scrapy框架手动请求发送练习之爬取古诗文网论语全篇

本文链接：https://blog.csdn.net/Mypassword321/article/details/115909468

scrapy框架手动请求发送练习代码

爬取古诗文网论语全篇
url: https://so.gushiwen.org/guwen/book_46653FD803893E4F75696240258265D2.aspx

setting配置

# Scrapy settings for handReqPro project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://docs.scrapy.org/en/latest/topics/settings.html
#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'handReqPro'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'handReqPro (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

LOG_LEVEL = 'ERROR'

# 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://docs.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://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'handReqPro.middlewares.HandreqproSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'handReqPro.middlewares.HandreqproDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'handReqPro.pipelines.HandreqproPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.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://docs.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'

hand.py

import scrapy
from handReqPro.items import HandreqproItem

class HandSpider(scrapy.Spider):
    name = 'hand'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['https://so.gushiwen.org/guwen/bookv_46653FD803893E4F699E8628DEAEE3C0.aspx']
    page = 2
    path = '//*[@class="bookvmiddle"]/a[%d]/@href'
    def parse(self, response):
        p_list = response.xpath('//p/text()').extract()
        p_title = response.xpath('//b/text()').extract()
        item = HandreqproItem()
        item['title'] = p_title
        item['p'] = p_list
        yield item
        # print(1)
        new_path = format(self.path%self.page)
        self.page = 3
        try:
            new_url = response.xpath(new_path).extract()
        except BaseException:
            print('爬取失败！')

        else:
            if len(new_url):
                print(new_url)
                yield scrapy.Request(url=new_url[0],callback=self.parse)
            else:
                print('爬取完毕！')

item.py

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy


class HandreqproItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = scrapy.Field()
    p = scrapy.Field()

pipelines.py

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html


# useful for handling different item types with a single interface
from itemadapter import ItemAdapter


class HandreqproPipeline:
    fp = None
    def open_spider(self, spider):
        # print('我只会在开始时执行一次')
        self.fp = open('./论语.docx','w',encoding='utf-8')
    def close_spider(self, spider):
        # print('我只会在结束的时候执行一次')
        self.fp.close()
    def process_item(self, item, spider):
        p_str = ''.join(item['p'])
        # print(p_str)
        title = item['title']
        print(title[0])
        self.fp.write(title[0]+':'+p_str+'\n\n\n')
        return item