python2 spider 豆瓣电视剧

直接上代码，第一种方式获取不到数据。

#.*-coding:utf-8-*-
import requests
import re
import sys
reload(sys)
sys.setdefaultencoding("utf-8")
from lxml import etree

class spider(object):

    # 获取url对应的网页源码
    def getsource(self,url):
        headers = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:52.0) Gecko/20100101 Firefox/52.0'}
        source = requests.get(url, headers=headers)
        return source.text

    def getNeedInfo(self,sourceHtml):
        selector = etree.HTML(sourceHtml)
        print selector
        result = etree.tostring(selector)
        #print(result.decode("utf-8"))
        fd = open("result.txt", "w")
        fd.write(result.decode("utf-8"))
        fd.close()

        html_title = selector.xpath('//a[@class="item"]/div[@class="cover-wp"]/img//@alt')
        print html_title
        ht