随笔- 79 文章- 0 评论- 2 阅读- 35622

xpath基础

 1 #!/usr/bin/env python
 2 # -*- coding:utf-8 -*-
 3 # Author:woshinidaye
 4 
 5 #xpath是在XML文档中搜索内蒙的一门语言，html是xml的一个子集
 6 #安装lxml模块 pip install lxml
 7 
 8 
 9 from lxml import html
10 etree = html.etree
11 a = '''
12 <note>
13     <to>George</to>
14     <from>John</from>
15     <author>
16         <nick id='1'>abc</nick>
17         <nick id='2'>def</nick>
18         <nick id='3'>ghi</nick>
19         <div>
20             <nick id='4'>qwe</nick>
21         </div>
22         <span>
23             <nick id='5'>qwe12313</nick>
24             <pan>
25                 <nick id='6'>6666</nick>
26             </pan>
27         </span>
28     </author>
29     <heading>Reminder</heading>
30     <body>Don't forget the meeting!</body>
31 </note>
32 '''
33 
34 # tree = etree.parse('b.html')
35 tree = etree.XML(a)
36 # res = tree.xpath('/note')             #/表示层级关系，表示从根节点查找
37 # res = tree.xpath('/note/from')             #/表示层级关系
38 # res = tree.xpath('/note/from/text()')             #text()是那from下面的内容
39 # res = tree.xpath('/note/author/nick/text()')        #这样没法拿到div下的nick获取到，
40 # res = tree.xpath('/note/author/*/nick/text()')          #*可以代替author下的任何一个节点，通配符
41 # res = tree.xpath('/note/author//nick/text()')                   #//就表示所有author下的所有nick
42 # res = tree.xpath('/note/author/nick[1]/text()')         #编号从1开始！！！！[]索引
43 # res = tree.xpath(r'/note/author/nick[@id="2"]/text()')       #类似于BeautifulSoup中确定标签，这里用@id=sss来表示标签
44 res = tree.xpath('/note/author/nick/@id')               #@XXXX   获取属性值
45 for i in res:
46     print(i)
47 
48 
49 #提取页面源代码
50 #提取数据
51 '''
52 from lxml import html
53 import requests,csv
54 etree = html.etree
55 url = 'https://chengdu.zbj.com/search/f/?kw=SAAS'
56 header = {
57 "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36"
58 }
59 rep = requests.get(url=url,headers=header)
60 # print(rep.text)
61 html = etree.HTML(rep.text)   #解析
62 divs = html.xpath('/html/body/div[6]/div/div/div[2]/div[5]/div[1]/div')
63 with open('1128.txt','a+',encoding='utf-8',newline='') as f :
64     for div in divs:    #拿到每一个服务商的信息
65         service_price = div.xpath('./div/div/a[2]/div[2]/div[1]/span/text()')[0]
66         service_title = 'SAAS'.join(div.xpath('./div/div/a[2]/div[2]/div[2]/p/text()'))         #拼接
67         company = div.xpath('./div/div/a[1]/div[1]/p/text()')[1].strip()
68         a = [company,service_title,service_price]
69         csvwriter = csv.writer(f)
70         csvwriter.writerow(a)
71 print('done!!')
72 '''