网站实战

注意以上两图红色部分以及运行结果的区别,附源代码如下:

import requests
from lxml import etree
url = 'http://weekend.ctrip.com/around/'
response = requests.get(url)
html = response.content.decode()
html = etree.HTML(html)
divs = html.xpath('//div[@class="wc_link_title"]')
for div in divs:
    title = div.xpath('a/text()')[0]
    url_l = 'http://weekend.ctrip.com' + div.xpath('a/@href')[0]
    response = requests.get(url_l)
    html = response.content.decode()
    html = etree.HTML(html)
    divs = html.xpath('//div[@class="product_m"]')
    for div in divs:
         title = div.xpath('h2/a/text()')[0]
         href = div.xpath('h2/a/@href')[0]
         print(title, href)