18 lines
622 B
Python
18 lines
622 B
Python
|
from urllib.request import urlopen
|
|||
|
|
from xml.etree.ElementTree import parse
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
u = urlopen('http://planet.python.org/rss20.xml')
|
|||
|
|
# 使用xml.etree.ElementTree的parse方法来解析文档
|
|||
|
|
doc = parse(u)
|
|||
|
|
print(doc)
|
|||
|
|
|
|||
|
|
# 可以使用.iterfind来对解析出来的文档进行迭代，找到所有指定名称的节点
|
|||
|
|
for item in doc.iterfind('channel/item'):
|
|||
|
|
# 使用findtext在节点中寻找需要的数据
|
|||
|
|
title = item.findtext('title')
|
|||
|
|
date = item.findtext('pubDate')
|
|||
|
|
link = item.findtext('link')
|
|||
|
|
|
|||
|
|
print(title, date, link, sep="\n")
|