从0开始学习scrapy框架——（六）item的实例——阳光政务平台爬虫

’http://wz.sun0769.com/political/index/politicsNewest’
需求：爬取该网站的标题，链接，时间和详情页面的内容

settings.py：

# Scrapy settings for yangguang 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 = 'yangguang'

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

LOG_LEVEL = 'ERROR'
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.114 Safari/537.36 Edg/89.0.774.68'

# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'yangguang (+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 = 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 = {
#    'yangguang.middlewares.YangguangSpiderMiddleware': 543,
#}

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

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 YangguangPipeline:
    def process_item(self, item, spider):
        print(item)
        return item

yg.py

import scrapy

from yangguang.items import YangguangItem
class YgSpider(scrapy.Spider):
    name = 'yg'
    # allowed_domains = ['www.ya.com']
    start_urls = ['http://wz.sun0769.com/political/index/politicsNewest']
    # url = 'http://wz.sun0769.com/political/index/politicsNewest?id=1&page=1'
    page_num = 2
    def parse(self, response):
        # 分组
        li_list = response.xpath('/html/body/div[2]/div[3]/ul[2]/li')
        for li in li_list:
            item = YangguangItem()
            item['title'] = li.xpath('./span[3]/a/text()').extract_first()
            item['href'] = 'http://wz.sun0769.com' + li.xpath('./span[3]/a/@href').extract_first()
            item['publish_time'] = li.xpath('./span[5]/text()').extract_first()

            yield scrapy.Request(
                item['href'],
                callback= self.parse_detail,
                meta = {
                    'item':item
                }
            )

        new_url = f'http://wz.sun0769.com/political/index/politicsNewest?id=1&page={self.page_num}'
        self.page_num += 1
        if self.page_num <= 5:
            yield scrapy.Request(
                new_url,
                callback=self.parse
            )


    def parse_detail(self,response): # 处理详情页
        item = response.meta['item']
        item['content'] = response.xpath('/html/body/div[3]/div[2]/div[2]/div[2]/pre//text()').extract()
        # print(item)
        yield item