python - 属性错误: 'list' object has no attribute 'extract' ?

Question

我只想通过 xpath 从这个 url( http://www.tuniu.com/g3300/whole-nj-0/list-l1602-h0-i-j0_0/ ) 中提取信息。当我运行以下代码时，出现 AttributeError: 'list' object has no attribute 'extract'?我的模块导入是否错误或不匹配？

# -*- coding: utf-8 -*-

import urllib2
import sys
import lxml.html as HTML
reload(sys)
sys.setdefaultencoding("utf-8")


class spider(object):
    def __init__(self):
        print u'开始爬取内容'

def getSource(self, url):
    html = urllib2.Request(url)
    pageContent = urllib2.urlopen(html,timeout=60).read()
    return pageContent

def getUrl(self, pageContent):
    htmlSource = HTML.fromstring(pageContent)
    urlInfo = htmlSource.xpath('//dd[@class="tqs"]/span/a/@href').extract()[0]
    return urlInfo


if __name__ == "__main__":
    url = "http://www.tuniu.com/g3300/whole-nj-0/list-l1602-h0-i-j0_0/"
    tuniu = spider()
    tuniu.getUrl(url)

以下错误!

 Traceback (most recent call last):
 File "<stdin>", line 1, in <module>
 File "D:\anzhuang\Anaconda\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 682, in runfile
execfile(filename, namespace)
 File "D:\anzhuang\Anaconda\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 71, in execfile
exec(compile(scripttext, filename, 'exec'), glob, loc)
 File "D:/python/tuniu2/tuniu.py", line 34, in <module>
tuniu.getUrl(url)
 File "D:/python/tuniu2/tuniu.py", line 27, in getUrl
urlInfo = htmlSource.xpath('//dd[@class="tqs"]/span/a/@href').extract()[0]
 AttributeError: 'list' object has no attribute 'extract'

Answer 1

首先，使用 url 调用 getUrl。它不会获取 url 的内容。修改它以获取页面内容。

并且不需要extract。要获取 href，只需从返回的列表中获取一个项目即可。

def getUrl(self, url):
    pageContent = self.getSource(url)  # <---
    htmlSource = HTML.fromstring(pageContent)
    urlInfo = htmlSource.xpath('//dd[@class="tqs"]/span/a/@href')[0]
    return urlInfo