Last active
October 25, 2016 15:04
-
-
Save jameslyons/8468367 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import urllib | |
from xml.etree.ElementTree import parse | |
URL = '''http://jameslyons0.blogspot.com.au/feeds/posts/default?max-results=9999''' | |
xml = parse(urllib.urlopen(URL)).getroot() | |
info = {} | |
for post in xml.getchildren(): | |
if post.tag=='{http://www.w3.org/2005/Atom}entry': | |
headers,title,link=[],None,None | |
for entry in post.getchildren(): | |
if entry.tag=='{http://www.w3.org/2005/Atom}category': | |
headers.append(entry.attrib['term']) | |
if entry.tag=='{http://www.w3.org/2005/Atom}title': | |
title = entry.text | |
if entry.tag=='{http://www.w3.org/2005/Atom}link': | |
link = entry.attrib['href'] | |
for h in headers: | |
if h not in info: info[h] = [(title,link)] | |
else: info[h].append((title,link)) | |
for label in info.keys(): | |
print "<h2>",label,"</h2>" | |
for title,link in info[label]: | |
print '<a href="',link,'">',title,'</a><br />' | |
print '<br />' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment