import scrapy
class diploma(CrawlSpider):
name = "diploma"
allowed_domains="pikabu.ru"
start_urls = [
"https://pikabu.ru/hot"
]
def parse(self, response):
for sel in response.xpath("//div[@class='stories-feed__container']/article[@class='story']"):
item = DiplomaItem()
item['MainPageUrl'] = "https://pikabu.ru"+sel.xpath('div[2]/header[@class="story__header"]/h2/a/@href').extract()[0]
request = scrapy.Request(item['MainPageUrl'], callback=self.parsePage)
request.meta['item'] = item
yield request
def parsePage(self, response):
print("hHAHAHAHAH")
item = response.meta['item']
return item
Не вызывается функция parsePage. В консоле показываются ссылки, по которым идет запрос. Однако запрос посылается всего один раз, хотя ссылок найдено около 20.
Логи:
Konstantins-MBP:diploma mymac$ scrapy crawl diploma
2018-03-15 18:11:26 [scrapy.utils.log] INFO: Scrapy 1.5.0 started (bot: diploma)
2018-03-15 18:11:26 [scrapy.utils.log] INFO: Versions: lxml 4.1.1.0, libxml2 2.9.7, cssselect 1.0.3, parsel 1.4.0, w3lib 1.19.0, Twisted 17.9.0, Python 2.7.10 (default, Feb 7 2017, 00:08:15) - [GCC 4.2.1 Compatible Apple LLVM 8.0.0 (clang-800.0.34)], pyOpenSSL 17.5.0 (OpenSSL 1.1.0g 2 Nov 2017), cryptography 2.1.4, Platform Darwin-16.7.0-x86_64-i386-64bit
2018-03-15 18:11:26 [scrapy.crawler] INFO: Overridden settings: {'NEWSPIDER_MODULE': 'diploma.spiders', 'SPIDER_MODULES': ['diploma.spiders'], 'CONCURRENT_REQUESTS': 250, 'DOWNLOAD_DELAY': 5, 'BOT_NAME': 'diploma'}
2018-03-15 18:11:26 [scrapy.middleware] INFO: Enabled extensions:
['scrapy.extensions.memusage.MemoryUsage',
'scrapy.extensions.logstats.LogStats',
'scrapy.extensions.telnet.TelnetConsole',
'scrapy.extensions.corestats.CoreStats']
2018-03-15 18:11:26 [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']
2018-03-15 18:11:26 [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']
2018-03-15 18:11:26 [scrapy.middleware] INFO: Enabled item pipelines:
[]
2018-03-15 18:11:26 [scrapy.core.engine] INFO: Spider opened
2018-03-15 18:11:26 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
2018-03-15 18:11:26 [scrapy.extensions.telnet] DEBUG: Telnet console listening on 127.0.0.1:6023
2018-03-15 18:11:27 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://pikabu.ru/hot> (referer: None)
~~~
/story/kak_pogoda_50_na_50_5777191
2018-03-15 18:11:27 [scrapy.spidermiddlewares.offsite] DEBUG: Filtered offsite request to 'pikabu.ru': <GET https://pikabu.ru/story/kak_pogoda_50_na_50_5777191>
~~~
/story/chto_mozhet_poyti_ne_tak_5773824
~~~
/story/strannyiy_chelovek_5777133
~~~
/story/kogda_prepodavatelyu_pora_na_pensiyu_5774544
~~~
/story/kitaytsyi_uzhe_strakhuyutsya_ot_pochtyi_rossii_5774083
~~~
/story/dolzhnost_quotvladikquot_5769237
~~~
/story/popyitalsya_ubit_svidetelya_sharikovoy_ruchkoy__5774049
~~~
/story/otlichnaya_plitka_dlya_tualeta_5770880
~~~
/story/legendarnyiy_master_parkovki_5768086
~~~
/story/kak_ya_zabiral_ayfon_s_pochtyi_rossii_ili_khitryie_kitaytsyi_5776835
~~~
/story/kopirayterskie_slozhnosti_ch14_5776220
~~~
/story/novyiy_televizor_samsung_mozhet_slivatsya_s_poverkhnostyu_5775567
~~~
/story/neobyichnyiy_vkhod_v_podezd_5767500
~~~
/story/muzhchina_khotel_brosit_rabotu_chtobyi_ukhazhivat_za_bolnyim_rakom_syinom_no_kollegi_otrabotali_za_nego_3300_chasov_5770070
~~~
/story/kak_ya_uchilsya_khodit_5776376
~~~
/story/zabavnoe_dialogi_s_zakazchikami_5_5777655
~~~
/story/pro_metallurga_iz_magnitogorska_snyali_yepichnuyu_korotkometrazhku_5774307
~~~
/story/lovkost_ruk_i_nikakogo_moshennichestva_5777007
~~~
/story/kogda_nashelsya_novyiy_sponsor_5769282
~~~
/story/nikto_ne_chitaet_kharakteristiki_5771821
~~~
/story/posmotrite_na_yeti_shedevryi_5777462
2018-03-15 18:11:27 [scrapy.core.engine] INFO: Closing spider (finished)
2018-03-15 18:11:27 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
{'downloader/request_bytes': 211,
'downloader/request_count': 1,
'downloader/request_method_count/GET': 1,
'downloader/response_bytes': 39452,
'downloader/response_count': 1,
'downloader/response_status_count/200': 1,
'finish_reason': 'finished',
'finish_time': datetime.datetime(2018, 3, 15, 12, 11, 27, 860712),
'log_count/DEBUG': 3,
'log_count/INFO': 7,
'memusage/max': 46387200,
'memusage/startup': 46387200,
'offsite/domains': 1,
'offsite/filtered': 21,
'request_depth_max': 1,
'response_received_count': 1,
'scheduler/dequeued': 1,
'scheduler/dequeued/memory': 1,
'scheduler/enqueued': 1,
'scheduler/enqueued/memory': 1,
'start_time': datetime.datetime(2018, 3, 15, 12, 11, 26, 740826)}
2018-03-15 18:11:27 [scrapy.core.engine] INFO: Spider closed (finished)
Здесь видно что запрос отправился только по первой ссылке и все. Функция не вызвалась по ответу, или ответ не пришел. В чем причина?
