从网络上爬取小说《武动乾坤》(www.biqutxt.com)
【bqg.py】
# -*- coding: utf-8 -*-
import scrapy
class BqgSpider(scrapy.Spider):
name = 'bqg'
allowed_domains = ['biqutxt.com']
start_urls = ['https://www.biqutxt.com/69_69889/22672760.html']
def parse(self, response):
# 从第一张开始爬取;然后爬完第一张内容后,在爬取下一章节
title = response.xpath('//h1/text()').extract_first()
content = '\n'.join(response.xpath('//div[@id="content"]/text()').extract())
yield {'title': title, 'content': content}
# 爬取下一章小说的内容
next_url = response.xpath('//div[@class="bottem1"]/a[4]/@href').extract_first()
yield scrapy.Request('https://www.biqutxt.com/69_69899{}'.format(next_url))
# yield scrapy.Request(response.urljoin(next_url))
# -*- 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 XiaoshuoPipeline(object):
def open_spider(self, spider):
self.file = open('wdqk.txt', 'w', encoding='utf-8')
def process_item(self, item, spider):
info = item['title'] + '\n\n' + item['content'] + '\n'
self.file.write(info)
return item
def close_spider(self, spider):
self.file.close()
【items.py】
# -*- 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 XiaoshuoItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
pass
【begin.py】
# -*- 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 XiaoshuoItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
pass
# -*- coding: utf-8 -*-
# Scrapy settings for xiaoshuo project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# https://doc.scrapy.org/en/latest/topics/settings.html
# https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
BOT_NAME = 'xiaoshuo'
SPIDER_MODULES = ['xiaoshuo.spiders']
NEWSPIDER_MODULE = 'xiaoshuo.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
# 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://doc.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://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'xiaoshuo.middlewares.XiaoshuoSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'xiaoshuo.middlewares.XiaoshuoDownloaderMiddleware': 543,
#}
# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}
# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
'xiaoshuo.pipelines.XiaoshuoPipeline': 300,
}
# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.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://doc.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'