1 import scrapy
 2 import sys
 3
 4 class Jizhi(scrapy.Spider):
 5
 6     name = 'jizhi'
 7
 8     arg = ' '.join(sys.argv[3:])
 9
10     base_urls = "https://www.baidu.com"
11
12     start_urls = [
13         'https://www.baidu.com/s?{}'.format(arg)
14     ]
15
16     counter = 0
17
18     def parse(self, response):
19
20         result_lst = response.css("h3.t a::text")
21
22         for result in result_lst:
23             yield {
24                 'title':result.extract()
25             }
26
27         Jizhi.counter +=1
28
29         # next_page:css('a.n')
30
31         if Jizhi.counter == 5: return
32
33         next_page = response.css('a.n::attr(href)')
34
35         if len(next_page) == 2:
36             next_page_url = next_page[1].extract()
37         else:
38             next_page_url = next_page.extract_first()
39
40         yield scrapy.Request(self.base_urls + next_page_url, callback=self.parse)

2018-07-26 09:37:28 [scrapy.utils.log] INFO: Scrapy 1.5.0 started (bot: jizhi)
2018-07-26 09:37:28 [scrapy.utils.log] INFO: Versions: lxml 4.2.1.0, libxml2 2.9.8, cssselect 1.0.3, parsel 1.4.0, w3lib 1.19.0, Twisted 17.5.0, Python 3.6.5 |Anaconda, Inc.| (default, Mar 29 2018, 13:32:41) [MSC v.1900 64 bit (AMD64)], pyOpenSSL 18.0.0 (OpenSSL 1.0.2k  26 Jan 2017), cryptography 2.2.2, Platform Windows-10-10.0.17134-SP0
2018-07-26 09:37:28 [scrapy.crawler] INFO: Overridden settings: {'BOT_NAME': 'jizhi', 'NEWSPIDER_MODULE': 'jizhi.spiders', 'SPIDER_MODULES': ['jizhi.spiders']}
2018-07-26 09:37:29 [scrapy.middleware] INFO: Enabled extensions:
['scrapy.extensions.corestats.CoreStats','scrapy.extensions.telnet.TelnetConsole','scrapy.extensions.logstats.LogStats']
2018-07-26 09:37:29 [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']
2018-07-26 09:37:29 [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']
2018-07-26 09:37:29 [scrapy.middleware] INFO: Enabled item pipelines:
[]
2018-07-26 09:37:29 [scrapy.core.engine] INFO: Spider opened
2018-07-26 09:37:29 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
2018-07-26 09:37:29 [scrapy.extensions.telnet] DEBUG: Telnet console listening on 127.0.0.1:6023
2018-07-26 09:37:29 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://www.baidu.com/s?wd=jizhi> (referer: None)
2018-07-26 09:37:29 [scrapy.core.scraper] ERROR: Spider error processing <GET https://www.baidu.com/s?wd=jizhi> (referer: None)
Traceback (most recent call last):File "C:\Users\asus\Anaconda3\lib\site-packages\scrapy\utils\defer.py", line 102, in iter_errbackyield next(it)File "C:\Users\asus\Anaconda3\lib\site-packages\scrapy\spidermiddlewares\offsite.py", line 30, in process_spider_outputfor x in result:File "C:\Users\asus\Anaconda3\lib\site-packages\scrapy\spidermiddlewares\referer.py", line 339, in <genexpr>return (_set_referer(r) for r in result or ())File "C:\Users\asus\Anaconda3\lib\site-packages\scrapy\spidermiddlewares\urllength.py", line 37, in <genexpr>return (r for r in result or () if _filter(r))File "C:\Users\asus\Anaconda3\lib\site-packages\scrapy\spidermiddlewares\depth.py", line 58, in <genexpr>return (r for r in result or () if _filter(r))File "C:\Users\asus\Documents\GitHub\spider\jizhi\jizhi\spiders\jizhi.py", line 40, in parseyield scrapy.Request(self.base_urls + next_page_url, callback=self.parse)
TypeError: must be str, not NoneType
2018-07-26 09:37:29 [scrapy.core.engine] INFO: Closing spider (finished)
2018-07-26 09:37:29 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
{'downloader/request_bytes': 222,'downloader/request_count': 1,'downloader/request_method_count/GET': 1,'downloader/response_bytes': 872,'downloader/response_count': 1,'downloader/response_status_count/200': 1,'finish_reason': 'finished','finish_time': datetime.datetime(2018, 7, 26, 1, 37, 29, 585191),'log_count/DEBUG': 2,'log_count/ERROR': 1,'log_count/INFO': 7,'response_received_count': 1,'scheduler/dequeued': 1,'scheduler/dequeued/memory': 1,'scheduler/enqueued': 1,'scheduler/enqueued/memory': 1,'spider_exceptions/TypeError': 1,'start_time': datetime.datetime(2018, 7, 26, 1, 37, 29, 324887)}
2018-07-26 09:37:29 [scrapy.core.engine] INFO: Spider closed (finished)