python利用xpath爬取網上數據並存儲到django模型中

Posted on by

幫朋友制作一個網站，需要一些產品數據信息，因為是代理其他公司產品，直接爬取代理公司產品數據

1.設計數據庫

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):
  """產品分類"""
  name = models.CharField('產品分類名', max_length=80, unique=True)
  description = models.TextField('產品分類描述', blank=True, null=True)
  slug = models.SlugField('slug', max_length=80, blank=True, null=True)
  parent_category = models.ForeignKey('self', verbose_name="父級分類", 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 = "產品分類"
    verbose_name_plural = verbose_name


class ProductsTag(models.Model):
  """產品標簽"""
  name = models.CharField('產品標簽名', 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 = "產品標簽"
    verbose_name_plural = verbose_name


class Product(models.Model):
  title = models.CharField('標題', max_length=255, unique=True)
  slug = models.SlugField('slug', max_length=255, blank=True, null=True)
  jscs = models.TextField('技術參數', blank=True, null=True)
  image = models.ImageField(upload_to=products_directory_path, verbose_name="產品圖片")
  views = models.PositiveIntegerField('瀏覽量', default=0)
  category = models.ForeignKey('ProductsCategory', verbose_name='分類', on_delete=models.CASCADE, blank=True, null=True)
  tags = models.ManyToManyField('ProductsTag', verbose_name='標簽集合', 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 = "產品"
    verbose_name_plural = verbose_name


class ProductAdvantage(models.Model):
  content = models.TextField('產品優勢', 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 = "產品優勢"
    verbose_name_plural = verbose_name


class ProductBody(models.Model):
  body = models.CharField('產品內容', 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 = "產品內容"
    verbose_name_plural = verbose_name

2.腳本編寫

2.1編寫獲取網頁源代碼函數

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根據base頁面獲取所有產品分類頁面鏈接

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

2.3根據產品分類頁面鏈接獲取對應所有產品鏈接

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

兩者結合起來就可以打印出所有產品鏈接

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

2.2使用xpath解析函數返回產品鏈接的內容

if __name__ == '__main__':
  content = get_one_page(url)
  tree = etree.HTML(content)
  # 產品名稱
  title = tree.xpath('//*[@id="wrap"]//h1/text()')
  images = tree.xpath('//div[@class="sol_tj_left"]/a/img/@src')
  # 產品圖片
  images_url = 'http://www.kexinjianji.com/' + images[0]
  # 性能特點
  xntd = tree.xpath('//div[@class="w"]//div/span/text()|//div[@class="w"]//div/text()')
  # 技術參數
  jscs = tree.xpath('//table')[0]
  jscs_str = etree.tostring(jscs, encoding='utf-8').decode('utf-8')
  # 產品內容
  cpnr = tree.xpath('//div[@class="describe"]/p')
  print('產品名稱:' + title[0])
  print('產品圖片:' + images_url)
  for td in xntd:
    print('性能特點:' + td)
  print('技術參數:' + jscs_str)
  for cp in cpnr:
    # string(.) 獲取當前標簽下所有文本內容
    cp = cp.xpath('string(.)')
    print('產品內容:' + cp)
  print('============================================')

