AO8’s gists

AO8 / it_enrollment_scraper2.py

Created July 18, 2018 18:05

A slightly different version of previous IT enrollment Python web scraper project. Includes GUI automation with pyautogui, scraping with BeautifulSoup, and sending gmail notifications with smtplib and MIMEText

	# Standard Library
	import smtplib
	import webbrowser
	from time import sleep
	from datetime import datetime as dt
	from urllib.request import urlopen
	from email.mime.text import MIMEText
	# Third-party
	import pyautogui
	from bs4 import BeautifulSoup

AO8 / ask_zen_of_python.py

Last active August 6, 2018 21:28

Scrape a random piece of Zen from PEP 20 (Zen of Python) with BeautifulSoup.

	# Python 3.6.4

	import random
	from time import sleep
	import requests
	from bs4 import BeautifulSoup

	html = requests.get("https://www.python.org/dev/peps/pep-0020/")
	soup = BeautifulSoup(html.text, "html.parser")
	zen_of_python = soup.find("pre").get_text()

AO8 / table_writer.py

Last active May 22, 2025 05:18

Convert an HTML table into a CSV file with Python and BeautifulSoup.

	# Adapted from example in "Web Scraping with Python, 2nd Edition" by Ran Mitchell.

	import csv
	from urllib.request import urlopen
	from bs4 import BeautifulSoup

	html = urlopen("http://en.wikipedia.org/wiki/"
	"Comparison_of_text_editors")
	soup = BeautifulSoup(html, "html.parser")
	table = soup.findAll("table", {"class":"wikitable"})[0]

AO8 / story_scraper.py

Last active June 21, 2018 17:05

Using Python and BeautifulSoup, pull top stories from Medium on the topic of your choice.

	# Get unlimited access to the smartest writers and biggest ideas by becoming
	# a Medium member for just $5 / month. Visit https://medium.com/membership

	import sys
	import requests
	from bs4 import BeautifulSoup

	# Build elements of url to get

	url = "https://medium.com/search?q=" # replace 'python' with the search keyword of your choice

AO8 / crawler.py

Last active May 23, 2023 09:12

Crawl a website and gather all internal links with Python and BeautifulSoup.

	# Adapted from example in Ch.3 of "Web Scraping With Python, Second Edition" by Ryan Mitchell

	import re
	import requests
	from bs4 import BeautifulSoup

	pages = set()

	def get_links(page_url):
	global pages

AO8 / it_enrollment_scraper.py

Last active October 26, 2020 23:37

IT enrollment Python web scraper. Includes GUI automation with pyautogui, scraping with BeautifulSoup, and sending email notifications with smtplib.

	# Standard Library
	import smtplib
	import webbrowser
	from time import sleep
	from datetime import datetime as dt
	from urllib.request import urlopen
	# Third-party
	import pyautogui
	from bs4 import BeautifulSoup

AO8 / bacon_crawler.py

Last active May 25, 2018 18:23

Using Python and BeautifulSoup, decipher untold connections to Kevin Bacon with this mesmerizing Wikipedia crawler.

	# Adapted from example in Ch.3 of "Web Scraping With Python, Second Edition" by Ryan Mitchell
	# Make a tax-deductible donation to the Wikimedia Foundation at https://wikimediafoundation.org/wiki/Ways_to_Give
	# Takeaway from this program: recursion is at the heart of web crawling. Crawlers retrieve page contents for a URL,
	# examine that page for another URL, and retrieve that page, ad infinitum

	import re
	import random
	import requests
	from bs4 import BeautifulSoup
	from datetime import datetime as dt

AO8 / dow_visualizer.py

Last active June 21, 2018 19:14

Use Python, Requests, BeautifulSoup, CSV Writer, and MatPlotLib to scrape, write, and visualize a day on the stock market.

	# From Python's Standard Library
	from time import sleep
	import datetime
	import csv
	# Third-party
	import requests
	import bs4
	import matplotlib.pyplot as plt

	times = []

AO8 / csv_dow_tracker.py

Created March 8, 2018 18:08

Dow Jones tracker re-written with Requests package. Scrape and write data to a CSV file using Python 3 and Beautiful Soup.

	import requests
	import csv
	import re
	from bs4 import BeautifulSoup
	from datetime import datetime as dt

	dow_jones_page = "https://www.bloomberg.com/quote/INDU:IND"
	html = requests.get(dow_jones_page).text
	soup = BeautifulSoup(html, "html.parser")

AO8 / cc_decrypt.py

Created March 3, 2018 23:57

Simple Caesar Cipher Python decryption function.

	import string
	from time import sleep

	alphabet = string.ascii_lowercase # "abcdefghijklmnopqrstuvwxyz"

	def decrypt():

	print("Welcome to Caesar Cipher Decryption.\n")
	encrypted_message = input("Enter the message you would like to decrypt: ").strip()
	print()

AO AO8