For Sarah April 2019 - part 2

get_all_agency_urls2.py

from urllib.request import urlopen
from bs4 import BeautifulSoup
from selenium import webdriver
import time
import csv

driver = webdriver.Chrome('/Users/mcadams/Documents/python/scraping2019/chromedriver')
# testing the 'C' page only
driver.get('https://www.usa.gov/federal-agencies/c')

# pause because page is slow to load
time.sleep(5)

html = driver.page_source
bs = BeautifulSoup(html, "html5lib")

# close automated chrome
driver.quit()

# get all a elements and test by printing
letter_list = bs.find( 'ul', {'class':'one_column_bullet'} )
letter_urls = letter_list.find_all('a')

print(len(letter_urls))
print(letter_urls[0])
print(letter_urls[12])
print( letter_urls[len(letter_urls) -1] )

Again, not getting hrefs, but see how this code is almost identical to the previous script.