Morse Sample Scraper

scrape_morse.py

from bs4 import BeautifulSoup
import requests
import os

def fetch(url):
	if (url[0:4] != "http"):
		url = 'http://www.arrl.org'+url
	fname = url.split("/")[-1]
	print("Fetching [{}] from {}".format(fname, url))
	if os.path.isfile(fname):
		print("\tCached.")
		return
	res = requests.get(url)
	if not res.ok:
		print("\tERROR")
		return
	with open(fname, 'wb') as f:
		for block in res.iter_content(1024):
			f.write(block)

def getSamples(speed):
	r = requests.get('http://www.arrl.org/{}-wpm-code-archive'.format(speed))
	soup = BeautifulSoup(r.text, 'html.parser')
	mp3s = []
	transcripts = []
	for a in soup.find_all('a'):
		if (a.get('href') and a.get('href')[-3:]=='mp3'):
			fetch(a.get('href'))
			text = a.find_parent('td').find_next_sibling().find('a').get('href')
			fetch(text)


for n in ['5', '7-5', '10', '13', '15', '20', '25', '30', '35', '40']:
	getSamples(n)