练手实例：Scrapy爬取一本完整小说

戳这里查看此小说
整体都很简单，没啥多说的，10分钟搞定
外循环在主页面找url进行拼接，小循环解析详细页内容提取小说文本。



biquge.py

import scrapy
from scrapy.selector import Selector

class BiqugeSpider(scrapy.Spider):
    name = 'biquge'
    allowed_domains = ['biquge.info']
    start_urls = ['https://www.biquge.info/34_34370/']

    def parse(self, response):
        selector = Selector(response)
        find_all = selector.xpath("/html/body/div[@id='wrapper']/div[@class='box_con'][2]/div[@id='list']/dl/dd")
        for section in find_all:
            href = section.xpath('.//@href').extract_first()
            real_url = response.urljoin(href)
            request = scrapy.Request(real_url,callback=self.parse_detail)
            yield request
            # print(real_url)测试成功


    def parse_detail(self,response):
        selector = Selector(response)
        content_list = selector.xpath('//div[@id="content"]/text()').extract()
        # for real in content:
            # print(real)测试成功
        content = '\n'.join(content_list)
        item = dict()
        item['content'] = content
        print(content)
        yield item
        

itempipins.py

class XiaoshuoPipeline(object):
    def __init__(self):
        self.file = open('D://女帝直播攻略.txt','a+',encoding='utf-8')
        
    def process_item(self, item, spider):
        self.file.write(item['content'])
        return item

settings.py

LOG_LEVEL = 'WARNING'
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'

结果


真的不得不佩服scrapy的速度，太猛了，上了个厕所就爬完了一千七百多章。。