scrapy(itcast)

import scrapy


class ItcastSpider(scrapy.Spider):
    ###爬虫名
    name = 'itcast'
    #运行爬取的范围
    allowed_domains = ['itcas.cn']
    #最开始请求的地址
    start_urls = ['http://www.itcast.cn/channel/teacher.shtml']

        ###处理start_urls响应
    def parse(self, response):
        ########extract()提取xpath数据
        # res = response.xpath("//div[@class='tea_con']//h3/text()").extract()
        # print(res)

        li_list = response.xpath("//div[@class='tea_con']//li")
        for li in li_list:
            item={}
            #####scrapy多个爬虫区分方式1
            item["come_from"]="itcast"
            ##.extract_first() 和 .extract()[0] 作用一样自动提起第一个值
            ####如果爬取数据没有extract_first() 返回nono
            item["name"]=li.xpath(".//h3/text()").extract_first()
            item["title"]=li.xpath(".//h4/text()").extract()[0]
            # print(item)
            ###item数据需要传到pipelines处理
            yield item

 

 

# Define your item pipelines here
#管道
# 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 MyspiderPipeline:
    def process_item(self, item, spider):
        # print(item)
        item["hellow"]="world"
        return item
class MyspiderPipeline1:
    def process_item(self, item, spider):
        print(item)
        return item

 #####scrapy多个爬虫区分方式 1
# class MyspiderPipeline:
#     def process_item(self, item, spider):
#         if item["come_frome"]=="itcast":
#         return item
#
# class MyspiderPipeline:
#     def process_item(self, item, spider):
#         if spider.name == "itcast":

 

# Scrapy settings for myspider 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 = 'myspider'

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

###设置输出日志等级
LOG_LEVEL = 'WARNING'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'myspider (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = True

# 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 = {
#    'myspider.middlewares.MyspiderSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'myspider.middlewares.MyspiderDownloaderMiddleware': 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
####开启pipelines,300可以理解为优先级
ITEM_PIPELINES = {
   'myspider.pipelines.MyspiderPipeline': 300,
   'myspider.pipelines.MyspiderPipeline1': 301,
}

# 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'