erikgregorywebb

  ggplot(moment, aes(x = minuteCount)) + 
    geom_histogram(binwidth = 10) + 
    labs(title="Distribution of Minute Counts") 

erikgregorywebb

# https://unboxed-analytics.shinyapps.io/the-potential-for-growth/
# http://unboxed-analytics.com/life-hacking/fundamentals-of-investing/

library(FinCal)
library(ggplot2)
library(tidyr)
library(shinythemes)
library(scales)

# Define UI for application that draws a histogram

erikgregorywebb

    def getListingLinks(link):
        # Open the driver
        driver = webdriver.Chrome(executable_path="/Users/erikgregorywebb/Downloads/chromedriver 2")
        driver.get(link)

        # Save the links
        listing_links = []
        links = driver.find_elements_by_css_selector('.listing-item-link')
        for link in links:
            listing_links.append(str(link.get_attribute('href')))

erikgregorywebb

  def getListingContent(listing_link):
      # Open the driver
      driver = webdriver.Chrome(executable_path="/Users/erikgregorywebb/Downloads/chromedriver 2")
      driver.get(listing_link)

      # Collect listing informtion
      try:
          title = driver.find_element_by_css_selector('.listingDetails-title')
          location = driver.find_element_by_css_selector('.listingDetails-location')
          price = driver.find_element_by_css_selector('.listingDetails-price')

erikgregorywebb

  from selenium import webdriver
  from selenium.webdriver.common.keys import Keys
  import time
  import pandas as pd

erikgregorywebb

    def getListings(url):
        links = getListingLinks(url)
        listings = []

        # Loop over each listing link
        for i in range(0, 10):
            time.sleep(3)
            try:
                listing = getListingContent(links[i])
                listings.append(listing)

erikgregorywebb

    def cleanLlistings(df):
        # Split the location variable into location and days_online
        df['location'], df['days_online'] = df['location'].str.split('|', 1).str

        # Remove the dollar sign in price
        df['price'] = df['price'].str.replace('$', '')
        df['price'] = df['price'].str.replace(',', '')

        # Convert from string to numeric
        df['views'] = pd.to_numeric(df['views'])

erikgregorywebb

    def main(url):
        start_time = time.time()

        # Process
        raw_df = getListings(url)
        df = cleanLlistings(raw_df)

        # Export
        df.to_csv("/Users/erikgregorywebb/Documents/Python/ksl-scrapper/listings.csv", sep = ',')

erikgregorywebb

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import time
import pandas as pd

def getListingLinks(link):
    # Open the driver
    driver = webdriver.Chrome(executable_path="/Users/erikgregorywebb/Downloads/chromedriver 2")
    driver.get(link)
    

erikgregorywebb