Last active
October 10, 2017 06:39
-
-
Save JoaoGFarias/61602f8f68e57e686f96b800517039dd to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
2017-10-10 03:19:09 [scrapy.core.engine] INFO: Closing spider (closespider_pagecount) | |
2017-10-10 03:19:09 [scrapy.core.engine] DEBUG: Crawled (200) <GET https://www.brandsmartusa.com/samsung/215588/galaxy+j7+prime+smartphone.htm> (referer: None) ['cached'] | |
<extractor.BrandsMartUSAExtractor.BrandsMartUSAExtractor object at 0x10f559ac8> | |
name: Galaxy J7 Prime 5.5", 8MP Rear/5MP Front Camera, Octa Core Processor, 16GB Memory, 3GB RAM, 3300 mAh Battery, Android 6.0.1 Marshmallow Smartphone - Gold | |
model: | |
price: $149.00 | |
brand: Samsung | |
OS: Android 6.0 "Marshmallow" | |
color: Gold | |
network: MetroPCS | |
SIM_card_slot: Dual SIM | |
back_camera: 13.0 Megapixels (MP) | |
ROM: 16 GB | |
RAM: 3GB | |
screen_size: 5.5" | |
screen_resolution: 1920 x 1080 | |
battery_capacity: | |
battery_voltage: | |
weight: 6.0 oz | |
dimensions: 5.9 in x 3.0 in x 0.3 in | |
---------------------- | |
None | |
2017-10-10 03:19:10 [scrapy.core.scraper] ERROR: Spider error processing <GET https://www.brandsmartusa.com/samsung/215588/galaxy+j7+prime+smartphone.htm> (referer: None) | |
Traceback (most recent call last): | |
File "/usr/local/lib/python3.6/site-packages/scrapy/utils/defer.py", line 102, in iter_errback | |
yield next(it) | |
File "/usr/local/lib/python3.6/site-packages/scrapy/spidermiddlewares/offsite.py", line 29, in process_spider_output | |
for x in result: | |
File "/usr/local/lib/python3.6/site-packages/scrapy/spidermiddlewares/referer.py", line 339, in <genexpr> | |
return (_set_referer(r) for r in result or ()) | |
File "/usr/local/lib/python3.6/site-packages/scrapy/spidermiddlewares/urllength.py", line 37, in <genexpr> | |
return (r for r in result or () if _filter(r)) | |
File "/usr/local/lib/python3.6/site-packages/scrapy/spidermiddlewares/depth.py", line 58, in <genexpr> | |
return (r for r in result or () if _filter(r)) | |
File "/Users/joaofarias/Documents/UFPE/jgfd-tpshc_IF962-proj1/crawler/spiders/Anchor_Spider.py", line 19, in parse | |
self.add_page(response) | |
File "/Users/joaofarias/Documents/UFPE/jgfd-tpshc_IF962-proj1/crawler/spiders/Smartphone_Spider.py", line 94, inadd_page | |
page.insertCrawlerInfo(self.name) | |
File "/Users/joaofarias/Documents/UFPE/jgfd-tpshc_IF962-proj1/crawler/database/Page.py", line 110, in insertCrawlerInfo | |
self.save_smartphone_data(cursor, self.smartphone_data) | |
File "/Users/joaofarias/Documents/UFPE/jgfd-tpshc_IF962-proj1/crawler/database/Page.py", line 76, in save_smartphone_data | |
values = smartphone_data.get_data_as_tuple() | |
AttributeError: 'NoneType' object has no attribute 'get_data_as_tuple' | |
2017-10-10 03:19:10 [scrapy.statscollectors] INFO: Dumping Scrapy stats: | |
{'downloader/request_bytes': 563, | |
'downloader/request_count': 2, | |
'downloader/request_method_count/GET': 2, | |
'downloader/response_bytes': 25538, | |
'downloader/response_count': 2, | |
'downloader/response_status_count/200': 2, | |
'finish_reason': 'closespider_pagecount', | |
'finish_time': datetime.datetime(2017, 10, 10, 6, 19, 10, 197076), | |
'httpcache/hit': 2, | |
'log_count/DEBUG': 4, | |
'log_count/ERROR': 1, | |
'log_count/INFO': 7, | |
'memusage/max': 76435456, | |
'memusage/startup': 76435456, | |
'response_received_count': 2, | |
'scheduler/dequeued': 1, | |
'scheduler/dequeued/memory': 1, | |
'scheduler/enqueued': 1, | |
'scheduler/enqueued/memory': 1, | |
'spider_exceptions/AttributeError': 1, | |
'start_time': datetime.datetime(2017, 10, 10, 6, 19, 9, 433662)} | |
2017-10-10 03:19:10 [scrapy.core.engine] INFO: Spider closed (closespider_pagecount) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
2017-10-10 03:39:32 [scrapy.core.scraper] ERROR: Spider error processing <GET https://www.brandsmartusa.com/headphones/on+sale+items/_/N-103504> (referer: https://www.brandsmartusa.com/headphones/bluetooth+headphones/_/N-102991) | |
Traceback (most recent call last): | |
File "/usr/local/lib/python3.6/site-packages/scrapy/utils/defer.py", line 102, in iter_errback | |
yield next(it) | |
File "/usr/local/lib/python3.6/site-packages/scrapy/spidermiddlewares/offsite.py", line 29, in process_spider_output | |
for x in result: | |
File "/usr/local/lib/python3.6/site-packages/scrapy/spidermiddlewares/referer.py", line 339, in <genexpr> | |
return (_set_referer(r) for r in result or ()) | |
File "/usr/local/lib/python3.6/site-packages/scrapy/spidermiddlewares/urllength.py", line 37, in <genexpr> | |
return (r for r in result or () if _filter(r)) | |
File "/usr/local/lib/python3.6/site-packages/scrapy/spidermiddlewares/depth.py", line 58, in <genexpr> | |
return (r for r in result or () if _filter(r)) | |
File "/Users/joaofarias/Documents/UFPE/jgfd-tpshc_IF962-proj1/crawler/spiders/Anchor_Spider.py", line 19, in parse | |
self.add_page(response) | |
File "/Users/joaofarias/Documents/UFPE/jgfd-tpshc_IF962-proj1/crawler/spiders/Smartphone_Spider.py", line 91, inadd_page | |
page.smartphone_data = extractor.extract(response) | |
File "../extractor/BrandsMartUSAExtractor.py", line 23, in extract | |
smartphone.price = price[price.rfind('$'):] | |
AttributeError: 'NoneType' object has no attribute 'rfind' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment