python 第二周（第八天） 我的python成长记 一个月搞定python数据挖掘！(14)

Posted 2020-09-30 yugengde

from lxml import etree

doubanhtml = ‘‘‘‘‘‘
doc = etree.fromstring(doubanhtml)

for eachbook in doc.xpath(‘//dl/dd‘):
    bookname = eachbook.xpath(‘a/text()‘)[0]
    bookurl = eachbook.xpath(‘a/@href‘)[0]
    pub = eachbook.xpath(‘div[@class="desc"]/text()‘)[0]
    rate = eachbook.xpath(‘div[@class="rating"]/span[@class="rating_nums"]/text()‘)[0]
    print bookname,bookurl,pub,rate