Move iTunes code to feedify.py

morss/feedify.py

@@ -15,10 +15,12 @@ try:
     from ConfigParser import ConfigParser
     from urlparse import urlparse, urljoin
     from urllib2 import urlopen
+    from httplib import HTTPException
 except ImportError:
     from configparser import ConfigParser
     from urllib.parse import urlparse, urljoin
     from urllib.request import urlopen
+    from http.client import HTTPException
 
 try:
     basestring
@@ -95,12 +97,20 @@ def format_string(string, getter, error=False):
 
 
 def pre_worker(url):
-    if urlparse(url).netloc == 'itunes.apple.com':
+    if url.startswith('http://itunes.apple.com/') or url.startswith('https://itunes.apple.com/'):
         match = re.search('/id([0-9]+)(\?.*)?$', url)
         if match:
             iid = match.groups()[0]
-            redirect = 'https://itunes.apple.com/lookup?id={id}'.format(id=iid)
-            return redirect
+            redirect = 'https://itunes.apple.com/lookup?id=%s' % iid
+
+            try:
+                con = crawler.custom_handler(basic=True).open(redirect, timeout=4)
+                data = con.read()
+
+            except (IOError, HTTPException):
+                raise
+
+            return json.loads(data.decode('utf-8', 'replace'))['results'][0]['feedUrl']
 
     return None
 

morss/morss.py

@@ -7,7 +7,6 @@ import threading
 
 from fnmatch import fnmatch
 import re
-import json
 
 import lxml.etree
 import lxml.html
@@ -335,7 +334,7 @@ def FeedFetch(url, options):
     if isinstance(url, bytes):
         url = url.decode()
 
-    # do some useful facebook work
+    # allow for code execution for feedify
     pre = feedify.pre_worker(url)
     if pre:
         url = pre
@@ -357,12 +356,7 @@ def FeedFetch(url, options):
 
     contenttype = con.info().get('Content-Type', '').split(';')[0]
 
-    if url.startswith('https://itunes.apple.com/lookup?id='):
-        link = json.loads(xml.decode('utf-8', 'replace'))['results'][0]['feedUrl']
-        log('itunes redirect: %s' % link)
-        return FeedFetch(link, options)
-
-    elif re.match(b'\s*<?xml', xml) is not None or contenttype in crawler.MIMETYPE['xml']:
+    if re.match(b'\s*<?xml', xml) is not None or contenttype in crawler.MIMETYPE['xml']:
         rss = feeds.parse(xml)
 
     elif feedify.supported(url):