Python Scrapy实战之古诗文网的爬取

scrapy startproject prose

cd prose
scrapy genspider gs gushiwen.cn

# Scrapy settings for prose 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 = 'prose'

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

LOG_LEVEL = "WARNING"


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

# 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://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 1
# 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 = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36',
    '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 = {
#    'prose.middlewares.ProseSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'prose.middlewares.ProseDownloaderMiddleware': 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 = {
   'prose.pipelines.ProsePipeline': 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'

import scrapy
from prose.items import ProseItem


class GsSpider(scrapy.Spider):
    name = 'gs'
    allowed_domains = ['gushiwen.cn']
    start_urls = ['https://www.gushiwen.cn/default_1.aspx']

    # 解析列表页面
    def parse(self, response):
        # 一个class="sons"对应的是一首诗
        div_list = response.xpath('//div[@class="left"]/div[@class="sons"]')
        for div in div_list:
            try:
                # 提取诗词标题信息
                title = div.xpath('.//b/text()').get()
                # 提取作者和朝代
                source = div.xpath('.//p[@class="source"]/a/text()').getall()
                # 作者
                # replace
                author = source[0]
                # 朝代
                dynasty = source[1]
                content_list = div.xpath('.//div[@class="contson"]//text()').getall()
                content_plus = ''.join(content_list).strip()
                # 拿到诗词详情页面的url
                detail_url = div.xpath('.//p/a/@href').get()
                item = ProseItem(title=title, author=author, dynasty=dynasty, content_plus=content_plus, detail_url=detail_url)
                # print(item)
                yield scrapy.Request(
                    url=detail_url,
                    callback=self.parse_detail,
                    meta={'prose_item': item}
                )
            except:
                pass

        next_url = response.xpath('//a[@id="amore"]/@href').get()
        if next_url:
            print(next_url)
            yield scrapy.Request(
                url=next_url,
                callback=self.parse
            )


    # 用于解析详情页面
    def parse_detail(self, response):
        item = response.meta.get('prose_item')
        translation = response.xpath('//div[@class="sons"]/div[@class="contyishang"]/p//text()').getall()
        item['translation'] = ''.join(translation).strip()
        # print(item)
        yield item
        pass

import scrapy


class ProseItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    # 标题
    title = scrapy.Field()
    # 作者
    author = scrapy.Field()
    # 朝代
    dynasty = scrapy.Field()
    # 诗词内容
    content_plus = scrapy.Field()
    # 详情页面的url
    detail_url = scrapy.Field()
    # 译文
    translation = scrapy.Field()
    pass

from itemadapter import ItemAdapter
import json


class ProsePipeline:
    def __init__(self):
        self.f = open('gs.txt', 'w', encoding='utf-8')

    def process_item(self, item, spider):
    	# 将item先转化为字典， 再转化为 json类型的字符串
        item_json = json.dumps(dict(item), ensure_ascii=False)
        self.f.write(item_json + '\n')
        return item

    def close_spider(self, spider):
        self.f.close()

from scrapy import cmdline

cmdline.execute('scrapy crawl gs'.split())