scrapy 爬取空值

DEBUG: Redirecting (301) to from

import scrapy


class S1Spider(scrapy.Spider):
    name = 's1'  # 爬虫的名字
    allowed_domains = ['blog.csdn.net'] # 如果URL地址的HOST不属于allowed_domains,则过滤掉该请求
    start_urls = ['http://blog.csdn.net/'] # 项目启动时，访问的URL地址

    def parse(self, response):
        print('-'*90)
        # print(response.body)
        # print('-'*40)# 访问start_urls,得到响应后调用的方案，response为响应对象
        print(response.xpath('//div[@class="nav_com"]/ul/li/a/text()').extract())
        print('-' * 90)
        # print('-'*40)# 对response 做Xpath

    # 爬虫开始，执行的方法，相当于start_urls
    # def start_requests(self):      # 向调度器发送一个request对象
    #     yield scrapy.Request(
    #         url=('http://edu.csdn.net'),   # 请求地址，默认是GET方式
    #         callback=self.parse2,      # 得到响应后，调用的函数
    #     )
    # def parse2(self,response):          # 得到响应后，调用的函数
    #     print(response.xpath('//div[@id="nav_com"]//li/a/text()'))           # 得到字节类型 的数据

D:\爬虫\scrapy_spider1\myscrapy1>scrapy crawl s1
2020-10-03 08:25:48 [scrapy.utils.log] INFO: Scrapy 2.3.0 started (bot: myscrapy1)
2020-10-03 08:25:48 [scrapy.utils.log] INFO: Versions: lxml 4.5.2.0, libxml2 2.9.5, cssselect 1.1.0, parsel 1.6.0,
w3lib 1.22.0, Twisted 20.3.0, Python 3.8.5 (tags/v3.8.5:580fbb0, Jul 20 2020, 15:43:08) [MSC v.1926 32 bit (Intel)]
, pyOpenSSL 19.1.0 (OpenSSL 1.1.1h  22 Sep 2020), cryptography 3.1.1, Platform Windows-10-10.0.18362-SP0
2020-10-03 08:25:48 [scrapy.utils.log] DEBUG: Using reactor: twisted.internet.selectreactor.SelectReactor
2020-10-03 08:25:48 [scrapy.crawler] INFO: Overridden settings:
{
     'BOT_NAME': 'myscrapy1',
 'NEWSPIDER_MODULE': 'myscrapy1.spiders',
 'SPIDER_MODULES': ['myscrapy1.spiders'],
 'USER_AGENT': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like '
               'Gecko) Chrome/41.0.2228.0 Safari/537.36'}
2020-10-03 08:25:49 [scrapy.extensions.telnet] INFO: Telnet Password: b9d51701061fdac5
2020-10-03 08:25:49 [scrapy.middleware] INFO: Enabled extensions:
['scrapy.extensions.corestats.CoreStats',
 'scrapy.extensions.telnet.TelnetConsole',
 'scrapy.extensions.logstats.LogStats']
2020-10-03 08:25:49 [scrapy.middleware] INFO: Enabled downloader middlewares:
['scrapy.downloadermiddlewares.httpauth.HttpAuthMiddleware',
 'scrapy.downloadermiddlewares.downloadtimeout.DownloadTimeoutMiddleware',
 'scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware',
 'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware',
 'scrapy.downloadermiddlewares.retry.RetryMiddleware',
 'scrapy.downloadermiddlewares.redirect.MetaRefreshMiddleware',
 'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware',
 'scrapy.downloadermiddlewares.redirect.RedirectMiddleware',
 'scrapy.downloadermiddlewares.cookies.CookiesMiddleware',
 'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware',
 'scrapy.downloadermiddlewares.stats.DownloaderStats']
2020-10-03 08:25:49 [scrapy.middleware] INFO: Enabled spider middlewares:
['scrapy.spidermiddlewares.httperror.HttpErrorMiddleware',
 'scrapy.spidermiddlewares.offsite.OffsiteMiddleware',
 'scrapy.spidermiddlewares.referer.RefererMiddleware',
 'scrapy.spidermiddlewares.urllength.UrlLengthMiddleware',
 'scrapy.spidermiddlewares.depth.DepthMiddleware']
2020-10-03 08:25:49 [scrapy.middleware] INFO: Enabled item pipelines:
[]
2020-10-03 08:25:49 [scrapy.core.engine] INFO: Spider opened
2020-10-03 08:25:49 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 item
s/min)
2020-10-03 08:25:49 [scrapy.extensions.telnet] INFO: Telnet console listening on 127.0.0.1:6023
2020-10-03 08:25:49 [scrapy.downloadermiddlewares.redirect] DEBUG: Redirecting (301) to <GET https://blog.csdn.net/
> from <GET http://blog.csdn.net/>
2020-10-03 08:25:50 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://blog.csdn.net/> (referer: None)
------------------------------------------------------------------------------------------
[]
------------------------------------------------------------------------------------------
2020-10-03 08:25:50 [scrapy.core.engine] INFO: Closing spider (finished)
2020-10-03 08:25:50 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
{
     'downloader/request_bytes': 558,
 'downloader/request_count': 2,
 'downloader/request_method_count/GET': 2,
 'downloader/response_bytes': 14583,
 'downloader/response_count': 2,
 'downloader/response_status_count/200': 1,
 'downloader/response_status_count/301': 1,
 'elapsed_time_seconds': 0.527588,
 'finish_reason': 'finished',
 'finish_time': datetime.datetime(2020, 10, 3, 0, 25, 50, 372656),
 'log_count/DEBUG': 2,
 'log_count/INFO': 10,
 'response_received_count': 1,
 'scheduler/dequeued': 2,
 'scheduler/dequeued/memory': 2,
 'scheduler/enqueued': 2,
 'scheduler/enqueued/memory': 2,
 'start_time': datetime.datetime(2020, 10, 3, 0, 25, 49, 845068)}
2020-10-03 08:25:50 [scrapy.core.engine] INFO: Spider closed (finished)

爬取空值