Web Scraping hipsters.tech inspirado no podcast #82 - Programar sem enxergar

podcast-scraping.py

#!/usr/bin/env python3
# -*- coding: UTF-8 -*-

# Web Scraping com BeautifulSoup para baixar ultimos 5 podcasts do hipsters.tech
# Inspirado no podcast: Programar sem enxergar - Hipsters #82 
# https://hipsters.tech/programar-sem-enxergar-hipsters-82/

import requests
from bs4 import BeautifulSoup
from time import time
from os import system

def catch_audio_link(url):
	soup = get_soup(url)
	link = soup.find('audio').source['src']
	return link[0:link.find('.mp3')+4]

def get_soup(url):
	page = requests.get(url).text
	return BeautifulSoup(page, 'html.parser')

print('Fazendo scraping na pagina: https://hipsters.tech ...')
inicio = time()
soup = get_soup('https://hipsters.tech')
links = soup.find_all('h1', attrs={'class': 'entry-title'}, limit=5)
urls = list(map(lambda link: link.a['href'], links))
audio_links = list(map(catch_audio_link, urls))
fim = time()

print("Tempo de scraping: {} segundos".format(int(fim - inicio)))
print('Baixando os 5 últimos podcasts...')
print('Pressione Ctrl+C para cancelar')

for mp3 in audio_links:
	print("\nBaixando: " + mp3)
	system('wget ' + mp3 + ' -q --show-progress')