文章目录
xpath基本概念
xpath解析：最常用且最便捷高效的一种解析方式。通用性强。
xpath解析原理
1.实例化一个etree的对象，且需要将被解析的页面源码数据加载到该对象中
2.调用etree对象中的xpath方法结合xpath表达式实现标签的定位和内容的捕获。
环境安装
pip install lxml
如何实例化一个etree对象：
from lxml import etree
1.将本地的html文件中的远吗数据加载到etree对象中：
etree.parse(filePath)
2.可以将从互联网上获取的原码数据加载到该对象中：
etree.HTML('page_text’)xpath('xpath表达式’)
- 属性定位：//div[@class='song'] tag[@attrName='attrValue']
- 索引定位：//div[@class='song']/p[3] 索引从1开始的
- //text()标签中非直系的文本内容（所有文本内容）
- 取属性：/@attrName ==>img/src
xpath爬取58二手房实例
爬取网址
https://xa.58.com/ershoufang/完整代码
from lxml import etree
import requests
if __name__ == '__main__':
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36'
}
url = 'https://xa.58.com/ershoufang/'
page_text = requests.get(url=url,headers=headers).text
tree = etree.HTML(page_text)
div_list = tree.xpath('//section[@class="list"]/div')
fp = open('./58同城二手房.txt','w',encoding='utf-8')
for div in div_list:
title = div.xpath('.//div[@class="property-content-title"]/h3/text()')[0]
print(title)
fp.write(title+'\n'+'\n')
xpath图片解析下载实例
爬取网址
https://pic.netbian.com/4kmeinv/完整代码
import requests,os
from lxml import etree
if __name__ == '__main__':
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36'
}
url = 'https://pic.netbian.com/4kmeinv/'
page_text = requests.get(url=url,headers=headers).text
tree = etree.HTML(page_text)
li_list = tree.xpath('//div[@class="slist"]/ul/li/a')
if not os.path.exists('./piclibs'):
os.mkdir('./piclibs')
for li in li_list:
detail_url ='https://pic.netbian.com' + li.xpath('./img/@src')[0]
detail_name = li.xpath('./img/@alt')[0]+'.jpg'
detail_name = detail_name.encode('iso-8859-1').decode('GBK')
detail_path = './piclibs/' + detail_name
detail_data = requests.get(url=detail_url, headers=headers).content
with open(detail_path,'wb') as fp:
fp.write(detail_data)
print(detail_name,'seccess!!')
xpath爬取全国城市名称实例
爬取网址
https://www./historydata/完整代码
import requests
from lxml import etree
if __name__ == '__main__':
url = 'https://www./historydata/'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36',
}
page_text = requests.get(url=url,headers=headers).content.decode('utf-8')
tree = etree.HTML(page_text)
#热门城市 //div[@class="bottom"]/ul/li
#全部城市 //div[@class="bottom"]/ul/div[2]/li
a_list = tree.xpath('//div[@class="bottom"]/ul/li | //div[@class="bottom"]/ul/div[2]/li')
fp = open('./citys.txt','w',encoding='utf-8')
i = 0
for a in a_list:
city_name = a.xpath('.//a/text()')[0]
fp.write(city_name+'\t')
i=i+1
if i == 6:
i = 0
fp.write('\n')
print('爬取成功')
xpath爬取简历模板实例
爬取网址
https://sc.chinaz.com/jianli/free.html完整代码
import requests,os
from lxml import etree
if __name__ == '__main__':
url = 'https://sc.chinaz.com/jianli/free.html'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36',
}
page_text = requests.get(url=url,headers=headers).content.decode('utf-8')
tree = etree.HTML(page_text)
a_list = tree.xpath('//div[@class="box col3 ws_block"]/a')
if not os.path.exists('./简历模板'):
os.mkdir('./简历模板')
for a in a_list:
detail_url = 'https:'+a.xpath('./@href')[0]
detail_page_text = requests.get(url=detail_url,headers=headers).content.decode('utf-8')
detail_tree = etree.HTML(detail_page_text)
detail_a_list = detail_tree.xpath('//div[@class="clearfix mt20 downlist"]/ul/li[1]/a')
for a in detail_a_list:
download_name = detail_tree.xpath('//div[@class="ppt_tit clearfix"]/h1/text()')[0]
download_url = a.xpath('./@href')[0]
download_data = requests.get(url=download_url,headers=headers).content
download_path = './简历模板/'+download_name+'.rar'
with open(download_path,'wb') as fp:
fp.write(download_data)
print(download_name,'success!!')
