（爬虫）书籍和电影，程序员不可或缺爬虫步骤1. 分析目标网页的特征2. 找到需要爬取的数据3.多页面数据的跳转4.数据存储

        html_doc = response.body
        soup = BeautifulSoup(html_doc, 'html.parser')

        img_url = urljoin(CDN, soup.find('img').attrs.get('src').replace('//','/'))
        download_url = soup.find('a', class_='downloads').attrs.get('href')
        title = soup.find_all('div', class_='hanghang-za-title')
        name = title[0].text

        content = soup.find_all('div', class_='hanghang-za-content')
        author_info = content[0].text
        directory = '\n'.join([i.text.replace("\u3000", '') for i in content[1].find_all('p')])

        info = soup.find('div', class_='hanghang-shu-content-font').find_all('p')

        author = info[0].text.split('作者：')[1]
        category = info[1].text.split('分类：')[1]
        score = info[2].text.split('豆瓣评分：')[1]
        introduction = info[4].text

        next_url = urljoin(DOMAIN, soup.find_all('a')[-2].attrs.get('href'))
        yield scrapy.Request(next_url, callback=self.parse)

# django中
from django.db import models


# Create your models here.
class Book(models.Model):
    id = models.IntegerField(primary_key=True)
    name = models.CharField(max_length=255)
    author = models.CharField(max_length=255)
    category = models.CharField(max_length=255)
    score = models.CharField(max_length=100)
    img_url = models.URLField()
    download_url = models.URLField()
    introduction = models.CharField(max_length=2048)
    author_info = models.CharField(max_length=2048)
    directory = models.CharField(max_length=4096)
    create_edit = models.DateTimeField(auto_now_add=True)

    class Meta:
        managed = False
        db_table = "ireadweek"

# scrapy settings.py配置
import os
import sys
import django

sys.path.append(os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), ".."))
os.environ['DJANGO_SETTINGS_MODULE'] = 'Rino_nakasone_backend.settings'

django.setup()


# 在 scrapy中pipelines.py
from ireadweek.models import Book
import datetime


class RinonakasonePipeline(object):
    def process_item(self, item, spider):
        book = Book()
        book.name = item.get('name')
        book.author = item.get('author')
        book.category = item.get('category')
        book.score = item.get('score')
        book.image_url = item.get('image_url')
        book.download_url = item.get('download_url')
        book.introduction = item.get('introduction')
        book.author_info = item.get('author_info')
        book.directory = item.get('directory')
        book.create_edit = datetime.datetime.now()
        book.save()
        return item

# 在spider中引用

    def parse_news(self, response):
        item = IreadweekItem()
        html_doc = response.body
        soup = BeautifulSoup(html_doc, 'html.parser')

        img_url = urljoin(CDN, soup.find('img').attrs.get('src').replace('//','/'))
        download_url = soup.find('a', class_='downloads').attrs.get('href')
        title = soup.find_all('div', class_='hanghang-za-title')
        name = title[0].text

        content = soup.find_all('div', class_='hanghang-za-content')
        author_info = content[0].text
        directory = '\n'.join([i.text.replace("\u3000", '') for i in content[1].find_all('p')])

        info = soup.find('div', class_='hanghang-shu-content-font').find_all('p')

        author = info[0].text.split('作者：')[1]
        category = info[1].text.split('分类：')[1]
        score = info[2].text.split('豆瓣评分：')[1]
        introduction = info[4].text

        item['name'] = name
        item['img_url'] = img_url
        item['download_url'] = download_url
        item['author'] = author
        item['author_info'] = author_info
        item['category'] = category
        item['score'] = score
        item['introduction'] = introduction
        item['directory'] = directory

        return item

# 还有一个配置 settings.py
ITEM_PIPELINES = {
   'RinoNakasone.pipelines.RinonakasonePipeline': 300,
}