python利用xpath爬取网上数据并存储到django模型中


Posted in Python onFebruary 26, 2021

帮朋友制作一个网站,需要一些产品数据信息,因为是代理其他公司产品,直接爬取代理公司产品数据

1.设计数据库

from django.db import models
from uuslug import slugify
import uuid
import os


def products_directory_path(instance, filename):
  ext = filename.split('.')[-1]
  filename = '{}.{}'.format(uuid.uuid4().hex[:8], ext)
  # return the whole path to the file
  return os.path.join('images', "products", instance.title, filename)


def product_relatedimage_directory_path(instance, filename):
  ext = filename.split('.')[-1]
  filename = '{}.{}'.format(uuid.uuid4().hex[:8], ext)
  # return the whole path to the file
  return os.path.join('images', "product_relatedimage", instance.product.title, filename)


class ProductsCategory(models.Model):
  """产品分类"""
  name = models.CharField('产品分类名', max_length=80, unique=True)
  description = models.TextField('产品分类描述', blank=True, null=True)
  slug = models.SlugField('slug', max_length=80, blank=True, null=True)
  parent_category = models.ForeignKey('self', verbose_name="父级分类", blank=True, null=True, on_delete=models.CASCADE)

  def save(self, *args, **kwargs):
    if not self.id or not self.slug:
      self.slug = slugify(self.name)
    super().save(*args, **kwargs)

  def __str__(self):
    return self.name

  class Meta:
    ordering = ['name']
    verbose_name = "产品分类"
    verbose_name_plural = verbose_name


class ProductsTag(models.Model):
  """产品标签"""
  name = models.CharField('产品标签名', max_length=30, unique=True)
  slug = models.SlugField('slug', max_length=40)

  def __str__(self):
    return self.name

  def save(self, *args, **kwargs):
    if not self.id or not self.slug:
      self.slug = slugify(self.name)
    super().save(*args, **kwargs)

  class Meta:
    ordering = ['name']
    verbose_name = "产品标签"
    verbose_name_plural = verbose_name


class Product(models.Model):
  title = models.CharField('标题', max_length=255, unique=True)
  slug = models.SlugField('slug', max_length=255, blank=True, null=True)
  jscs = models.TextField('技术参数', blank=True, null=True)
  image = models.ImageField(upload_to=products_directory_path, verbose_name="产品图片")
  views = models.PositiveIntegerField('浏览量', default=0)
  category = models.ForeignKey('ProductsCategory', verbose_name='分类', on_delete=models.CASCADE, blank=True, null=True)
  tags = models.ManyToManyField('ProductsTag', verbose_name='标签集合', blank=True)

  def save(self, *args, **kwargs):
    if not self.id or not self.slug:
      self.slug = slugify(self.title)
    super().save(*args, **kwargs)

  def update_views(self):
    self.views += 1
    self.save(update_fields=['views'])

  def get_pre(self):
    return Product.objects.filter(id__lt=self.id).order_by('-id').first()

  def get_next(self):
    return Product.objects.filter(id__gt=self.id).order_by('id').first()

  def __str__(self):
    return self.title

  class Meta:
    verbose_name = "产品"
    verbose_name_plural = verbose_name


class ProductAdvantage(models.Model):
  content = models.TextField('产品优势', blank=True, null=True)
  product = models.ForeignKey(Product, on_delete=models.CASCADE, blank=True, null=True)

  def __str__(self):
    return self.content

  class Meta:
    verbose_name = "产品优势"
    verbose_name_plural = verbose_name


class ProductBody(models.Model):
  body = models.CharField('产品内容', max_length=256, blank=True, null=True)
  product = models.ForeignKey(Product, on_delete=models.CASCADE, blank=True, null=True)

  def __str__(self):
    return self.product.title

  class Meta:
    verbose_name = "产品内容"
    verbose_name_plural = verbose_name

2.脚本编写

2.1编写获取网页源代码函数

def get_one_page(url):
  try:
    headers = {
      "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36"}
    res = requests.get(url=url, headers=headers)
    res.encoding = 'utf-8'
    if res.status_code == 200:
      return res.text
    else:
      return None
  except Exception:
    return None

2.2根据base页面获取所有产品分类页面链接

if __name__ == '__main__':
  content = get_one_page(url)
  tree = etree.HTML(content)
  # 产品分类url
  catgory_urls = tree.xpath('//div[@class="fdh-01-nav"]/div/h3/a/@href')
  # 处理catgory_urls
  for url in catgory_urls:
    url = 'http://www.kexinjianji.com' + url
    print(url)

