Reputation: 149
spider_closed() function is not performing. If i give just print statement it is printing but if i perform any function call and return the value it is not working.
import scrapy
import re
from pydispatch import dispatcher
from scrapy import signals
from SouthShore.items import Product
from SouthShore.internalData import internalApi
from scrapy.http import Request
class bestbuycaspider(scrapy.Spider):
name = "bestbuy_dca"
allowed_domains = ["bestbuy.ca"]
start_urls = ["http://www.bestbuy.ca/Search/SearchResults.aspx?type=product&page=1&sortBy=relevance&sortDir=desc&pageSize=96&query=south+shore+furniture+beds",
"http://www.bestbuy.ca/Search/SearchResults.aspx?type=product&page=1&sortBy=relevance&sortDir=desc&pageSize=96&query=south+shore+furniture+night+stand",
"http://www.bestbuy.ca/Search/SearchResults.aspx?type=product&page=1&sortBy=relevance&sortDir=desc&pageSize=96&query=south+shore+furniture+headboard",
"http://www.bestbuy.ca/Search/SearchResults.aspx?type=product&page=1&sortBy=relevance&sortDir=desc&pageSize=96&query=south+shore+furniture+desk",
"http://www.bestbuy.ca/Search/SearchResults.aspx?type=product&page=1&sortBy=relevance&sortDir=desc&pageSize=96&query=south+shore+furniture+bookcase",
"http://www.bestbuy.ca/Search/SearchResults.aspx?type=product&page=1&sortBy=relevance&sortDir=desc&pageSize=96&query=south+shore+furniture+dresser",
"http://www.bestbuy.ca/Search/SearchResults.aspx?type=product&page=1&sortBy=relevance&sortDir=desc&pageSize=96&query=south+shore+furniture+tv+stand",
"http://www.bestbuy.ca/Search/SearchResults.aspx?type=product&page=1&sortBy=relevance&sortDir=desc&pageSize=96&query=south+shore+furniture+armoire",
"http://www.bestbuy.ca/Search/SearchResults.aspx?type=product&page=1&sortBy=relevance&sortDir=desc&pageSize=96&query=south+shore+furniture+kids",
"http://www.bestbuy.ca/Search/SearchResults.aspx?type=product&page=1&sortBy=relevance&sortDir=desc&pageSize=96&query=south+shore+furniture+changing+table",
"http://www.bestbuy.ca/Search/SearchResults.aspx?type=product&page=1&sortBy=relevance&sortDir=desc&pageSize=96&query=south+shore+furniture+baby"]
def __init__(self,jsondetails="",serverdetails="", *args,**kwargs):
super(bestbuycaspider, self).__init__(*args, **kwargs)
dispatcher.connect(self.spider_closed, signal=signals.spider_closed)
self.jsondetails = jsondetails
self.serverdetails=serverdetails
self.data = []
def parse(self,response):
#my stuff here
def spider_closed(self,spider):
print "returning values"
self.results['extractedData']=self.data
print self.results=internalApi(self.jsondetails,self.serverdetails)
yield self.results
1) I want to call some function and return the scraped values
Upvotes: 1
Views: 2470
Reputation: 21436
You can create an Item Pipeline with close_spider()
method:
class MyPipeline(object):
def close_spider(self, spider):
do_something_here()
Just don't forget to activate it in settings.py as described in the docummentation link above.
Upvotes: 4