一、项目目录结构

spiders文件夹内包含doubanSpider.py文件,对于项目的构建以及结构逻辑,详见环境搭建篇。

Scrapy项目 - 源码工程 - 实现豆瓣 Top250 电影信息爬取的爬虫设计

二、项目源码

1.doubanSpider.py

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

#创建爬虫类
class DoubanspiderSpider(scrapy.Spider):
    name = 'doubanSpider'   #爬虫名字
    allowed_domains = ['movie.douban.com']  #容许爬虫的作用范围
    #定义开始的URL
    offset=0
    url='https://movie.douban.com/top250?start='

    start_urls = [url+str(offset)]    #爬虫开始的URL

    def parse(self, response):
         #with open("douban.html","w",encoding="utf-8") as f:
             #f.write(str(response.body,encoding="utf-8"))
        #继承
        item=DoubanItem()
        #根节点
        movies=response.xpath("//div[@class='info']")

        for each in movies:
            #标题
            item['title']=each.xpath(".//span[@class='title'][1]/text()").extract()[0]
            #信息
            #item['info'] = each.xpath(".//div[@class='bd']/p[@class='']/text()[2]").extract()[0]
            item['info'] = each.xpath(".//div[@class='bd']/p[normalize-space(@class)='']/text()[2]").extract()[0]



            # xinxi
            #item['info2'] = each.xpath(".//div[@class='bd']/p[@class='']/text()[2]").extract()[0]
            # 评分
            item['star'] = each.xpath(".//div[@class='bd']/div[@class='star']/span[@class='rating_num']/text()").extract()[0]
            # 简介
            quote = each.xpath(".//div[@class='bd']/p[@class='quote']/span/text()").extract()


            #异常处理
            if len(quote)!=0:
                item['quote']=quote[0]

            print(item)
            yield item
        if self.offset < 255:
            self.offset += 25
            # 每次处理完一页之后,重新发送下一页请求
            # self offset 自增25,同时拼接为新的URL并调用回调函数,self parse 处理response
            yield scrapy.Request(self.url + str(self.offset),callback=self.parse)







        # 通过scrapy 的xpath匹配所有老师的根节点列表集合
        #teacher_list = response.xpath("//div[@class='teacher-text']")

        # 所有列表集合
        #teacherItem = []

        # 遍历根节点的集合
        #for each in teacher_list:
            # Item对象来保存数据
            #item = GecspiderItem()

            # 不加extract() 结果为xpath匹配对象
            #name = each.xpath('./h4/text()').extract()
            # 职位
            #title = each.xpath('./h6/text()').extract()
            # 个人简介
            #info = each.xpath('./p/text()').extract()
            #item['name'] = name[0]
            #item['title'] = title[0]
            #item['info'] = info[0]
            # 上一次运行位置暂停继续运行,病返回
            #   yield item

            #teacherItem.append(item)

            # print(name[0])
            # print(title[0])
            # print(info[0])
        #return teacherItem

2.items.py

# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/items.html

import scrapy


class DoubanItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    #标题
    title = scrapy.Field()
    #信息
    info = scrapy.Field()
    #评分
    star = scrapy.Field()
     #简介

    quote = scrapy.Field()

    pingjia = scrapy.Field()

3.main.py

from scrapy import cmdline
#
cmdline.execute("scrapy crawl doubanSpider ".split())

4.pipelines.py

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
import json
from openpyxl import Workbook
class DoubanPipeline(object):
    wb = Workbook()
    ws = wb.active
    # 设置表头
    ws.append(['标题','评分','信息','简介'])

    def process_item(self, item, spider):
        # 添加数据
        line = [item['title'],item['star'],item['info'],item['quote']]
        self.ws.append(line)  # 按行添加
        self.wb.save('douban.xlsx')
        return item

5.settings.py

# -*- coding: utf-8 -*-

# Scrapy settings for douban project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://doc.scrapy.org/en/latest/topics/settings.html
#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'douban'

SPIDER_MODULES = ['douban.spiders']
NEWSPIDER_MODULE = 'douban.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'

# Obey robots.txt rules
#ROBOTSTXT_OBEY = True

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
#}

# Enable or disable spider middlewares
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'douban.middlewares.DoubanSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'douban.middlewares.DoubanDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
    'douban.pipelines.DoubanPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'