API_ds.Rmd

---
title: "R Notebook"
output: html_notebook
editor_options: 
  chunk_output_type: inline
---

```{r}
#install.packages("httr")
library(httr)
```

```{r}
# Sending API request with a key
response <- GET("https://api.themoviedb.org/3/tv/top_rated?api_key=e3125dff006ab216b7133dda421fdea0&language=en-US&page=1")
```

```{r}
# Checking the status code (200 - all good, 404 - error) and content 
response$status_code

#check the content
response$content

# Converting the raw file to character
api_char <- base::rawToChar(response$content)

#Converting the json file to a readable version
api_json <- jsonlite::fromJSON(api_char, flatten = TRUE)
api_json

#Converting the json file to dataframe
df <- data.frame(api_json)
ncol(df)
```

```{r}
View(df)
```

```{r}
#Creating empty dataframe with 16 columns to use in for loop
dt<-NULL
dt <- data.frame(matrix(ncol=16,nrow=0))
colnames(dt) <- colnames(df)
```

```{r}
# Creating a for loop to convert every page of the json file to dataframe and add to df
for (i in 1:131)
  {
      response <- GET(sprintf("https://api.themoviedb.org/3/tv/top_rated?api_key=e3125dff006ab216b7133dda421fdea0&language=en-US&page=%s",i))
      api_char <- base::rawToChar(response$content)
      api_json <- jsonlite::fromJSON(api_char, flatten = TRUE)
      df_temp <- data.frame(api_json)
      dt <- rbind(dt, df_temp)
  }
View(dt)
```

```{r}
# Remove unnecessary columns
dt <- subset(dt, select=c("results.first_air_date", "results.origin_country", "results.original_language", "results.name", "results.popularity", "results.vote_average", "results.vote_count", "results.overview"))

#Standardize column names
colnames(dt) <- gsub("results.", "", colnames(dt))

#Convert columns of list type to character type

```


```{r}
dt$origin_country <- as.character(dt$origin_country)
```

```{r}
write.csv(dt, "./data_TV.csv", row.names=FALSE)
```

```{r}
skimr::skim(dt$origin_country)
nrow(dt)
unique(dt$origin_country)
```
```{r}
skimr::skim(dt$first_air_date)
```