python实战之爬取喜玛拉雅专辑信息

import urllib.request
import json
from lxml import etree

url='http://www.ximalaya.com/dq/8.ajax'
headers ={    
    "User-Agent":'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
}
req = urllib.request.Request(url, headers= headers)
response = urllib.request.urlopen(req)
jsonobj=json.loads(response.read().decode('utf-8'))
html=jsonobj['html']
xml= etree.HTML(html)
nodeList = xml.xpath('//div[@class="discoverAlbum_item"]')
for node in nodeList:
    img=node.xpath('.//img/@src')
    print(img[0],end='\t')
    title=node.xpath('.//img/@alt')
    print(title[0],end='\t')
    href = node.xpath('./a/@href')
    print(href[0],end='\t')

采用xpath解析html