將三者結合在一起就可以獲取所有產品信息

if __name__ == '__main__':
  content = get_one_page(url)
  tree = etree.HTML(content)
  # 產品分類url
  catgory_urls = tree.xpath('//div[@class="fdh-01-nav"]/div/h3/a/@href')
  # 處理catgory_urls
  for url in catgory_urls:
    url = 'http://www.kexinjianji.com' + url
    content = get_one_page(url)
    tree = etree.HTML(content)
    # 產品分類
    catgory = tree.xpath('//div[@class="cplb-3n-ts-03 b"]/h3/span/text()')
    # 該分類下產品url
    urls = tree.xpath('//div[@class="cplb-3n-ts-03-list"]/dl/dt/a/@href')
    # 處理url
    for url in urls:
      url = 'http://www.kexinjianji.com' + url
      content = get_one_page(url)
      try:
        tree = etree.HTML(content)
        # 產品名稱
        title = tree.xpath('//*[@id="wrap"]//h1/text()')
        images = tree.xpath('//div[@class="sol_tj_left"]/a/img/@src')
        # 產品圖片
        images_url = 'http://www.kexinjianji.com' + images[0]
        # 性能特點
        xntd = tree.xpath('//div[@class="w"]//div/span/text()|//div[@class="w"]//div/text()')
        # 技術參數
        jscs = tree.xpath('//table')[0]
        jscs_str = etree.tostring(jscs, encoding='utf-8').decode('utf-8')
        # 產品內容
        cpnr = tree.xpath('//div[@class="describe"]/p')
        print("產品分類：" + catgory[0])
        print('產品鏈接:' + url)
        print('產品名稱:' + title[0])
        print('產品圖片:' + images_url)
        for td in xntd:
          print('性能特點:' + td.strip())
        # print('技術參數:' + jscs_str)
        for cp in cpnr:
          # string(.) 獲取當前標簽下所有文本內容
          cp = cp.xpath('string(.)')
          print('產品內容:' + cp)
        print('============================================')
      except Exception as e:
        print(e)
        print('出錯url:' + url)
        pass

3.存儲到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)
  # 產品分類url
  catgory_urls = tree.xpath('//div[@class="fdh-01-nav"]/div/h3/a/@href')
  # 處理catgory_urls
  for url in catgory_urls:
    url = 'http://www.kexinjianji.com' + url
    content = get_one_page(url)
    tree = etree.HTML(content)
    # 產品分類
    p_catgory = tree.xpath('//div[@class="cplb-3n-ts-03 b"]/h3/span/text()')
    # 該分類下產品url
    urls = tree.xpath('//div[@class="cplb-3n-ts-03-list"]/dl/dt/a/@href')
    # 處理url
    for url in urls:
      url = 'http://www.kexinjianji.com' + url
      content = get_one_page(url)
      try:
        tree = etree.HTML(content)
        # 產品名稱
        title = tree.xpath('//*[@id="wrap"]//h1/text()')
        images = tree.xpath('//div[@class="sol_tj_left"]/a/img/@src')
        # 產品圖片
        images_url = 'http://www.kexinjianji.com' + images[0]
        # 性能特點
        xntd = tree.xpath('//div[@class="w"]//div/span/text()|//div[@class="w"]//div/text()')
        # 技術參數
        jscs = tree.xpath('//table')[0]
        jscs_str = etree.tostring(jscs, encoding='utf-8').decode('utf-8')
        # 產品內容
        cpnr = tree.xpath('//div[@class="describe"]/p')
        # 判斷是否有這分類，沒有則新建
        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)

        # 保存產品圖片
        image_content = requests.get(url=images_url)
        ext = images_url.split('.')[-1] # 獲取圖片類型
        filename = '{}.{}'.format(uuid.uuid4().hex[:8], ext) # 隨機生成圖片名字
        upload_image_file = ContentFile(image_content.content, name=filename) # 將圖片保存為django類型
        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('出錯url:' + url)

最後自己手動處理出錯url（頁面沒有獲取到技術參數，技術參數是一張圖片）

4.總結

1.xpath 獲取標簽內容時，p標簽中嵌套span標簽，源碼如下

<div class="describe" style="position: relative;"> 
   <p><span>板  寬：</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獲取p標簽內容
我想得到的效果如下
板 寬：1500mm
板 厚：4.5 mm
出料口：6口
重 量：6000 kg
使用以下xpath 隻能分開獲取，不是想要的效果

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

百度之後找到的解決辦法，使用xpath(‘string(.)’)
1.先獲取所有p標簽

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

2.使用**string(.)**獲取所有標簽所有文本

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

循環遍歷所有p標簽即可

到此這篇關於python利用xpath爬取網上數據並存儲到django模型中的文章就介紹到這瞭,更多相關xpath爬取網上數據存儲到django模型內容請搜索WalkonNet以前的文章或繼續瀏覽下面的相關文章希望大傢以後多多支持WalkonNet！

推薦閱讀：