From 09e606af22c50eb7b42b9e40acf2a644964e96de Mon Sep 17 00:00:00 2001
From: lost <root@negativezero.link>
Date: Fri, 23 Jul 2021 00:00:00 +0000
Subject: [PATCH] Add Apple Podcasts.

---
 scripts/determine_site.py            |  2 ++
 scripts/extractors/apple_podcasts.py | 37 ++++++++++++++++++++++++++++
 tests/apple_podcasts.txt             |  2 ++
 3 files changed, 41 insertions(+)
 create mode 100644 scripts/extractors/apple_podcasts.py
 create mode 100644 tests/apple_podcasts.txt

diff --git a/scripts/determine_site.py b/scripts/determine_site.py
index 1f7eb97..83af2aa 100644
--- a/scripts/determine_site.py
+++ b/scripts/determine_site.py
@@ -1,6 +1,8 @@
 #!/usr/bin/python3
 
 supported_sites = {
+	"apple_podcasts" : [ "podcasts.apple.com" ],
+
 	"castro_fm" : ["castro.fm"],
 
 	"chirbit" : [
diff --git a/scripts/extractors/apple_podcasts.py b/scripts/extractors/apple_podcasts.py
new file mode 100644
index 0000000..dd65690
--- /dev/null
+++ b/scripts/extractors/apple_podcasts.py
@@ -0,0 +1,37 @@
+#!/usr/bin/python3
+
+from utils import *
+from download_page import download
+
+# portable code to get filename
+import os
+platform = os.path.basename(__file__)
+if platform.endswith(".py"):
+	platform = platform[:(-3)]
+
+def extract_from_page (page, verbosity):
+	feed_url = search (page, '"feedUrl":"', '"')
+	if not feed_url is None:
+		return feed_url
+
+def extract (url, page=None, network=False, verbosity=3, args={}):
+	notify ("Unable to get feed from URL alone", verbosity, platform)
+	if network == True:
+		# the format is like
+		# https://podcasts.apple.com/us/podcast/the-api-academy-podcast/id1171911720
+		# and we want the number after domain/country/podcast/name/id
+		# in this example, 1171911720
+		podcast_id = url[url.find("/podcast/")+len("/podcast/"):]
+		podcast_id = podcast_id[podcast_id.find("/id")+len("/id"):]
+		# strip stuff from end
+		for symbol in ["/", "?", "&", ";"]:
+			if symbol in podcast_id:
+				podcast_id = podcast_id[:podcast_id.index(symbol)]
+		query_url = "https://itunes.apple.com/lookup?entity=podcast&id=" + podcast_id
+
+		# Apple API query about podcast (returns JSON object)
+		debug ("Querying Apple API for " + podcast_id + "...", verbosity, platform)
+		page = download (platform, query_url, args, verbosity)
+		feed = extract_from_page (page, verbosity)
+		if not feed is None:
+			return feed
diff --git a/tests/apple_podcasts.txt b/tests/apple_podcasts.txt
new file mode 100644
index 0000000..ba9cd7a
--- /dev/null
+++ b/tests/apple_podcasts.txt
@@ -0,0 +1,2 @@
+https://podcasts.apple.com/us/podcast/the-api-academy-podcast/id1171911720 https://feeds.soundcloud.com/users/soundcloud:users:262261799/sounds.rss
+https://podcasts.apple.com/us/podcast/darknet-diaries/id1296350485 https://feeds.megaphone.fm/darknetdiaries