Last active
August 29, 2015 13:56
-
-
Save marktyers/8943106 to your computer and use it in GitHub Desktop.
#python code showing how to parse an RSS feed using the DOM #321COM
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
| from xml.dom.minidom import parseString, Node | |
| import urllib | |
| # http://www.highways.gov.uk/news/connect/rss-feeds/traffic-information-rss-feeds/ | |
| url = 'http://hatrafficinfo.dft.gov.uk/feeds/rss/CurrentAndFutureEvents/West%20Midlands.xml' | |
| f = urllib.urlopen(url) | |
| xml = f.read() | |
| xmldoc = parseString(xml) | |
| #print xmldoc.toprettyxml() | |
| #print xmldoc | |
| title = xmldoc.getElementsByTagName('channel')[0].getElementsByTagName('description')[0] | |
| print '====================================================' | |
| print title.firstChild.nodeValue | |
| print '====================================================' | |
| items = xmldoc.getElementsByTagName('item') | |
| print '----------------------------------------------------' | |
| for item in items: | |
| category = item.getElementsByTagName('category')[0] | |
| description = item.getElementsByTagName('description')[0] | |
| #print description.toprettyxml() | |
| print category.firstChild.nodeValue | |
| print description.firstChild.nodeValue | |
| print '----------------------------------------------------' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Loads entire XML feed into a single DOM object. Not suitable for huge XML datasets. You should use a SAX approach if the dataset is huge otherwise you will run out of memory...