~/Music/iTunes/iTunes Media/Podcasts/' | |
| Dir.chdir(File.expand_path(origin_folder)) | |
| contents = Dir.glob('*') | |
| contents.each {|folder| |
| https://github.com/search?q=BROWSER_STACK_ACCESS_KEY= OR BROWSER_STACK_USERNAME= OR browserConnectionEnabled= OR BROWSERSTACK_ACCESS_KEY=&s=indexed&type=Code | |
| https://github.com/search?q=CHROME_CLIENT_SECRET= OR CHROME_EXTENSION_ID= OR CHROME_REFRESH_TOKEN= OR CI_DEPLOY_PASSWORD= OR CI_DEPLOY_USER=&s=indexed&type=Code | |
| https://github.com/search?q=CLOUDAMQP_URL= OR CLOUDANT_APPLIANCE_DATABASE= OR CLOUDANT_ARCHIVED_DATABASE= OR CLOUDANT_AUDITED_DATABASE=&s=indexed&type=Code | |
| https://github.com/search?q=CLOUDANT_ORDER_DATABASE= OR CLOUDANT_PARSED_DATABASE= OR CLOUDANT_PASSWORD= OR CLOUDANT_PROCESSED_DATABASE=&s=indexed&type=Code | |
| https://github.com/search?q=CONTENTFUL_PHP_MANAGEMENT_TEST_TOKEN= OR CONTENTFUL_TEST_ORG_CMA_TOKEN= OR CONTENTFUL_V2_ACCESS_TOKEN=&s=indexed&type=Code | |
| https://github.com/search?q=-DSELION_BROWSER_RUN_HEADLESS= OR -DSELION_DOWNLOAD_DEPENDENCIES= OR -DSELION_SELENIUM_RUN_LOCALLY=&s=indexed&type=Code | |
| https://github.com/search?q=ELASTICSEARCH_PASSWORD= OR ELASTICSEARCH_USERNAME= OR EMAIL_NOTIFI |
| success. |