123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325 |
- 2023-09-06 17:15:04 [scrapy.extensions.telnet] INFO: Telnet Password: 0a6f0691559c16c3
- 2023-09-06 17:15:04 [scrapy.middleware] INFO: Enabled extensions:
- ['scrapy.extensions.corestats.CoreStats',
- 'scrapy.extensions.telnet.TelnetConsole',
- 'scrapy.extensions.memusage.MemoryUsage',
- 'scrapy.extensions.logstats.LogStats']
- 2023-09-06 17:15:04 [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']
- 2023-09-06 17:15:04 [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']
- 2023-09-06 17:15:04 [scrapy.middleware] INFO: Enabled item pipelines:
- ['gzh_spider.pipelines.GzhSpiderPipeline']
- 2023-09-06 17:15:04 [scrapy.core.engine] INFO: Spider opened
- 2023-09-06 17:15:04 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
- 2023-09-06 17:15:04 [scrapy.extensions.telnet] INFO: Telnet console listening on 127.0.0.1:6023
- 2023-09-06 17:16:07 [scrapy.extensions.logstats] INFO: Crawled 19 pages (at 19 pages/min), scraped 0 items (at 0 items/min)
- 2023-09-06 17:17:05 [scrapy.extensions.logstats] INFO: Crawled 23 pages (at 4 pages/min), scraped 5 items (at 5 items/min)
- 2023-09-06 17:18:06 [scrapy.extensions.logstats] INFO: Crawled 44 pages (at 21 pages/min), scraped 5 items (at 0 items/min)
- 2023-09-06 17:19:07 [scrapy.extensions.logstats] INFO: Crawled 60 pages (at 16 pages/min), scraped 5 items (at 0 items/min)
- 2023-09-06 17:20:06 [scrapy.extensions.logstats] INFO: Crawled 79 pages (at 19 pages/min), scraped 5 items (at 0 items/min)
- 2023-09-06 17:21:06 [scrapy.extensions.logstats] INFO: Crawled 96 pages (at 17 pages/min), scraped 5 items (at 0 items/min)
- 2023-09-06 17:22:08 [scrapy.extensions.logstats] INFO: Crawled 114 pages (at 18 pages/min), scraped 5 items (at 0 items/min)
- 2023-09-06 17:23:05 [scrapy.extensions.logstats] INFO: Crawled 131 pages (at 17 pages/min), scraped 5 items (at 0 items/min)
- 2023-09-06 17:23:26 [scrapy.crawler] INFO: Received SIGINT, shutting down gracefully. Send again to force
- 2023-09-06 17:23:27 [scrapy.crawler] INFO: Received SIGINT twice, forcing unclean shutdown
- 2023-09-06 17:23:32 [scrapy.core.engine] INFO: Closing spider (shutdown)
- 2023-09-06 20:44:01 [scrapy.extensions.telnet] INFO: Telnet Password: 3ad0b6b5d835e2da
- 2023-09-06 20:44:01 [scrapy.middleware] INFO: Enabled extensions:
- ['scrapy.extensions.corestats.CoreStats',
- 'scrapy.extensions.telnet.TelnetConsole',
- 'scrapy.extensions.memusage.MemoryUsage',
- 'scrapy.extensions.logstats.LogStats']
- 2023-09-06 20:44:01 [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']
- 2023-09-06 20:44:01 [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']
- 2023-09-06 20:44:01 [scrapy.middleware] INFO: Enabled item pipelines:
- ['gzh_spider.pipelines.GzhSpiderPipeline']
- 2023-09-06 20:44:01 [scrapy.core.engine] INFO: Spider opened
- 2023-09-06 20:44:01 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
- 2023-09-06 20:44:01 [scrapy.extensions.telnet] INFO: Telnet console listening on 127.0.0.1:6023
- 2023-09-06 20:44:05 [scrapy.core.engine] INFO: Closing spider (finished)
- 2023-09-06 20:44:05 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
- {'downloader/request_bytes': 793,
- 'downloader/request_count': 1,
- 'downloader/request_method_count/POST': 1,
- 'downloader/response_bytes': 1682,
- 'downloader/response_count': 1,
- 'downloader/response_status_count/200': 1,
- 'elapsed_time_seconds': 3.419013,
- 'finish_reason': 'finished',
- 'finish_time': datetime.datetime(2023, 9, 6, 12, 44, 5, 194926),
- 'log_count/INFO': 10,
- 'memusage/max': 79691776,
- 'memusage/startup': 79691776,
- 'response_received_count': 1,
- 'scheduler/dequeued': 1,
- 'scheduler/dequeued/memory': 1,
- 'scheduler/enqueued': 1,
- 'scheduler/enqueued/memory': 1,
- 'start_time': datetime.datetime(2023, 9, 6, 12, 44, 1, 775913)}
- 2023-09-06 20:44:05 [scrapy.core.engine] INFO: Spider closed (finished)
- 2023-09-06 20:44:20 [scrapy.extensions.telnet] INFO: Telnet Password: 25808bb038f0748e
- 2023-09-06 20:44:20 [scrapy.middleware] INFO: Enabled extensions:
- ['scrapy.extensions.corestats.CoreStats',
- 'scrapy.extensions.telnet.TelnetConsole',
- 'scrapy.extensions.memusage.MemoryUsage',
- 'scrapy.extensions.logstats.LogStats']
- 2023-09-06 20:44:20 [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']
- 2023-09-06 20:44:20 [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']
- 2023-09-06 20:44:20 [scrapy.middleware] INFO: Enabled item pipelines:
- ['gzh_spider.pipelines.GzhSpiderPipeline']
- 2023-09-06 20:44:20 [scrapy.core.engine] INFO: Spider opened
- 2023-09-06 20:44:20 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
- 2023-09-06 20:44:21 [scrapy.extensions.telnet] INFO: Telnet console listening on 127.0.0.1:6023
- 2023-09-06 20:44:24 [scrapy.core.engine] INFO: Closing spider (finished)
- 2023-09-06 20:44:24 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
- {'downloader/request_bytes': 794,
- 'downloader/request_count': 1,
- 'downloader/request_method_count/POST': 1,
- 'downloader/response_bytes': 1682,
- 'downloader/response_count': 1,
- 'downloader/response_status_count/200': 1,
- 'elapsed_time_seconds': 3.429014,
- 'finish_reason': 'finished',
- 'finish_time': datetime.datetime(2023, 9, 6, 12, 44, 24, 428050),
- 'log_count/INFO': 10,
- 'memusage/max': 79478784,
- 'memusage/startup': 79478784,
- 'response_received_count': 1,
- 'scheduler/dequeued': 1,
- 'scheduler/dequeued/memory': 1,
- 'scheduler/enqueued': 1,
- 'scheduler/enqueued/memory': 1,
- 'start_time': datetime.datetime(2023, 9, 6, 12, 44, 20, 999036)}
- 2023-09-06 20:44:24 [scrapy.core.engine] INFO: Spider closed (finished)
- 2023-09-06 20:44:51 [scrapy.extensions.telnet] INFO: Telnet Password: e0d4a2f020af7209
- 2023-09-06 20:44:51 [scrapy.middleware] INFO: Enabled extensions:
- ['scrapy.extensions.corestats.CoreStats',
- 'scrapy.extensions.telnet.TelnetConsole',
- 'scrapy.extensions.memusage.MemoryUsage',
- 'scrapy.extensions.logstats.LogStats']
- 2023-09-06 20:44:51 [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']
- 2023-09-06 20:44:51 [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']
- 2023-09-06 20:44:51 [scrapy.middleware] INFO: Enabled item pipelines:
- ['gzh_spider.pipelines.GzhSpiderPipeline']
- 2023-09-06 20:44:51 [scrapy.core.engine] INFO: Spider opened
- 2023-09-06 20:44:51 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
- 2023-09-06 20:44:51 [scrapy.extensions.telnet] INFO: Telnet console listening on 127.0.0.1:6023
- 2023-09-06 20:44:54 [scrapy.core.engine] INFO: Closing spider (finished)
- 2023-09-06 20:44:54 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
- {'downloader/request_bytes': 794,
- 'downloader/request_count': 1,
- 'downloader/request_method_count/POST': 1,
- 'downloader/response_bytes': 1682,
- 'downloader/response_count': 1,
- 'downloader/response_status_count/200': 1,
- 'elapsed_time_seconds': 2.375282,
- 'finish_reason': 'finished',
- 'finish_time': datetime.datetime(2023, 9, 6, 12, 44, 54, 264424),
- 'log_count/INFO': 10,
- 'memusage/max': 79364096,
- 'memusage/startup': 79364096,
- 'response_received_count': 1,
- 'scheduler/dequeued': 1,
- 'scheduler/dequeued/memory': 1,
- 'scheduler/enqueued': 1,
- 'scheduler/enqueued/memory': 1,
- 'start_time': datetime.datetime(2023, 9, 6, 12, 44, 51, 889142)}
- 2023-09-06 20:44:54 [scrapy.core.engine] INFO: Spider closed (finished)
- 2023-09-06 20:45:16 [scrapy.extensions.telnet] INFO: Telnet Password: 6b6dc9a3ebbf3a7a
- 2023-09-06 20:45:16 [scrapy.middleware] INFO: Enabled extensions:
- ['scrapy.extensions.corestats.CoreStats',
- 'scrapy.extensions.telnet.TelnetConsole',
- 'scrapy.extensions.memusage.MemoryUsage',
- 'scrapy.extensions.logstats.LogStats']
- 2023-09-06 20:45:17 [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']
- 2023-09-06 20:45:17 [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']
- 2023-09-06 20:45:17 [scrapy.middleware] INFO: Enabled item pipelines:
- ['gzh_spider.pipelines.GzhSpiderPipeline']
- 2023-09-06 20:45:17 [scrapy.core.engine] INFO: Spider opened
- 2023-09-06 20:45:17 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
- 2023-09-06 20:45:17 [scrapy.extensions.telnet] INFO: Telnet console listening on 127.0.0.1:6023
- 2023-09-06 20:45:19 [scrapy.core.engine] INFO: Closing spider (finished)
- 2023-09-06 20:45:19 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
- {'downloader/request_bytes': 794,
- 'downloader/request_count': 1,
- 'downloader/request_method_count/POST': 1,
- 'downloader/response_bytes': 1682,
- 'downloader/response_count': 1,
- 'downloader/response_status_count/200': 1,
- 'elapsed_time_seconds': 2.296588,
- 'finish_reason': 'finished',
- 'finish_time': datetime.datetime(2023, 9, 6, 12, 45, 19, 326976),
- 'log_count/INFO': 10,
- 'memusage/max': 79036416,
- 'memusage/startup': 79036416,
- 'response_received_count': 1,
- 'scheduler/dequeued': 1,
- 'scheduler/dequeued/memory': 1,
- 'scheduler/enqueued': 1,
- 'scheduler/enqueued/memory': 1,
- 'start_time': datetime.datetime(2023, 9, 6, 12, 45, 17, 30388)}
- 2023-09-06 20:45:19 [scrapy.core.engine] INFO: Spider closed (finished)
- 2023-09-06 20:46:28 [scrapy.extensions.telnet] INFO: Telnet Password: 284d3bb7b6388af4
- 2023-09-06 20:46:28 [scrapy.middleware] INFO: Enabled extensions:
- ['scrapy.extensions.corestats.CoreStats',
- 'scrapy.extensions.telnet.TelnetConsole',
- 'scrapy.extensions.memusage.MemoryUsage',
- 'scrapy.extensions.logstats.LogStats']
- 2023-09-06 20:46:28 [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']
- 2023-09-06 20:46:28 [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']
- 2023-09-06 20:46:28 [scrapy.middleware] INFO: Enabled item pipelines:
- ['gzh_spider.pipelines.GzhSpiderPipeline']
- 2023-09-06 20:46:28 [scrapy.core.engine] INFO: Spider opened
- 2023-09-06 20:46:28 [scrapy.extensions.logstats] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
- 2023-09-06 20:46:28 [scrapy.extensions.telnet] INFO: Telnet console listening on 127.0.0.1:6023
- 2023-09-06 20:46:33 [scrapy.core.engine] INFO: Closing spider (finished)
- 2023-09-06 20:46:33 [scrapy.statscollectors] INFO: Dumping Scrapy stats:
- {'downloader/request_bytes': 233,
- 'downloader/request_count': 1,
- 'downloader/request_method_count/GET': 1,
- 'downloader/response_bytes': 7289,
- 'downloader/response_count': 1,
- 'downloader/response_status_count/200': 1,
- 'elapsed_time_seconds': 4.421293,
- 'finish_reason': 'finished',
- 'finish_time': datetime.datetime(2023, 9, 6, 12, 46, 33, 321213),
- 'httpcompression/response_bytes': 14978,
- 'httpcompression/response_count': 1,
- 'log_count/INFO': 10,
- 'memusage/max': 79659008,
- 'memusage/startup': 79659008,
- 'response_received_count': 1,
- 'scheduler/dequeued': 1,
- 'scheduler/dequeued/memory': 1,
- 'scheduler/enqueued': 1,
- 'scheduler/enqueued/memory': 1,
- 'start_time': datetime.datetime(2023, 9, 6, 12, 46, 28, 899920)}
- 2023-09-06 20:46:33 [scrapy.core.engine] INFO: Spider closed (finished)
- 2023-09-06 21:05:52 [scrapy.core.scraper] ERROR: Spider error processing <GET https://mp.weixin.qq.com/cgi-bin/appmsg> (referer: https://mp.weixin.qq.com/cgi-bin/searchbiz)
- Traceback (most recent call last):
- File "/Users/luojunhui/miniconda3/envs/Spider/lib/python3.9/site-packages/scrapy/utils/defer.py", line 260, in iter_errback
- yield next(it)
- File "/Users/luojunhui/miniconda3/envs/Spider/lib/python3.9/site-packages/scrapy/utils/python.py", line 336, in __next__
- return next(self.data)
- File "/Users/luojunhui/miniconda3/envs/Spider/lib/python3.9/site-packages/scrapy/utils/python.py", line 336, in __next__
- return next(self.data)
- File "/Users/luojunhui/miniconda3/envs/Spider/lib/python3.9/site-packages/scrapy/core/spidermw.py", line 106, in process_sync
- for r in iterable:
- File "/Users/luojunhui/miniconda3/envs/Spider/lib/python3.9/site-packages/scrapy/spidermiddlewares/offsite.py", line 28, in <genexpr>
- return (r for r in result or () if self._filter(r, spider))
- File "/Users/luojunhui/miniconda3/envs/Spider/lib/python3.9/site-packages/scrapy/core/spidermw.py", line 106, in process_sync
- for r in iterable:
- File "/Users/luojunhui/miniconda3/envs/Spider/lib/python3.9/site-packages/scrapy/spidermiddlewares/referer.py", line 352, in <genexpr>
- return (self._set_referer(r, response) for r in result or ())
- File "/Users/luojunhui/miniconda3/envs/Spider/lib/python3.9/site-packages/scrapy/core/spidermw.py", line 106, in process_sync
- for r in iterable:
- File "/Users/luojunhui/miniconda3/envs/Spider/lib/python3.9/site-packages/scrapy/spidermiddlewares/urllength.py", line 27, in <genexpr>
- return (r for r in result or () if self._filter(r, spider))
- File "/Users/luojunhui/miniconda3/envs/Spider/lib/python3.9/site-packages/scrapy/core/spidermw.py", line 106, in process_sync
- for r in iterable:
- File "/Users/luojunhui/miniconda3/envs/Spider/lib/python3.9/site-packages/scrapy/spidermiddlewares/depth.py", line 31, in <genexpr>
- return (r for r in result or () if self._filter(r, response, spider))
- File "/Users/luojunhui/miniconda3/envs/Spider/lib/python3.9/site-packages/scrapy/core/spidermw.py", line 106, in process_sync
- for r in iterable:
- File "/Users/luojunhui/cyber/gzh_spider/gzh_spider/spiders/gzh_author.py", line 161, in parse_video
- item['video_url'] = functions.find_video_url(article_url)
- File "/Users/luojunhui/cyber/gzh_spider/gzh_spider/functions/get_video_url.py", line 54, in find_video_url
- video_url = get_tencent_video_url(video_id)
- File "/Users/luojunhui/cyber/gzh_spider/gzh_spider/functions/get_video_url.py", line 72, in get_tencent_video_url
- url = response["vl"]["vi"][0]["ul"]["ui"][0]["url"]
- KeyError: 'vl'
|