Download all items in a podcast.

download_podcast.py

#!/usr/bin/env python3

import datetime
import feedparser
import time
import os
import sys
from urllib.request import Request, urlopen

# Some hosts (i.e. Patreon) will deny requests with an HTTP 403
# if they appear to come from scripts; pretend to be Firefox.
USER_AGENT='Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:72.0) Gecko/20100101 Firefox/72.0'

# From http://stackoverflow.com/a/1160227
if sys.version_info < (3, 3):
    def touch(fname, mode=0o666, dir_fd=None, **kwargs):
        flags = os.O_CREAT | os.O_APPEND
        times = kwargs['times'] if 'times' in kwargs else None
        with os.fdopen(os.open(fname, flags, mode)) as f:
            os.utime(fname, times)
else:
    def touch(fname, mode=0o666, dir_fd=None, **kwargs):
        flags = os.O_CREAT | os.O_APPEND
        with os.fdopen(os.open(fname, flags=flags, mode=mode, dir_fd=dir_fd)) as f:
            os.utime(f.fileno() if os.utime in os.supports_fd else fname,
                dir_fd=None if os.supports_fd else dir_fd, **kwargs)

# From http://stackoverflow.com/a/7244263
def downloadFile(url, file_name):
    req = Request(url)
    req.add_header('User-Agent', USER_AGENT)
    # Download the file from `url` and save it locally under `file_name`:
    with urlopen(req) as response, open(file_name, 'wb') as out_file:
        data = response.read() # a `bytes` object
        out_file.write(data)

def getContentLength(url):
    print("Enclosure length mismatch. Checking content-length explicitly...")
    req = Request(url)
    req.add_header('User-Agent', USER_AGENT)
    with urlopen(req) as response:
        size = response.headers.get("content-length")
        return int(size) if size else 0

def downloadAll(feedURL):
    feed = feedparser.parse(feedURL)
    print("Processing feed %s..." % feed['feed']['title'])

    for post in reversed(feed.entries):
        print("Processing item %s... " % post.title, end="")

        if len(post.enclosures) != 1:
            print("Post has %d enclosures, not 1. Skipping post."
                    % len(post.enclosures))
        else:
            media = post.enclosures[0]
            mediaURL = media.href
            # cut the extension off the end to use in the filename
            mediaExt = mediaURL[mediaURL.rfind('.')+1:]
            quesPos = mediaExt.find('?')
            if quesPos != -1:
                mediaExt = mediaExt[:quesPos]
            mediaSize = int(media.length) # media.length is of type str

            filename = "%s.%s" % (post.title.replace('/', '_'), mediaExt)

            stat = os.stat(filename) if os.path.isfile(filename) else None
            if stat and stat.st_size > 0\
                    and (\
                            stat.st_size == mediaSize\
                            or mediaSize == 0\
                            or getContentLength(mediaURL) == stat.st_size # manually verify enclosure length; it might be wrong
                        ):
                print("File already downloaded. Skipping.")
            else:
                if stat and stat.st_size != mediaSize:
                    print("Incorrect file found. Redownloading... ", end="")
                    sys.stdout.flush()
                else:
                    print("Downloading... ", end="")
                    sys.stdout.flush()
                # Download the file...
                downloadFile(mediaURL, filename)
                print("Done.")

            # From http://stackoverflow.com/a/1697907
            pubTimestamp = time.mktime(post.published_parsed)

            # ... and set its created time to the publication time.
            touch(filename, times=(stat.st_atime if stat else pubTimestamp,
                                   pubTimestamp))

_feedURLfilename = ".podcast_source"

if __name__ == "__main__":
    # Remember the feed URL in a hidden file named _feedURLfilename
    #   Always use the command-line URL if given and remember it in that file.
    if len(sys.argv) == 2:
        feedURL = sys.argv[1]
        with open(_feedURLfilename, 'w') as feedURLfile:
            feedURLfile.write(feedURL)
    elif len(sys.argv) == 1 and os.path.isfile(_feedURLfilename):
        with open(_feedURLfilename, 'r') as feedURLfile:
            feedURL = feedURLfile.read()
    else:
        print("USAGE: %s feedURL" % sys.argv[0])
        sys.exit(1)

    downloadAll(feedURL)