以XML格式从etree的单个元素获取文本

Question

下面的代码可以正常工作，但是没有任何python方法来获得相同的功能吗？ 我只想解析XML并从多个元素（name、name\u status、url）中获取文本。在

from lxml import etree
from urllib2 import urlopen

def ask_CoL(url):
    tree = etree.parse(urlopen(url))
    tn=[ el.get('total_number_of_results') for el in tree.iter('results') ]
    try:
        nr = int(tn[0])
    except ValueError:
        nr = 0
    if nr == 1:
        newstr = str([ el.text for el in tree.getiterator(tag='name')])\
                                             .strip("[]'")+','\
                +str([ el.text for el in tree.getiterator(tag='name_status')])\
                                             .strip("[]'")+','\
                +str([ el.text for el in tree.getiterator(tag='url')])\
                                             .strip("[]'")+'\n'
    else:
        newstr = 'NA\n'
    return newstr

XML示例：

^{pr2}$

Answer 1

您可以简化接口和实现：

import urllib2
from xml.etree import cElementTree as etree

def f(url):
    tree = etree.parse(urllib2.urlopen(url))         
    el = tree.find('results')
    if el is not None:
       lst = [el.findtext(tag) or '' for tag in "name name_status url".split()]
       return ','.join(lst)