Scrapy 框架爬取武动乾坤小说

﹏ヽ暗。殇╰゛Y 2023-05-29 06:55 58阅读 0赞

# 首先是创建项目  #

scrapy startproject qidan

cd qi

scrapy genspider qi "qidian.com"

# qi.py #

# -*- coding: utf-8 -*-
    import scrapy
    
    class QiSpider(scrapy.Spider):
        name = 'qi'
        allowed_domains = ['qidian.com']
        start_urls = ['https://book.qidian.com/info/2048120']
    
        def parse(self, response):
            print(response.url)
            item = {}
            item["book_name"] = response.xpath("//h1/em/text()").extract_first()
            item["book_author"] = response.xpath("//a[@class='writer']/text()").extract_first()
            item["book_img"] = response.xpath("//a[@class='J-getJumpUrl']/img/@src").extract_first()
            item["book_first"] = "https:%s" % response.xpath("//a[@class='red-btn J-getJumpUrl ']/@href").extract_first()
            yield scrapy.Request(
                item["book_first"],
                callback=self.parse_book,
                meta={"item": item}
            )
    
        def parse_book(self, response):
            item = response.meta["item"]
            # 这个本业的内容
            contents = response.xpath("//div[@class='read-content j_readContent']/p")
    
            # 这个是下一章的的连接
            next_url = "https:%s" % response.xpath("//a[@id='j_chapterNext']/@href").extract_first()
            result = ""
    
            # 处理文章名
            result = str(response.xpath("//span[@class='content-wrap']/text()").extract_first())
            result += "\n\n"
            for content in contents:
    
                # 处理每段文字的内容
                temp = str(content.xpath("./text()").extract_first())
                # 处理乱码
                temp.replace('[', '').replace("]", "")
                temp.strip().replace(u'\u3000', u' ').replace(u'\xa0', u' ')
                result += str(temp)
                # 给每段文字加上一点回车符
                result += "\n\n"
    
            item["book_content"] = result
            yield item
    
            yield scrapy.Request(
                next_url,
                callback=self.parse_book,
                meta={"item": item}
            )
        # 判断变量类型的函数

#  pineplines.py #

# -*- coding: utf-8 -*-
    
    # 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
    
    class QidianPipeline(object):
        def __init__(self):
            # 这里的文本存储的地方
            self.f = open(r"D:/1.txt", "w", encoding="UTF-8")
    
        def process_item(self, item, spider):
    
            for content in item["book_content"]:
             self.f.write(content)
    
            self.f.flush()
            return item
    
        def close_spider(self, spider):
            # 爬虫关闭时进行：文件关闭
            self.f.close()

# setting.py  #

# -*- coding: utf-8 -*-
    
    # Scrapy settings for qidian 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 = 'qidian'
    
    SPIDER_MODULES = ['qidian.spiders']
    NEWSPIDER_MODULE = 'qidian.spiders'
    
    
    # Crawl responsibly by identifying yourself (and your website) on the user-agent
    #USER_AGENT = 'qidian (+http://www.yourdomain.com)'
    
    # Obey robots.txt rules
    ROBOTSTXT_OBEY = False
    USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36"
    
    # 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://docs.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://docs.scrapy.org/en/latest/topics/spider-middleware.html
    #SPIDER_MIDDLEWARES = {
    #    'qidian.middlewares.QidianSpiderMiddleware': 543,
    #}
    
    # Enable or disable downloader middlewares
    # See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
    #DOWNLOADER_MIDDLEWARES = {
    #    'qidian.middlewares.QidianDownloaderMiddleware': 543,
    #}
    
    # Enable or disable extensions
    # See https://docs.scrapy.org/en/latest/topics/extensions.html
    #EXTENSIONS = {
    #    'scrapy.extensions.telnet.TelnetConsole': None,
    #}
    
    # Configure item pipelines
    # See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
    ITEM_PIPELINES = {
       'qidian.pipelines.QidianPipeline': 300,
    }
    
    # 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'