Xpath数据解析

好段子网内容爬取

 1 from lxml import etree
 2 import requests
 3 url='http://www.haoduanzi.com'
 4 headers = {
 5         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36',
 6     }
 7 url_content=requests.get(url=url,headers=headers).text
 8 tree=etree.HTML(url_content)
 9 #xpath返回值是一个列表
10 div_list=tree.xpath('//div[@id="main"]/div')[2:-2]
11 ur_list=[]
12 for div in div_list:
13     img_url=div.xpath('./div/img/@src')[0]
14     ur_list.append(img_url)
15 print(ur_list)
爬虫代码

煎蛋网图片爬取

 1 from lxml import etree
 2 import requests
 3 import base64
 4 url="http://jandan.net/ooxx"
 5 headers = {
 6         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36',
 7     }
 8 url_content=requests.get(url=url,headers=headers).text
 9 # url_content
10 tree=etree.HTML(url_content)
11 img_list=tree.xpath('//span[@class="img-hash"]/text()')
12 img_so_list=[]
13 for imgcode in img_list:
14     img_url="http:"+base64.b64decode(imgcode).decode()
15     img_so_list.append(img_url)
16 img_so_list
爬虫代码

站长素材中进行免费简历模板的下载

 1 from lxml import etree
 2 import requests
 3 import random
 4 url = 'http://sc.chinaz.com/jianli/free_%d.html'
 5 headers = {
 6     'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'
 7     'Connection':'close'
 8 }
 9 
10 for pageNum in range(1,3):
11     pageUrl = format(url%pageNum)
12     if pageNum == 1:
13         pageUrl = 'http://sc.chinaz.com/jianli/free.html'
14     #page_text = requests.get(url=pageUrl,headers=headers).text
15     response = requests.get(url=pageUrl,headers=headers)
16     #将请求到的页面源码数据的编码格式进行指定的修改
17     response.encoding = 'utf-8'
18     page_text = response.text
19     #解析：简历的名称 详情页的url
20     tree = etree.HTML(page_text)
21     div_list = tree.xpath('//div[@id="container"]/div')
22     for div in div_list:
23         #存储谋一份建立的12个下载通道
24         download_list = []
25         
26         detail_url = div.xpath('./p/a/@href')[0]
27         title = div.xpath('./p/a/text()')[0]
28         
29         #获取详情页面的页面数据
30         detail_text = requests.get(url=detail_url,headers=headers).text
31         #一个etree对象只可以加载一个页面源码数据
32         tree = etree.HTML(detail_text)
33         #12个下载通道的url
34         li_list =  tree.xpath('//div[@class="clearfix mt20 downlist"]/ul[@class="clearfix"]/li')
35         for li in li_list:
36             download_url = li.xpath('./a/@href')[0]
37             download_list.append(download_url)
38         #从12个下载通道中随机选择某一个下载通道    
39         download_data_url = random.choice(download_list)
40         #简历模板的下载
41         data = requests.get(url=download_data_url,headers=headers).content
42         data_path = title+'.rar'
43         with open(data_path,'wb') as fp:
44             fp.write(data)
45             print(data_path+'下载成功')
爬虫代码

 

posted @ 2018-12-12 20:37  北伽  阅读(430)  评论(0)  编辑  收藏  举报