nahali

# Scrapy settings for ProjetVinNicolas3 project
#
# For simplicity, this file contains only the most important settings by
# default. All the other settings are documented here:
#
#     http://doc.scrapy.org/topics/settings.html
#

BOT_NAME = 'ProjetVinNicolas4'

nahali

#!/usr/bin/python
#-*- coding: utf-8 -*-
from ProjetVinNicolas4.items import Projetvinnicolas4Item
from scrapy.contrib.exporter import CsvItemExporter
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.contrib.pipeline.images import ImagesPipeline
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.selector import HtmlXPathSelector
import lxml
import lxml.etree

nahali

# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/topics/items.html

from scrapy.item import Item, Field

class Projetvinnicolas4Item(Item):
    millesime= Field()
    temp_Conserv = Field()

nahali

# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/topics/items.html

from scrapy.item import Item, Field

class Projetvinnicolas3Item(Item):
    nomVin = Field()
    temp_Conserv = Field()

nahali

#!/usr/bin/python
#-*- coding: utf-8 -*-
from ProjetVinNicolas3.items import Projetvinnicolas3Item
from scrapy.contrib.exporter import CsvItemExporter
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.selector import HtmlXPathSelector
import lxml
import lxml.etree
import lxml.html

nahali

37, in maybeDeferred
            result = f(*args, **kw)
          File "C:\Python27\lib\site-packages\scrapy-0.16.5-py2.7.egg\scrapy\xli
b\pydispatch\robustapply.py", line 47, in robustApply
            return receiver(*arguments, **named)
          File "C:\Python27\lib\site-packages\scrapy-0.16.5-py2.7.egg\scrapy\con
trib\feedexport.py", line 190, in item_scraped
            slot = self.slots[spider]
        exceptions.KeyError: <MySpider 'vinNico3' at 0x3d27690>

nahali

BOT_NAME = 'ProjetVinNicolas3'

SPIDER_MODULES = ['ProjetVinNicolas3.spiders']
NEWSPIDER_MODULE = 'ProjetVinNicolas3.spiders'


ITEM_PIPELINES = ['scrapy.contrib.pipeline.images.ImagesPipeline', 'ProjetVinNicolas3.pipelines.MyImagesPipeline']
IMAGE_STORE =  '/img'

nahali

from scrapy.contrib.pipeline.images import ImagesPipeline
from scrapy.exceptions import DropItem
from scrapy.http import Request

class MyImagesPipeline(ImagesPipeline):

    def get_media_requests(self, item, info):
        for image_url in item['image_urls']:
            yield Request(image_url)