The XML:
<?xml version="1.0"?>
<pages>
<page>
<url>http://example.com/Labs</url>
<title>Labs</title>
<subpages>
<page>
<url>http://example.com/Labs/Email</url>
<title>Email</title>
<subpages>
<page>
<url>http://example.com/Labs/Email/How_to</url>
<title>How-To</title>
<subpages/>
</page>
<page>
<url>http://example.com/Labs/Social</url>
<title>Social</title>
</page>
<subpages/>
</page>
<page>
<url>http://example.com/Tests</url>
<title>Tests</title>
<subpages>
<page>
<url>http://example.com/Tests/Email</url>
<title>Email</title>
<subpages>
<page>
<url>http://example.com/Tests/Email/How_to</url>
<title>How-To</title>
<subpages/>
</page>
<page>
<url>http://example.com/Tests/Social</url>
<title>Social</title>
</page>
<subpages/>
</page>
</pages>
// rexml is the XML string read from a URL
from xml.etree import ElementTree as ET
tree = ET.fromstring(rexml)
for node in tree.iter('page'):
for url in node.iterfind('url'):
print url.text
for title in node.iterfind('title'):
print title.text.encode("utf-8")
print '-' * 30
http://example.com/article1
Article1
------------------------------
http://example.com/article1/subarticle1
SubArticle1
------------------------------
http://example.com/article2
Article2
------------------------------
http://example.com/article3
Article3
------------------------------
0
http://example.com/article1
Article1
------------------------------
1
http://example.com/article1/subarticle1
SubArticle1
------------------------------
0
http://example.com/article2
Article2
------------------------------
0
http://example.com/article3
Article3
------------------------------
Used lxml.html
.
import lxml.html
rexml = ...
def depth(node):
d = 0
while node is not None:
d += 1
node = node.getparent()
return d
tree = lxml.html.fromstring(rexml)
for node in tree.iter('page'):
print depth(node)
for url in node.iterfind('url'):
print url.text
for title in node.iterfind('title'):
print title.text.encode("utf-8")
print '-' * 30