Scrapy入门案例——爬取豆瓣电影

scrapy startproject xxx    创建scrapy项目
scrapy genspider xxx "xxx.com"  创建爬虫spider，名字不能和项目名一样
scrapy crawl xxx  运行某个爬虫项目

import scrapy

class DoubanItem(scrapy.Item):
    title = scrapy.Field()
    url = scrapy.Field()

# -*- coding: utf-8 -*-
import scrapy
from douban.items import DoubanItem
import json


class DoubanMovieSpider(scrapy.Spider):
    name = 'douban_movie'
    allowed_domains = ['movie.douban.com']
    start_urls = ['https://movie.douban.com/j/chart/top_list?type=11&interval_id=100%3A90&action=&start=0&limit=20']
    offset = 0
    def parse(self, response):
        item = DoubanItem()
        content_list = json.loads(response.body.decode())
        if (content_list == []):
            return
        for content in content_list:
            item['title'] = content['title']
            item['url'] = content['url']
            yield item
        self.offset += 20
        url = 'https://movie.douban.com/j/chart/top_list?type=11&interval_id=100%3A90&action=&start='+str(self.offset) + '&limit=20'
        yield scrapy.Request(url=url,callback=self.parse)

import json

class DoubanPipeline(object):
    def open_spider(self,spider):
        self.file = open("douban.json","w")
        self.num = 0
    def process_item(self, item, spider):
        self.num+=1
        content = json.dumps(dict(item),ensure_ascii=False)+'\n'
        self.file.write(content)
        return item
    def close_spider(self,spider):
        print('一共保存了'+str(self.num)+'条数据')
        self.file.close()

#打开这两个注释：
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.15 Safari/537.36'  #模拟浏览器

ITEM_PIPELINES = {
   'douban.pipelines.DoubanPipeline': 300,
}   #编辑好管道要记得注册管道

#ROBOTSTXT_OBEY = True  注释掉robot协议，不然会报错