From ec70a49352a7d26e8667ade920102cadec99f7d1 Mon Sep 17 00:00:00 2001
From: Sven Slootweg <jamsoftgamedev@gmail.com>
Date: Sun, 3 Jun 2012 01:30:31 +0200
Subject: [PATCH] Initial commit

---
 jamendoparser.py | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)
 create mode 100644 jamendoparser.py

diff --git a/jamendoparser.py b/jamendoparser.py
new file mode 100644
index 0000000..9ce7cd0
--- /dev/null
+++ b/jamendoparser.py
@@ -0,0 +1,30 @@
+import urllib, gzip
+from lxml import etree
+
+xml_url = "http://img.jamendo.com/data/dbdump_artistalbumtrack.xml.gz"
+xml_path = "dump.xml.gz"
+
+def update_progress(count, blocksize, totalsize):
+	percent = int(count * blocksize * 100 / totalsize)
+	sys.stdout.write("\r%2d%%" % percent)
+	sys.stdout.flush()
+
+def fast_iter(context, func):
+	# http://www.ibm.com/developerworks/xml/library/x-hiperfparse/
+	# Author: Liza Daly
+	for event, elem in context:
+		func(elem)
+		elem.clear()
+		while elem.getprevious() is not None:
+			del elem.getparent()[0]
+	del context
+
+def process_element(elem):
+	print elem.xpath( 'description/text( )' )
+
+print "Retrieving Jamendo database..."
+urllib.urlretrieve(xml_url, xml_file, reporthook=update_progress)
+
+exit(0)
+context = etree.iterparse( MYFILE, tag='item' )
+fast_iter(context,process_element)