jroberayalas

xml_contents(first_result)
#> {xml_nodeset (3)}
#> [1] <strong>Jan. 21 </strong>
#> [2] “I wasn't a fan of Iraq. I didn't want to go into Iraq.” 
#> [3] <span class="short-truth"><a href="https://www.buzzfeed.com/andrewkaczynski/in-2002-don ...

jroberayalas

xml_contents(first_result)[2] %>% html_text(trim = TRUE)
#> [1] "“I wasn't a fan of Iraq. I didn't want to go into Iraq.”"

jroberayalas

lie <- xml_contents(first_result)[2] %>% html_text(trim = TRUE)
str_sub(lie, 2, -2)
#> [1] "I wasn't a fan of Iraq. I didn't want to go into Iraq."

jroberayalas

explanation <- first_result %>% html_node(".short-truth") %>% html_text(trim = TRUE)
str_sub(explanation, 2, -2)
#> [1] "He was for an invasion before he was against it."

jroberayalas

url <- first_result %>% html_node("a") %>% html_attr("href")
url
#> [1] "https://www.buzzfeed.com/andrewkaczynski/in-2002-donald-trump-said-he-supported-invading-iraq-on-the"

jroberayalas

library(dplyr)
records <- vector("list", length = length(results))

for (i in seq_along(results)) {
    date <- str_c(results[i] %>% html_nodes("strong") %>% html_text(trim = TRUE), ", 2017")
    lie <- str_sub(xml_contents(results[i])[2] %>% html_text(trim = TRUE), 2, -2)
    explanation <- str_sub(results[i] %>% html_nodes(".short-truth") %>% html_text(trim = TRUE), 2, -2)
    url <- results[i] %>% html_nodes("a") %>% html_attr("href")
    records[[i]] <- data_frame(date = date, lie = lie, explanation = explanation, url = url)
}

jroberayalas

library(lubridate)
df$date <- mdy(df$date)
glimpse(df)
#> Observations: 116
#> Variables: 4
#> $ date        <date> 2017-01-21, 2017-01-21, 2017-01-23, 2017-01-25, 2017-01-25, 2017-01-...
#> $ lie         <chr> "I wasn't a fan of Iraq. I didn't want to go into Iraq.", "A reporter...
#> $ explanation <chr> "He was for an invasion before he was against it.", "Trump was on the...
#> $ url         <chr> "https://www.buzzfeed.com/andrewkaczynski/in-2002-donald-trump-said-h...

jroberayalas

# Load packages
library(rvest)
library(stringr)
library(dplyr)
library(lubridate)
library(readr)

# Read web page
webpage <- read_html("https://www.nytimes.com/interactive/2017/06/23/opinion/trumps-lies.html")

jroberayalas

write_csv(df, "trump_lies.csv")

jroberayalas

df <- read_csv("trump_lies.csv")
#> Parsed with column specification:
#> cols(
#>   date = col_date(format = ""),
#>   lie = col_character(),
#>   explanation = col_character(),
#>   url = col_character()
#> )