1.创建scrapy框架

scrapy startproject 项目名(scrapy_test_one)

创建好以后的目录是这样的

在这里插入图片描述

2.创建spider文件

在spiders目录下创建一个spider_one.py文件，可以随意命名，该文件主要是让我们进行数据爬取的。
运行命令：

scrapy genspider spider_one baidu.com

注意末尾的域名是用来设置爬取的范围的

spider_one.py代码如下

import scrapy
from scrapy import Request

from scrapy_test_one.items import ScrapyTestOneItem
# from scrapy.selector import HtmlXPathSelector


class SpiderOneSpider(scrapy.Spider):
    name = "spider_one"
    allowed_domains = ['movie.douban.com/top250']
    start_urls = ['https://movie.douban.com/top250']


    def parse(self, response, *args):
        movie_items = response.xpath('//div/ol[@class="grid_view"]')
        # print("======================",movie_items)

        for item in movie_items:
            movie = ScrapyTestOneItem()

            # src = item.xpath('//li/div/div/a/img/@src').extract_first()
            # print("===================",src)
            # movie["img"] = src

            title = item.xpath('//li/div/div[2]/div/a/span[1]/text()')
            movie["title"] = title.extract()
            print("=========================title=======================",title)
            # movie['rank'] = item.xpath('')
            # # print(movie['rank'])
            # movie['title'] = item.xpath(
            #     'div[@class="info"]/div[@class="hd"]/a/span[@class="title"][1]/text()').extract()
            # movie['poster'] = item.xpath('div[@class="pic"]/a/img/@src').extract()
            # movie['link'] = item.xpath('div[@class="info"]/div[@class="hd"]/a/@href').extract()
            # movie['rating'] = item.xpath(
            #     'div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[@class="rating_num"]/text()').extract()


            yield movie

3.对settings进行配置

放开useragent，配置好对应的值

USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'

关闭robots协议

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

放开管道限制

ITEM_PIPELINES = {
   "scrapy_test_one.pipelines.ScrapyTestOnePipeline": 300,
}

4.配置items文件

在items.py文件中添加需要的字段

import scrapy


class ScrapyTestOneItem(scrapy.Item):
    # define the fields for your item here like:
    name = scrapy.Field()
    img = scrapy.Field()
    title = scrapy.Field()

5.配置piplines.py文件

from itemadapter import ItemAdapter
from scrapy_test_one.items import ScrapyTestOneItem
import pymongo
host = 'localhost'
port = 27017
db_name = 'DBmovies'



class ScrapyTestOnePipeline:
    def open_spider(self, spider):
    	# 连接数据库
        self.client = pymongo.MongoClient(host=host, port=port)            
        self.db = self.client[db_name]


    def process_item(self, item, spider):
        items = dict(item)
        if isinstance(items, dict):
            print("============================",items)
            self.collection = self.db['movies']
            self.collection.insert_one(items)

            # self.db["movies"].insert_one(items)
        else:
            return "数据格式错误"