我的第一个python脚本

Posted 2021-02-25

import urllib2
import xml.dom.minidom
 
source = urllib2.urlopen('http://www.bbc.co.uk/')
#data = repr(source.read());
 
doc = xml.dom.minidom.parse(source)
 
all = doc.getElementsByTagName("h3")
 
for h3 in all :
	parent = h3.parentNode
	if (parent.getAttribute("id") == "promo_area"):
		child = h3.childNodes[1]
		child = child.childNodes[2]
		print ("\nPresent Headline : ")
		print (child.data+ "\n")