2.3根据产品分类页面链接获取对应所有产品链接

if __name__ == '__main__':
  content = get_one_page(url)
  tree = etree.HTML(content)
  # 产品分类
  catgory = tree.xpath('//div[@class="cplb-3n-ts-03 b"]/h3/span/text()')
  print("产品分类:" + catgory[0])
  # 该分类下产品url
  urls = tree.xpath('//div[@class="cplb-3n-ts-03-list"]/dl/dt/a/@href')
  # 处理url
  for url in urls:
    url = 'http://www.kexinjianji.com' + url
    print(url)
  print("=====================================================")

两者结合起来就可以打印出所有产品链接

if __name__ == '__main__':
  content = get_one_page(url)
  tree = etree.HTML(content)
  # 产品分类url
  catgory_urls = tree.xpath('//div[@class="fdh-01-nav"]/div/h3/a/@href')
  # 处理catgory_urls
  for url in catgory_urls:
    url = 'http://www.kexinjianji.com' + url
    content = get_one_page(url)
    tree = etree.HTML(content)
    # 产品分类
    catgory = tree.xpath('//div[@class="cplb-3n-ts-03 b"]/h3/span/text()')
    print("产品分类:" + catgory[0])
    # 该分类下产品url
    urls = tree.xpath('//div[@class="cplb-3n-ts-03-list"]/dl/dt/a/@href')
    # 处理url
    for url in urls:
      url = 'http://www.kexinjianji.com' + url
      print(url)
    print("=====================================================")

2.2使用xpath解析函数返回产品链接的内容

if __name__ == '__main__':
  content = get_one_page(url)
  tree = etree.HTML(content)
  # 产品名称
  title = tree.xpath('//*[@id="wrap"]//h1/text()')
  images = tree.xpath('//div[@class="sol_tj_left"]/a/img/@src')
  # 产品图片
  images_url = 'http://www.kexinjianji.com/' + images[0]
  # 性能特点
  xntd = tree.xpath('//div[@class="w"]//div/span/text()|//div[@class="w"]//div/text()')
  # 技术参数
  jscs = tree.xpath('//table')[0]
  jscs_str = etree.tostring(jscs, encoding='utf-8').decode('utf-8')
  # 产品内容
  cpnr = tree.xpath('//div[@class="describe"]/p')
  print('产品名称:' + title[0])
  print('产品图片:' + images_url)
  for td in xntd:
    print('性能特点:' + td)
  print('技术参数:' + jscs_str)
  for cp in cpnr:
    # string(.) 获取当前标签下所有文本内容
    cp = cp.xpath('string(.)')
    print('产品内容:' + cp)
  print('============================================')

将三者结合在一起就可以获取所有产品信息

if __name__ == '__main__':
  content = get_one_page(url)
  tree = etree.HTML(content)
  # 产品分类url
  catgory_urls = tree.xpath('//div[@class="fdh-01-nav"]/div/h3/a/@href')
  # 处理catgory_urls
  for url in catgory_urls:
    url = 'http://www.kexinjianji.com' + url
    content = get_one_page(url)
    tree = etree.HTML(content)
    # 产品分类
    catgory = tree.xpath('//div[@class="cplb-3n-ts-03 b"]/h3/span/text()')
    # 该分类下产品url
    urls = tree.xpath('//div[@class="cplb-3n-ts-03-list"]/dl/dt/a/@href')
    # 处理url
    for url in urls:
      url = 'http://www.kexinjianji.com' + url
      content = get_one_page(url)
      try:
        tree = etree.HTML(content)
        # 产品名称
        title = tree.xpath('//*[@id="wrap"]//h1/text()')
        images = tree.xpath('//div[@class="sol_tj_left"]/a/img/@src')
        # 产品图片
        images_url = 'http://www.kexinjianji.com' + images[0]
        # 性能特点
        xntd = tree.xpath('//div[@class="w"]//div/span/text()|//div[@class="w"]//div/text()')
        # 技术参数
        jscs = tree.xpath('//table')[0]
        jscs_str = etree.tostring(jscs, encoding='utf-8').decode('utf-8')
        # 产品内容
        cpnr = tree.xpath('//div[@class="describe"]/p')
        print("产品分类:" + catgory[0])
        print('产品链接:' + url)
        print('产品名称:' + title[0])
        print('产品图片:' + images_url)
        for td in xntd:
          print('性能特点:' + td.strip())
        # print('技术参数:' + jscs_str)
        for cp in cpnr:
          # string(.) 获取当前标签下所有文本内容
          cp = cp.xpath('string(.)')
          print('产品内容:' + cp)
        print('============================================')
      except Exception as e:
        print(e)
        print('出错url:' + url)
        pass

