Scrapy-Redis分布式爬虫库模拟多台服务器进行百万级别大数据爬取

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from scrapy_redis.spiders import RedisCrawlSpider


class MovieSpider(RedisCrawlSpider):
    # 爬虫任务名
    name = "movie"
    # 爬虫任务的域名范围
    allowed_domains = ["movie.douban.com"]

    # 注释掉爬虫任务的起始链接
    # start_urls = ["https://movie.douban.com/top250"]

    # 设置redis_key，通过redis_key向redis数据库中获取请求链接
    redis_key = 'start_urls'

    # rules是一个元组数据，规则
    # Rule是一个类，用于实例化一个对象。LinkExtractor也是类，用于实例化对象
    # 在LinkExtractor类中，需要记住allow(正则)和restrict_xpaths(xpath)参数，用于筛选数据
    # follow是用于设置页面跟随的开关，用来指定是否需要翻页抓取，为True代表翻页
    rules = (Rule(LinkExtractor(allow='^https://movie.douban.com/subject/\d+/$'), callback="parse_item", follow=False),
             Rule(LinkExtractor(restrict_xpaths='//span[@class="next"]/a'), follow=True),)

    # 回调函数,用于处理下载器返回的响应
    def parse_item(self, response):
        title = response.xpath('//span[@property="v:itemreviewed"]/text()').get()
        score = response.xpath('//strong[@property="v:average"]/text()').get()
        url = response.url
        text_list = response.xpath('//span[@property="v:summary"]/text()').getall()
        text = ''.join(text_list)
        text = text.replace('\n', '').replace(' ', '').replace('\u3000', '')
        item = {'标题': title, '评分': score, '网址': url, '简介': text}
        return item

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html


# useful for handling different item types with a single interface
from itemadapter import ItemAdapter
import pymongo


class DoubanMoviePipeline:
    # 使用init来初始化mongodb数据库的指定
    def __init__(self):
        # 连接mongodb数据库中的python_test数据库，并指定movie_top集合
        self.client = pymongo.MongoClient()
        self.db = self.client['python_test']
        self.collection = self.db['movie_top']

    def process_item(self, item, spider):
        print(item)
        self.collection.insert_one(item)
        return item


from scrapy import Request
from itemadapter import ItemAdapter
from scrapy.pipelines.images import ImagesPipeline


# 自定义图片管道类
class DoubanImagePipeline(ImagesPipeline):
    # 重写get_media_requests方法发送请求下载图片
    def get_media_requests(self, item, info):
        # 通过ItemAdapter来获取图片管道的image_urls字段
        urls = ItemAdapter(item).get(self.images_urls_field, [])
        # 遍历出image_urls字段中的链接，并发送下载图片的请求
        return [Request(u, meta={'image': item}) for u in urls]

    # 重写file_path方法来指定图片的保存位置和名称
    def file_path(self, request, response=None, info=None, *, item=None):
        # image_guid = hashlib.sha1(to_bytes(request.url)).hexdigest()
        # 获取请求的图片数据
        item = request.meta.get('image')
        # 获取请求的图片链接的图片名
        image_name = item['image_name']
        # 设置保存的文件夹和文件名
        return f"images/{image_name}.jpg"

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

BOT_NAME = "douban_movie"

SPIDER_MODULES = ["douban_movie.spiders"]
NEWSPIDER_MODULE = "douban_movie.spiders"

# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36"

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
CONCURRENT_REQUESTS = 3

# Configure a delay for requests for the same website (default: 0)
# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 1
# 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://docs.scrapy.org/en/latest/topics/spider-middleware.html
# SPIDER_MIDDLEWARES = {
#    "douban_movie.middlewares.DoubanMovieSpiderMiddleware": 543,
# }

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
#     "douban_movie.middlewares.DoubanMovieDownloaderMiddleware": 543,
# }

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

from scrapy.pipelines.images import ImagesPipeline

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
    # 普通文本数据保存的管道
    "douban_movie.pipelines.DoubanMoviePipeline": 300,
    # 图片数据保存的管道
    # "scrapy.pipelines.images.ImagesPipeline": 301,
    # 注册自定义的图片管道
    # "douban_movie.pipelines.DoubanImagePipeline": 302
}
# 指定图片保存的位置，保存到项目的当前路径下
# IMAGES_STORE = './'

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.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://docs.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"

# Set settings whose default value is deprecated to a future-proof value
REQUEST_FINGERPRINTER_IMPLEMENTATION = "2.7"
TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
FEED_EXPORT_ENCODING = "utf-8"

# ===========================================
# 这里是配置Scrapy-Redis信息

# 设置redis作为过滤器，防止请求重复的数据
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"

# 设置Redis作为任务调度器
SCHEDULER = "scrapy_redis.scheduler.Scheduler"

# 设置调度器持久化，保证数据的断点续爬
SCHEDULER_PERSIST = True

# 设置日志等级信息
LOG_LEVEL = 'DEBUG'

# 如果redis是部署在云端的，需要配置Redis的连接
# REDIS_URL = 'redis://user:pass@hostname:6379'