解析加密数据

解析加密数据

• 对一个新的网站进行爬取之前，首先要确定即将要进行爬取的数据是否为动态加载！

• 解析加密数据

  #需求：解析图片数据  
  import requests
  from lxml import etree
  import base64
  from urllib import request
  
  headers = {
      'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36'
  }
  url = 'http://******.net/ooxx/page-62#comments'
  page_text = requests.get(url=url,headers=headers).text
  
  #解析图片的密文
  tree = etree.HTML(page_text)
  code_list = tree.xpath('//span[@class="img-hash"]/text()')
  for code in code_list:
      # base64.b64decode(code).decode() 数据解密
      img_url ='http:' + base64.b64decode(code).decode()
      imgName = img_url.split('/')[-1]
      request.urlretrieve(img_url,imgName)
      print(imgName,'下载成功！！！')
  

• 爬取 模板信息

# 爬取某素材网站中的免费建立模板
import requests
from lxml import etree
import random

headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36',
    'Connection':'close'
}
url_page_one = 'http://sc.******.com/jianli/free.html'

#定制了一个通用的url模板
url_demo = 'http://sc.******.com/jianli/free_%d.html'
start_page = int(input('enter a start page num:'))
end_page = int(input('enter a end page num:'))

for pageNum in range(start_page,end_page+1):
    if pageNum == 1:
        url = url_page_one
    else:
        url = format(url_demo%pageNum)
        
    response = requests.get(url=url,headers=headers)
    response.encoding = 'utf-8'
    page_text = response.text

    #解析：简历详情页的url,和名称
    tree = etree.HTML(page_text)
    div_list = tree.xpath('//div[@id="container"]/div')
    for div in div_list:
        name = div.xpath('./p/a/text()')[0]
        detail_url = div.xpath('./p/a/@href')[0]
        #对详情页的url发起请求，获取详情页的源码数据
        detail_page_text = requests.get(url=detail_url,headers=headers).text
        #对详情页的源码数据进行解析：下载地址对应的url
        tree = etree.HTML(detail_page_text)
        li_list = tree.xpath('//div[@class="clearfix mt20 downlist"]/ul/li')
        #随机选取一个li标签（li标签中包含了下载地址的url）
        li = random.choice(li_list)
        download_url = li.xpath('./a/@href')[0]
        #进行简历数据的下载
        data = requests.get(url=download_url,headers=headers).content
        name = name+'.rar'
        with open(name,'wb') as fp:
            fp.write(data)
        print(name,'下载成功！')