---
title: "rvestTutorial"
author: "Kathleen Durant"
date: "October 15, 2017"
output: pdf_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

## R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see <http://rmarkdown.rstudio.com>.

When you click the **Knit** button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

```{r getdata}
library(rvest)
library(magrittr)
rpack_html <-
"http://cran.r-project.org/web/packages" %>%
read_html()
rpack_html %>% class()
rpack_html %>% xml_structure(indent = 1)
```
```{r}
rpack_html %>% html_text() %>% cat()
```


```{r}
rpack_html %>%
html_node(xpath="//p/a[contains(@href, 'views')]/..")


```
```{r}
rpack_html %>% # all links on page
html_nodes(xpath="//a") %>%
html_attr("href") %>% .[1:6]

rpack_html %>% # all links on page
html_nodes(xpath="//a") %>%html_attr("href") %>% extract(1:6)
```


```{r}

```


```{r}
library(rvest)
library(httr)
text <-
"Quirky spud boys can jam after zapping five worthy Polysixes."
mainpage <- read_html("http://read-able.com")
mainpage %>%
html_nodes(xpath="//form") %>%
html_attrs()


```


```{r}
library(httr)
# html operations
#GET: fetch an existing resource. The URL contains all the necessary information the server needs to locate and return the resource.
#POST: create a new resource. POST requests usually carry a payload that specifies the data for the new resource.
#PUT: update an existing resource. The payload may contain the updated data for the resource.
#DELETE: delete an existing resource.
r <- GET("http://httpbin.org/get")
r
status_code(r)
#> [1] 200
headers(r)
str(content(r))
r <- GET("http://httpbin.org/get")
# Get an informative description:
http_status(r)
r$status_code # 200 is success
content(r, "text")
# can extract cookies that persist
content(r, "text", encoding = "ISO-8859-1")
r <- GET("http://httpbin.org/cookies/set", query = list(a = 1))
cookies(r)
# passing arguments to a website to extract specific information
r <- GET("http://httpbin.org/get", 
  query = list(key1 = "value1", key2 = "value2"))
# add custom header 
r <- GET("http://httpbin.org/get", add_headers(Name = "Hadley"))
str(content(r)$headers)

content(r)$args
r <- GET("http://httpbin.org/cookies", set_cookies("MeWant" = "cookies"))
content(r)$cookies
# when posting you can include data in the body
r <- POST("http://httpbin.org/post", body = list(a = 1, b = 2, c = 3))
# you can set the encoding
url <- "http://httpbin.org/post"
body <- list(a = 1, b = 2, c = 3)

# Form encoded
r <- POST(url, body = body, encode = "form")
# Multipart encoded
r <- POST(url, body = body, encode = "multipart")
# JSON encoded
r <- POST(url, body = body, encode = "json")
# you can also upload files 
#POST(url, body = upload_file("mypath.txt"))
#POST(url, body = list(x = upload_file("mypath.txt")))
```
#