html-table-extractor

# Load the required library
library(xml2)
library(rvest)
library(dplyr)

# Define the base URL for the website
base_url <- "https://example.com/edit_this_url?

# Define the request URL for the website

req_url <- base_url |>
  
  read_html(encoding = "UTF-8") |>
  
  html_nodes("enter html node that contain request url") 

print(req_url)

# Extract the text values from the nodeset
requests <- xml_text(req_url)

# Combine all values into a single column
requests_df <- data.frame(Requests = requests)

# Print the resulting data frame
print(requests_df)

# requests_df is dataframe with the "Requests" column to combine with base_url

# Create an empty list to store data frames for each option
all_data_frames <- list()

# Loop through selected options
for (requests in requests_df) {
  # Combine the requests with the base URL to create the full URL
  url <- paste(base_url, requests, sep = "")
  
  # Read HTML content from the URL
  webpage <- read_html(url, encoding = "UTF-8")
  
  # Extract all tables from the HTML content
  tables <- webpage %>% html_nodes("table")
  
  # Extract data frames from each table
  data_frames <- lapply(tables, function(table) {
    as.data.frame(html_table(table))
  })
  
  # Store the data frames in the list, using the option as the key
  all_data_frames[[requests]] <- data_frames
}