3.存储到django模型

import requests
from lxml.html import etree
import os
import django
import uuid
from django.core.files.base import ContentFile

os.environ.setdefault("DJANGO_SETTINGS_MODULE", "jiaobanzhan.settings")
django.setup()

from products.models import ProductBody, ProductsCategory, Product, ProductAdvantage

url = 'http://www.kexinjianji.com/product/hzshntjbz_1/'


def get_one_page(url):
  try:
    headers = {
      "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36"}
    res = requests.get(url=url, headers=headers, timeout=10)
    res.encoding = 'utf-8'
    if res.status_code == 200:
      return res.text
    else:
      return None
  except Exception:
    print('aa')
    return None


if __name__ == '__main__':
  content = get_one_page(url)
  tree = etree.HTML(content)
  # 产品分类url
  catgory_urls = tree.xpath('//div[@class="fdh-01-nav"]/div/h3/a/@href')
  # 处理catgory_urls
  for url in catgory_urls:
    url = 'http://www.kexinjianji.com' + url
    content = get_one_page(url)
    tree = etree.HTML(content)
    # 产品分类
    p_catgory = tree.xpath('//div[@class="cplb-3n-ts-03 b"]/h3/span/text()')
    # 该分类下产品url
    urls = tree.xpath('//div[@class="cplb-3n-ts-03-list"]/dl/dt/a/@href')
    # 处理url
    for url in urls:
      url = 'http://www.kexinjianji.com' + url
      content = get_one_page(url)
      try:
        tree = etree.HTML(content)
        # 产品名称
        title = tree.xpath('//*[@id="wrap"]//h1/text()')
        images = tree.xpath('//div[@class="sol_tj_left"]/a/img/@src')
        # 产品图片
        images_url = 'http://www.kexinjianji.com' + images[0]
        # 性能特点
        xntd = tree.xpath('//div[@class="w"]//div/span/text()|//div[@class="w"]//div/text()')
        # 技术参数
        jscs = tree.xpath('//table')[0]
        jscs_str = etree.tostring(jscs, encoding='utf-8').decode('utf-8')
        # 产品内容
        cpnr = tree.xpath('//div[@class="describe"]/p')
        # 判断是否有这分类,没有则新建
        catgory = p_catgory[0]
        products_catgory = ProductsCategory.objects.filter(name=catgory).exists()
        if products_catgory:
          products_catgory = ProductsCategory.objects.get(name=catgory)
        else:
          products_catgory = ProductsCategory(name=catgory)
          products_catgory.save()
        print(products_catgory)

        # 保存产品图片
        image_content = requests.get(url=images_url)
        ext = images_url.split('.')[-1] # 获取图片类型
        filename = '{}.{}'.format(uuid.uuid4().hex[:8], ext) # 随机生成图片名字
        upload_image_file = ContentFile(image_content.content, name=filename) # 将图片保存为django类型
        product = Product(title=title[0], jscs=jscs_str, image=upload_image_file, category=products_catgory)
        product.save()
        for td in xntd:
          product_advantage = ProductAdvantage()
          product_advantage.content = td
          product_advantage.product = product
          product_advantage.save()
        for cp in cpnr:
          cp = cp.xpath('string(.)')
          product_body = ProductBody()
          product_body.body = cp
          product_body.product = product
          product_body.save()
      except Exception as e:
        print(e)
        print('出错url:' + url)

最后自己手动处理出错url(页面没有获取到技术参数,技术参数是一张图片)

4.总结

1.xpath 获取标签内容时,p标签中嵌套span标签,源码如下

<div class="describe" style="position: relative;"> 
   <p><span>板  宽:</span>1500mm</p> 
   <p><span>板  厚:</span>4.5 mm</p> 
   <p><span>出料口:</span>6口</p> 
   <p><span>重  量:</span>6000 kg</p>
</div>

使用xpath获取p标签内容
我想得到的效果如下
板 宽:1500mm
板 厚:4.5 mm
出料口:6口
重 量:6000 kg
使用以下xpath 只能分开获取,不是想要的效果

//div[@class="describe"]/p/span/text()|//div[@class="describe"]/p/text()

百度之后找到的解决办法,使用xpath(‘string(.)')
1.先获取所有p标签

cpnr = tree.xpath('//div[@class="describe"]/p')

2.使用**string(.)**获取所有标签所有文本

cp = cp.xpath('string(.)')

