Xpath解析:最常用且最便捷高效的一种解析方法
属性定位:
r=tree.xpath('//div[@class="song"]') #//是定位到div的
#@是定位到class属性
取属性值,网址链接
实例爬取58同城二手房信息
import requests
from lxml import etree
if __name__ == "__main__":
#爬取到页面源码数据
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:74.0) Gecko/20100101 Firefox/74.0'}
url='https://qd.58.com/ershoufang/?PGTID=0d100000-0007-a561-8676-fc901c0b0a3b&ClickID=2'
page_text=requests.get(url=url,headers=headers).text
#数据解析
tree=etree.HTML(page_text)
li_list=tree.xpath('//ul[@class="house-list-wrap"]/li')
fp=open('58.txt','w',encoding='utf-8')
#//表示从任意地方开始定位
for li in li_list:
title=li.xpath('./div[2]/h2/a/text()')[0]
print(title)
fp.write(title+'\n')
xpath 爬取图片
爬取图片
import requests
from lxml import etree
import os
if __name__ == "__main__":
#爬取到页面源码数据
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:74.0) Gecko/20100101 Firefox/74.0'}
url='http://pic.netbian.com/4kmeinv/'
res=requests.get(url=url,headers=headers)
res.encoding='gb2312'
page_text=res.text
#解析src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')
#里标签要循环
for li in li_list:
img_src='http://pic.netbian.com'+li.xpath('./a/img/@src')[0]
#局部解析要加.
img_name=li.xpath('./a/img/@alt')[0]+'.jpg'
#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!!!')