Scrapy - 小说爬虫

实例解析 - 小说爬虫

页面分析

共有三级页面

一级页面 大目录

二级页面 章节目录

三级界面 章节内容

爬取准备

一级界面

http://www.daomubiji.com/

二级页面xpath

直接复制的 xpath

/html/body/section/article/a/@href

这里存在着反爬虫机制, 改变了页面结构

在返回的数据改变了页面结构, 需要换为下面的 xpath 才可以

//ul[@class="sub-menu"]/li/a/@href

三级页面xpath

//article

项目准备

begin.py

pycharm 启动文件,方便操作

from scrapy import cmdline

cmdline.execute('scrapy crawl daomu --nolog'.split())

settings.py

相关的参数配置

BOT_NAME = 'Daomu'

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

ROBOTSTXT_OBEY = False

LOG_LEVEL = 'WARNING'

DEFAULT_REQUEST_HEADERS = {
  'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
  'Accept-Language': 'en',
  'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36',
}

ITEM_PIPELINES = {
   'Daomu.pipelines.DaomuPipeline': 300,
}

逻辑代码

items.py

指定相关期望数据

 -*- 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 DaomuItem(scrapy.Item):
    # define the fields for your item here like:
    # 卷名
    juan_name = scrapy.Field()
    # 章节数
    zh_num = scrapy.Field()
    # 章节名
    zh_name = scrapy.Field()
    # 章节链接
    zh_link = scrapy.Field()
    # 小说内容
    zh_content = scrapy.Field()

daomu.py

爬虫文件

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

class DaomuSpider(scrapy.Spider):
    name = 'daomu'
    allowed_domains = ['www.daomubiji.com']
    start_urls = ['http://www.daomubiji.com/']

    # 解析一级页面,提取 盗墓笔记1 2 3 ... 链接
    def parse(self, response):
        # print(response.text)
        one_link_list = response.xpath(
            '//ul[@class="sub-menu"]/li/a/@href'
        ).extract()
        # print('*' * 50)
        # print(one_link_list)
        # 把链接交给调度器入队列
        for one_link in one_link_list:
            yield scrapy.Request(
                url=one_link,
                callback=self.parse_two_link
            )

    # 解析二级页面
    def parse_two_link(self, response):
        # 基准xpath,匹配所有章节对象列表
        article_list = response.xpath('//article')
        # print(article_list)
        # 依次获取每个章节信息
        for article in article_list:
            # 创建item对象
            item = DaomuItem()
            info = article.xpath('./a/text()'). \
                extract_first().split()
            print(info)  # ['秦岭神树篇', '第一章', '老痒出狱']
            item['juan_name'] = info[0]
            item['zh_num'] = info[1]
            item['zh_name'] = info[2]
            item['zh_link'] = article.xpath('./a/@href').extract_first()
            # 把章节链接交给调度器

            yield scrapy.Request(
                url=item['zh_link'],
                # 把item传递到下一个解析函数
                meta={'item': item},
                callback=self.parse_three_link
            )

    # 解析三级页面
    def parse_three_link(self, response):
        item = response.meta['item']
        # 获取小说内容
        item['zh_content'] = '\n'.join(response.xpath(
            '//article[@class="article-content"]'
            '//p/text()'
        ).extract())

        yield item

        # '\n'.join(['第一段','第二段','第三段'])

pipelines.py

持久化处理

# -*- 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

class DaomuPipeline(object):
    def process_item(self, item, spider):

        filename = 'downloads/{}-{}-{}.txt'.format(
            item['juan_name'],
            item['zh_num'],
            item['zh_name']
        )

        f = open(filename,'w')
        f.write(item['zh_content'])
        f.close()

        return item