循环遍历所有p标签即可

到此这篇关于python利用xpath爬取网上数据并存储到django模型中的文章就介绍到这了,更多相关xpath爬取网上数据存储到django模型内容请搜索三水点靠木以前的文章或继续浏览下面的相关文章希望大家以后多多支持三水点靠木!

Python 相关文章推荐
使用C语言扩展Python程序的简单入门指引
Apr 14 Python
Python实现统计文本文件字数的方法
May 05 Python
对numpy数据写入文件的方法讲解
Jul 09 Python
对python 命令的-u参数详解
Dec 03 Python
Python实现去除列表中重复元素的方法总结【7种方法】
Feb 16 Python
搞定这套Python爬虫面试题(面试会so easy)
Apr 03 Python
django数据库自动重连的方法实例
Jul 21 Python
python 并发编程 阻塞IO模型原理解析
Aug 20 Python
基于python纯函数实现井字棋游戏
May 27 Python
Pycharm常用快捷键总结及配置方法
Nov 14 Python
python快速安装OpenCV的步骤记录
Feb 22 Python
用Python提取PDF表格的方法
Apr 11 Python
用python 绘制茎叶图和复合饼图
Feb 26 #Python
python lambda的使用详解
Feb 26 #Python
python爬虫scrapy框架之增量式爬虫的示例代码
Feb 26 #Python
详解Python openpyxl库的基本应用
Feb 26 #Python
解决python的空格和tab混淆而报错的问题
Feb 26 #Python
Python Spyder 调出缩进对齐线的操作
Feb 26 #Python
使用Python制作一盏 3D 花灯喜迎元宵佳节
Feb 26 #Python
You might like
php生成二维码不保存服务器还有下载功能的实现代码
2018/08/09 PHP
详解PHP中curl_multi并发的实现
2020/06/08 PHP
JavaScript的类型简单说明
2010/09/03 Javascript
JS求平均值的小例子
2013/11/29 Javascript
使用jquery实现以post打开新窗口
2014/03/19 Javascript
JavaScript基础教程之alert弹出提示框实例
2014/10/16 Javascript
Windows系统下Node.js的简单入门教程
2015/06/23 Javascript
jquery常用函数与方法汇总
2015/09/01 Javascript
js简单网速测试方法完整实例
2015/12/15 Javascript
基于jQuery实现仿51job城市选择功能实例代码
2016/03/02 Javascript
jQuery插件开发汇总
2016/05/15 Javascript
jQuery滚动监听实现商城楼梯式导航效果
2017/03/06 Javascript
js中apply()和call()的区别与用法实例分析
2018/08/14 Javascript
浅谈Vue 性能优化之深挖数组
2018/12/11 Javascript
js实现ATM机存取款功能
2020/10/27 Javascript
vue elementui el-form rules动态验证的实例代码详解
2019/05/23 Javascript
vue中uni-app 实现小程序登录注册功能
2019/10/12 Javascript
JavaScript闭包相关知识解析
2019/10/19 Javascript
node.js中process进程的概念和child_process子进程模块的使用方法示例
2020/02/11 Javascript
基于PHP pthreads实现多线程代码实例
2020/06/24 Javascript
一篇文章搞懂Python的类与对象名称空间
2018/12/10 Python
PyQt5 加载图片和文本文件的实例
2019/06/14 Python
Python如何优雅获取本机IP方法
2019/11/10 Python
Python脚本去除文件的只读性操作
2020/03/05 Python
pytorch中index_select()的用法详解
2021/01/06 Python
python自动生成sql语句的脚本
2021/02/24 Python
Gibson London官网:以地道的英国男装而著称
2019/12/06 全球购物
英国羊皮鞋类领先品牌:Just Sheepskin
2019/12/12 全球购物
JDBC操作数据库的基本流程是什么
2014/10/28 面试题
学校十一活动方案
2014/02/01 职场文书
大学生求职信
2014/06/17 职场文书
公司活动总结怎么写
2014/06/25 职场文书
学校党的群众路线教育实践活动总结报告
2014/07/03 职场文书
教师党员整改措施
2014/10/24 职场文书
2015年超市收银员工作总结
2015/04/25 职场文书
ROS系统将python包编译为可执行文件的简单步骤
2021/07/25 Python