Last active
November 5, 2018 18:48
Star
You must be signed in to star a gist
Python 3 code to archive franceculture.com radio shows as "YYYY-MM-DD-FRCULTURE-[Show] - [Title].mp3" files; usage: frculture <URL>. Only one URL at a time for now, and no progress bar, but downloads are usually very quick.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# !/usr/local/bin/python3 | |
# coding: utf8 | |
from bs4 import BeautifulSoup # pip install BeautifulSoup4 | |
import os | |
import re | |
import sys | |
import urllib.request | |
u = sys.argv[1] | |
p = BeautifulSoup(urllib.request.urlopen(u), 'html.parser') | |
# compose filename | |
# ---------------- | |
# part of page to scrape | |
b = p.find('button', attrs = {'class': 'replay-button'}) | |
# show title | |
t = b.get('title').strip().replace('Réécouter ', '') | |
t = re.sub(':|/', '-', t) | |
# show name | |
n = b.get('data-asset-surtitle') | |
# show date | |
d = b.get('data-asset-source') | |
d = re.sub('(.*?)(\d{2}).(\d{2}).(\d{4})(.*)', '\\4-\\3-\\2', d) | |
# filename | |
f = d + "-FRCULTURE-" + n + " - " + t + '.mp3' | |
# get URL | |
# ------- | |
# show file (.mp3) | |
u = b.get('data-asset-source') | |
print('[<<] ' + u) | |
print('[>>] ' + f) | |
print('[in] ' + os.getcwd()) | |
# download | |
# -------- | |
h = urllib.request.urlopen(u) | |
with open(f, 'wb') as output: | |
output.write(h.read()) | |
# kthxbye |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment