Python大数据之使用lxml库解析html网页文件示例

from lxml import etree
dom = etree.HTML(html)

dom.xpath(.//a/@href)

dom.xpath(".//a/text()")

#!/usr/bin/python
# -*- coding:utf-8 -*-
from scrapy.spiders import Spider
from lxml import etree
from jredu.items import JreduItem
class JreduSpider(Spider):
  name = 'tt' #爬虫的名字，必须的，唯一的
  allowed_domains = ['sohu.com']
  start_urls = [
    'http://www.sohu.com'
  ]
  def parse(self, response):
    content = response.body.decode('utf-8')
    dom = etree.HTML(content)
    for ul in dom.xpath("//div[@class='focus-news-box']/div[@class='list16']/ul"):
      lis = ul.xpath("./li")
      for li in lis:
        item = JreduItem() #定义对象
        if ul.index(li) == 0:
          strong = li.xpath("./a/strong/text()")
          li.xpath("./a/@href")
          item['title']= strong[0]
          item['href'] = li.xpath("./a/@href")[0]
        else:
          la = li.xpath("./a[last()]/text()")
          item['title'] = la[0]
          item['href'] = li.xpath("./a[last()]/href")[0]
        yield item