Fetch most recent N files for each feed if they aren'y already downloaded

autoradio/autoradio.py

@@ -4,6 +4,7 @@ import argparse
 import json
 import pycurl
 import subprocess
+import sys
 from pathlib import Path
 import traceback
 
@@ -13,7 +14,7 @@ def download_audio(link, destdir):
     ptarget = Path(destdir) / Path(parts[-1])
     target = ptarget.resolve()
     if target.exists():
-        print("File already exists, skipping")
+        print(f"File {target} already downloaded, skipping")
     else:
         with open(target, "wb") as fp:
             curl = pycurl.Curl()
@@ -21,7 +22,7 @@ def download_audio(link, destdir):
             curl.setopt(pycurl.FOLLOWLOCATION, 1)
             curl.setopt(pycurl.MAXREDIRS, 5)
             curl.setopt(pycurl.CONNECTTIMEOUT, 30)
-            curl.setopt(pycurl.TIMEOUT, 300)
+            curl.setopt(pycurl.TIMEOUT, 3000)
             curl.setopt(pycurl.NOSIGNAL, 1)
             curl.setopt(pycurl.WRITEDATA, fp)
             try:
@@ -39,14 +40,14 @@ def looks_audio(link):
     return False
 
 
-def get_latest(url, dir):
+def get_latest(url, dir, max):
     d = feedparser.parse(url)
     title = d.feed.get('title', "[no title]")
     entries = d.get('entries', [])
-    if entries:
-        latest = entries[0]
-        if 'links' in latest:
-            sounds = [ l for l in latest['links'] if looks_audio(l) ]
+    urls = []
+    for entry in entries[:max]:
+        if 'links' in entry:
+            sounds = [ l for l in entry['links'] if looks_audio(l) ]
             if len(sounds) < 0:
                 print("No audio links")
             if len(sounds) > 1:
@@ -54,8 +55,8 @@ def get_latest(url, dir):
             for s in sounds:
                 audio_url = s.get('href', '')
                 if audio_url:
-                    return audio_url
-    return None
+                    urls.append(audio_url)
+    return urls 
 
 def main():
     ap = argparse.ArgumentParser("autoradio - download audio from RSS feeds")
@@ -68,10 +69,11 @@ def main():
     args = ap.parse_args()
     with open(args.config, 'r') as cfh:
         cf = json.load(cfh)
+        m = int(cf.get("max", "5"))
         for name, config in cf['feeds'].items():
             print(f"Checking {name}")
-            url = get_latest(config['url'], config['dir'])
-            if url:
+            urls = get_latest(config['url'], config['dir'], m)
+            for url in urls:
                 print(f"content = {url}")
                 download_audio(url, config['dir'])
 

config.json

@@ -2,11 +2,12 @@
 	"feeds": {
 		"Utility Fog": {
 			"url": "https://www.frogworth.com/utilityfog/feed/",
-			"dir": "./output/UFog"
+			"dir": "/media/pi/Storage/Music/Utility Fog"
 		},
 		"RA Podcast": {
 			"url": "https://ra.co/xml/podcast.xml",
-			"dir": "./output/RA"
-		}
+			"dir": "/media/pi/Storage/Music/RA_Podcast"
 		}
+	},
+	"max": 10
 }

pyproject.toml

@@ -6,7 +6,7 @@ authors = ["Mike Lynch <m.lynch@sydney.edu.au>"]
 readme = "README.md"
 
 [tool.poetry.dependencies]
-python = "^3.9"
+python = "^3.7"
 feedparser = "^6.0.10"
 
 [tool.poetry.scripts]