runCallbacks
current.result = callback(current.result, *args, **kw)
File "C:\Users\martlee2\Downloads\google.py", line 24, in parse
sel = Selector(response)
NameError: global name 'Selector' is not defined
2016-06-02 14:46:23 [scrapy] INFO: Closing spider (finished)
2016-06-02 14:46:23 [scrapy] INFO: Dumping Scrapy stats:
{'downloader/request_bytes': 491,
'downloader/request_count': 2,
'downloader/request_method_count/GET': 2,
'downloader/response_bytes': 13623,
'downloader/response_count': 2,
'downloader/response_status_count/200': 1,
'downloader/response_status_count/302': 1,
'finish_reason': 'finished',
'finish_time': datetime.datetime(2016, 6, 2, 6, 46, 23, 25000),
'log_count/DEBUG': 3,
'log_count/ERROR': 1,
'log_count/INFO': 7,
'response_received_count': 1,
'scheduler/dequeued': 2,
'scheduler/dequeued/memory': 2,
'scheduler/enqueued': 2,
'scheduler/enqueued/memory': 2,
'spider_exceptions/NameError': 1,
'start_time': datetime.datetime(2016, 6, 2, 6, 46, 22, 3000)}
2016-06-02 14:46:23 [scrapy] INFO: Spider closed (finished)
C:\Users\martlee2\Downloads>scrapy runspider google.py > error.txt
2016-06-02 14:49:25 [scrapy] INFO: Scrapy 1.1.0 started (bot: scrapybot)
2016-06-02 14:49:25 [scrapy] INFO: Overridden settings: {}
2016-06-02 14:49:25 [scrapy] INFO: Enabled extensions:
['scrapy.extensions.logstats.LogStats',
'scrapy.extensions.telnet.TelnetConsole',
'scrapy.extensions.corestats.CoreStats']
2016-06-02 14:49:25 [scrapy] INFO: Enabled downloader middlewares:
['scrapy.downloadermiddlewares.httpauth.HttpAuthMiddleware',
'scrapy.downloadermiddlewares.downloadtimeout.DownloadTimeoutMiddleware',
'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware',
'scrapy.downloadermiddlewares.retry.RetryMiddleware',
'scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware',
'scrapy.downloadermiddlewares.redirect.MetaRefreshMiddleware',
'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware',
'scrapy.downloadermiddlewares.redirect.RedirectMiddleware',
'scrapy.downloadermiddlewares.cookies.CookiesMiddleware',
'scrapy.downloadermiddlewares.chunked.ChunkedTransferMiddleware',
'scrapy.downloadermiddlewares.stats.DownloaderStats']
2016-06-02 14:49:25 [scrapy] INFO: Enabled spider middlewares:
['scrapy.spidermiddlewares.httperror.HttpErrorMiddleware',
'scrapy.spidermiddlewares.offsite.OffsiteMiddleware',
'scrapy.spidermiddlewares.referer.RefererMiddleware',
'scrapy.spidermiddlewares.urllength.UrlLengthMiddleware',
'scrapy.spidermiddlewares.depth.DepthMiddleware']
2016-06-02 14:49:25 [scrapy] INFO: Enabled item pipelines:
[]
2016-06-02 14:49:25 [scrapy] INFO: Spider opened
2016-06-02 14:49:25 [scrapy] INFO: Crawled 0 pages (at 0 pages/min),
scraped 0
tems (at 0 items/min)
2016-06-02 14:49:25 [scrapy] DEBUG: Telnet console listening on
127.0.0.1:6023
2016-06-02 14:49:26 [scrapy] DEBUG: Redirecting (302) to <GET
https://www.googl
.com.hk/search?q=robot&gws_rd=cr&ei=oNZPV_voLoWX0gSohahw> from <GET
https://www
google.com/search?q=robot>
2016-06-02 14:49:26 [scrapy] DEBUG: Crawled (200) <GET
https://www.google.com.h
/search?q=robot&gws_rd=cr&ei=oNZPV_voLoWX0gSohahw> (referer: None)
2016-06-02 14:49:26 [scrapy] ERROR: Spider error processing <GET
https://www.go
gle.com.hk/search?q=robot&gws_rd=cr&ei=oNZPV_voLoWX0gSohahw> (referer: None)
Traceback (most recent call last):
File "c:\python27\lib\site-packages\twisted\internet\defer.py", line 588,
in
runCallbacks
current.result = callback(current.result, *args, **kw)
File "C:\Users\martlee2\Downloads\google.py", line 24, in parse
sel = Selector(response)
NameError: global name 'Selector' is not defined
2016-06-02 14:49:27 [scrapy] INFO: Closing spider (finished)
2016-06-02 14:49:27 [scrapy] INFO: Dumping Scrapy stats:
{'downloader/request_bytes': 489,
'downloader/request_count': 2,
'downloader/request_method_count/GET': 2,
'downloader/response_bytes': 13446,
'downloader/response_count': 2,
'downloader/response_status_count/200': 1,
'downloader/response_status_count/302': 1,
'finish_reason': 'finished',
'finish_time': datetime.datetime(2016, 6, 2, 6, 49, 27, 11000),
'log_count/DEBUG': 3,
'log_count/ERROR': 1,
'log_count/INFO': 7,
'response_received_count': 1,
'scheduler/dequeued': 2,
'scheduler/dequeued/memory': 2,
'scheduler/enqueued': 2,
'scheduler/enqueued/memory': 2,
'spider_exceptions/NameError': 1,
'start_time': datetime.datetime(2016, 6, 2, 6, 49, 25, 877000)}
2016-06-02 14:49:27 [scrapy] INFO: Spider closed (finished)
C:\Users\martlee2\Downloads>scrapy runspider google.py >> error.txt
2016-06-02 14:49:44 [scrapy] INFO: Scrapy 1.1.0 started (bot: scrapybot)
