python scrapy basic mapcompose

scrapy startproject crawl_novel cd crawl_novel/ cd crawl_novel/ cd spiders scrapy genspider basic www cd .. vi items.py

-- coding: utf-8 --

import scrapy class CrawlNovelItem(scrapy.Item): # Primary fields title = scrapy.Field() author = scrapy.Field() classify = scrapy.Field() recommend = scrapy.Field() chapter_urls = scrapy.Field()

代码语言：javascript复制

# Calculated fields
chapter = scrapy.Field()

# Housekeeping fields
url = scrapy.Field()
project = scrapy.Field()
spider = scrapy.Field()
server = scrapy.Field()
date = scrapy.Field()

vi basic.py

-- coding: utf-8 --

import datetime import socket from urllib.parse import urlparse,urljoin

import scrapy from scrapy.loader import ItemLoader from scrapy.loader.processors import MapCompose, Join

from crawl_novel.items import CrawlNovelItem

class BasicSpider(scrapy.Spider): name = 'basic' allowed_domains = ['www'] start_urls = ['http://www.biquge.info/22_22559/']

代码语言：javascript复制

def parse(self, response):
    # 定义装载器
    l = ItemLoader(item=CrawlNovelItem(), response=response)
    # 使用处理器
    # 去除首位空白符，使结果按照收尾标题格式
    l.add_xpath('title', '//h1[1]/text()', MapCompose(str.strip, str.title))
    l.add_xpath('author', '//*[@id="info"]/p[1]/text()', MapCompose(str.strip))
    l.add_xpath('classify', '//*[@id="info"]/p[2]/text()', MapCompose(str.strip))
    # 将多个结果连接在一起
    l.add_xpath('recommend', '//*[@id="listtj"]//text()', Join())
    # 使用lambda表达式（以response.url为基础，将相对路径i转化为绝对路径）
    l.add_xpath('chapter_urls', '//*[@id="list"]//a/@href', MapCompose(lambda i: urljoin(response.url, i)))
    # 添加管理字段
    l.add_value('url', response.url)
    l.add_value('project', self.settings.get('BOT_NAME'))
    l.add_value('spider', self.name)
    l.add_value('server', socket.gethostname())
    l.add_value('date', datetime.datetime.now())
    
    return l.load_item()

scrapy python 编程算法

0 人点赞