scrapy初探之实现爬取小说

Posted 2020-11-10

一、前言

上文说明了scrapy框架的基础知识，本篇实现了爬取第九中文网的免费小说。

二、scrapy实例创建

1、创建项目

C:\Users\LENOVO\PycharmProjects\fullstack\book9>scrapy startproject book9

2、定义要爬取的字段（item.py）

import scrapy

class Book9Item(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    book_name = scrapy.Field()   #小说名字
    chapter_name = scrapy.Field()   #小说章节名字
    chapter_content = scrapy.Field()    #小说章节内容

3、写爬虫（spiders/book.py）

在spiders目录下创建book.py文件
import scrapy
from book9.items import Book9Item
from scrapy.http import Request
import os

class Book9Spider(scrapy.Spider):
    name = "book9"
    allowed_domains = [‘book9.net‘]
    start_urls = [‘https://www.book9.net/xuanhuanxiaoshuo/‘]

    #爬取每本书的URL
    def parse(self, response):
        book_urls = response.xpath(‘//div[@class="r"]/ul/li/span[@class="s2"]/a/@href‘).extract()

        for book_url in book_urls:
            yield Request(book_url,callback=self.parse_read)

    #进入每一本书目录
    def parse_read(self,response):

        read_url = response.xpath(‘//div[@class="box_con"]/div/dl/dd/a/@href‘).extract()

        for i in read_url:
            read_url_path = os.path.join("https://www.book9.net" + i)

            yield Request(read_url_path,callback=self.parse_content)

    #爬取小说名，章节名，内容
    def parse_content(self,response):

        #爬取小说名
        book_name = response.xpath(‘//div[@class="con_top"]/a/text()‘).extract()[2]

        #爬取章节名
        chapter_name = response.xpath(‘//div[@class="bookname"]/h1/text()‘).extract_first()

        #爬取内容并处理
        chapter_content_2 = response.xpath(‘//div[@class="box_con"]/div/text()‘).extract()
        chapter_content_1 = ‘‘.join(chapter_content_2)
        chapter_content = chapter_content_1.replace(‘    ‘, ‘‘)

        item = Book9Item()
        item[‘book_name‘] = book_name
        item[‘chapter_name‘] = chapter_name
        item[‘chapter_content‘] = chapter_content

        yield item

4、处理爬虫返回的数据(pipelines.py)

import os

class Book9Pipeline(object):
    def process_item(self, item, spider):
        #创建小说目录

        file_path = os.path.join("D:\\Temp",item[‘book_name‘])
        print(file_path)
        if not os.path.exists(file_path):
            os.makedirs(file_path)

        #将各章节写入文件
        chapter_path = os.path.join(file_path,item[‘chapter_name‘] + ‘.txt‘)
        print(chapter_path)
        with open(chapter_path,‘w‘,encoding=‘utf-8‘) as f:
            f.write(item[‘chapter_content‘])

        return item

5、配置文件(settiings.py)

BOT_NAME = ‘book9‘

SPIDER_MODULES = [‘book9.spiders‘]
NEWSPIDER_MODULE = ‘book9.spiders‘
# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# 设置请求头部
DEFAULT_REQUEST_HEADERS = {
    "User-Agent" : "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0;",
    ‘Accept‘: ‘text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8‘
}
# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
    ‘book9.pipelines.Book9Pipeline‘: 300,
}

6、执行爬虫
C:\Users\LENOVO\PycharmProjects\fullstack\book9>scrapy crawl book9 --nolog

7、结果