【老男孩】爬虫学习笔记P24-P25Xpath解析基础-2xpath实战 58二手房

P24Xpath解析基础-2

#!/usr/bin/env python 
# -*- coding:utf-8 -*-
from lxml import etree
if __name__ == "__main__":
    #实例化好了一个etree对象，且将被解析的源码加载到了该对象中
    tree = etree.parse('test.html')
    # r = tree.xpath('/html/body/div')
    # r = tree.xpath('/html//div')
    # r = tree.xpath('//div')
    # r = tree.xpath('//div[@class="song"]')
    # r = tree.xpath('//div[@class="tang"]//li[5]/a/text()')[0]
    # r = tree.xpath('//li[7]//text()')
    # r = tree.xpath('//div[@class="tang"]//text()')
    r = tree.xpath('//div[@class="song"]/img/@src')





    print(r)

索引从1开始的

P25-xpath实战 58二手房

#!/usr/bin/env python 
# -*- coding:utf-8 -*-
import requests
from lxml import etree
#需求：爬取58二手房中的房源信息
if __name__ == "__main__":
    headers = {
    
    
        'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'
    }
    #爬取到页面源码数据
    url = 'https://bj.58.com/ershoufang/'
    page_text = requests.get(url=url,headers=headers).text

    #数据解析
    tree = etree.HTML(page_text)
    #存储的就是li标签对象
    li_list = tree.xpath('//ul[@class="house-list-wrap"]/li')
    fp = open('58.txt','w',encoding='utf-8')
    for li in li_list:
        #局部解析
        title = li.xpath('./div[2]/h2/a/text()')[0]
        print(title)
        fp.write(title+'\n')

#!/usr/bin/env python 
# -*- coding:utf-8 -*-
#需求：解析下载图片数据 http://pic.netbian.com/4kmeinv/
import requests
from lxml import etree
import os
if __name__ == "__main__":
    url = 'http://pic.netbian.com/4kmeinv/'
    headers = {
    
    
        'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'
    }
    response = requests.get(url=url,headers=headers)
    #手动设定响应数据的编码格式
    # response.encoding = 'utf-8'
    page_text = response.text

    #数据解析：src的属性值  alt属性
    tree = etree.HTML(page_text)
    li_list = tree.xpath('//div[@class="slist"]/ul/li')


    #创建一个文件夹
    if not os.path.exists('./picLibs'):
        os.mkdir('./picLibs')

    for li in li_list:
        img_src = 'http://pic.netbian.com'+li.xpath('./a/img/@src')[0]
        img_name = li.xpath('./a/img/@alt')[0]+'.jpg'
        #通用处理中文乱码的解决方案
        img_name = img_name.encode('iso-8859-1').decode('gbk')

        # print(img_name,img_src)
        #请求图片进行持久化存储
        img_data = requests.get(url=img_src,headers=headers).content
        img_path = 'picLibs/'+img_name
        with open(img_path,'wb') as fp:
            fp.write(img_data)
            print(img_name,'下载成功！！！')