2016-06-02 14:49:44 [scrapy] INFO: Overridden settings: {}
2016-06-02 14:49:44 [scrapy] INFO: Enabled extensions:
['scrapy.extensions.logstats.LogStats',
'scrapy.extensions.telnet.TelnetConsole',
'scrapy.extensions.corestats.CoreStats']
2016-06-02 14:49:44 [scrapy] INFO: Enabled downloader middlewares:
['scrapy.downloadermiddlewares.httpauth.HttpAuthMiddleware',
'scrapy.downloadermiddlewares.downloadtimeout.DownloadTimeoutMiddleware',
'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware',
'scrapy.downloadermiddlewares.retry.RetryMiddleware',
'scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware',
'scrapy.downloadermiddlewares.redirect.MetaRefreshMiddleware',
'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware',
'scrapy.downloadermiddlewares.redirect.RedirectMiddleware',
'scrapy.downloadermiddlewares.cookies.CookiesMiddleware',
'scrapy.downloadermiddlewares.chunked.ChunkedTransferMiddleware',
'scrapy.downloadermiddlewares.stats.DownloaderStats']
2016-06-02 14:49:44 [scrapy] INFO: Enabled spider middlewares:
['scrapy.spidermiddlewares.httperror.HttpErrorMiddleware',
'scrapy.spidermiddlewares.offsite.OffsiteMiddleware',
'scrapy.spidermiddlewares.referer.RefererMiddleware',
'scrapy.spidermiddlewares.urllength.UrlLengthMiddleware',
'scrapy.spidermiddlewares.depth.DepthMiddleware']
2016-06-02 14:49:44 [scrapy] INFO: Enabled item pipelines:
[]
2016-06-02 14:49:44 [scrapy] INFO: Spider opened
2016-06-02 14:49:44 [scrapy] INFO: Crawled 0 pages (at 0 pages/min),
scraped 0
tems (at 0 items/min)
2016-06-02 14:49:44 [scrapy] DEBUG: Telnet console listening on
127.0.0.1:6023
2016-06-02 14:49:45 [scrapy] DEBUG: Redirecting (302) to <GET
https://www.googl
.com.hk/search?q=robot&gws_rd=cr&ei=s9ZPV8OhMYjV0ATGkYngDw> from <GET
https://w
w.google.com/search?q=robot>
2016-06-02 14:49:45 [scrapy] DEBUG: Crawled (200) <GET
https://www.google.com.h
/search?q=robot&gws_rd=cr&ei=s9ZPV8OhMYjV0ATGkYngDw> (referer: None)
2016-06-02 14:49:45 [scrapy] ERROR: Spider error processing <GET
https://www.go
gle.com.hk/search?q=robot&gws_rd=cr&ei=s9ZPV8OhMYjV0ATGkYngDw> (referer:
None)
Traceback (most recent call last):
File "c:\python27\lib\site-packages\twisted\internet\defer.py", line 588,
in
runCallbacks
current.result = callback(current.result, *args, **kw)
File "C:\Users\martlee2\Downloads\google.py", line 24, in parse
sel = Selector(response)
NameError: global name 'Selector' is not defined
2016-06-02 14:49:45 [scrapy] INFO: Closing spider (finished)
2016-06-02 14:49:45 [scrapy] INFO: Dumping Scrapy stats:
{'downloader/request_bytes': 491,
'downloader/request_count': 2,
'downloader/request_method_count/GET': 2,
'downloader/response_bytes': 13444,
'downloader/response_count': 2,
'downloader/response_status_count/200': 1,
'downloader/response_status_count/302': 1,
'finish_reason': 'finished',
'finish_time': datetime.datetime(2016, 6, 2, 6, 49, 45, 784000),
'log_count/DEBUG': 3,
'log_count/ERROR': 1,
'log_count/INFO': 7,
'response_received_count': 1,
'scheduler/dequeued': 2,
'scheduler/dequeued/memory': 2,
'scheduler/enqueued': 2,
'scheduler/enqueued/memory': 2,
'spider_exceptions/NameError': 1,
'start_time': datetime.datetime(2016, 6, 2, 6, 49, 44, 925000)}
2016-06-02 14:49:45 [scrapy] INFO: Spider closed (finished)
# -*- coding: utf-8 -*-
import scrapy
import re
import os
import sys
import json
#from scrapy.spider import Spider
#from scrapy.selector import Selector
#scrapy startproject google
#scrapy genspider google google.com
#scrapy runspider google.py
class GoogleSpider(scrapy.Spider):
name = 'google'
custom_settings = {
'NUM_SEARCH_RESULTS' : '30',
'SENTENCE_LIMIT' : '50',
'MIN_WORD_IN_SENTENCE' : '7',
'ENABLE_DATE_SORT' : '0',
}
#set the search result here
name = 'Google search'
allowed_domains = ['www.google.com']
start_urls = ['https://www.google.com/search?q=robot']
def parse(self, response):
sel = Selector(response)
google_search_links_list = sel.xpath('//h3/a/@href').extract()
google_search_links_list = [re.search('q=(.*)&sa',n).group(1) for n in
google_search_links_list]
## Dump the output to json file
with open(r'C:\Users\hello\Downloads\googleresult.txt', "a") as outfile:
json.dump({'output_url':google_search_links_list}, outfile, indent=4)
--
You received this message because you are subscribed to the Google Groups
"scrapy-users" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To post to this group, send email to [email protected].
Visit this group at https://groups.google.com/group/scrapy-users.
For more options, visit https://groups.google.com/d/optout.
