Last active
March 13, 2019 12:27
-
-
Save AvverbioPronome/a5935deaa253d9f073c7f2126fcfcecc to your computer and use it in GitHub Desktop.
download a whole season from raiplay.it
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/bin/env python3 | |
# USAGE: | |
# $ ./downloader.py http://www.raiplay.it/programmi/*/puntate | youtube-dl -a - | |
import sys | |
import requests | |
import bs4 | |
from urllib.parse import urljoin | |
# TODO: (better, selective) Exception handling | |
def error(message, code=1): | |
print (message, file=sys.stderr) | |
exit(code) | |
if len(sys.argv) > 1: | |
pages = sys.argv[1:] | |
else: | |
pages = [x.rstrip() for x in sys.stdin] | |
for page in pages: | |
try: | |
req = requests.get(page) | |
req.raise_for_status() | |
except Exception as e: | |
error("Problem downloading your page.\n{}".format(e)) | |
try: | |
html = req.text | |
soup = bs4.BeautifulSoup(html, 'lxml') | |
tags = soup.select(".puntateItem a") | |
if len(tags) == 0: | |
tags = soup.select("a.singleVodUrl") | |
except Exception as e: | |
error("Problem parsing HTML.\n{}".format(e)) | |
if len(tags) > 0: | |
for tag in tags: | |
print ("{}".format(urljoin(page, tag.attrs['href']))) | |
else: | |
error("No episodes detected at this address.") | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment