I am new to python 2.7 & Scrapy, and receive the following error when running "scrapy crawl prop$" from the command line. I assume this is a simple fix, thus, any assistance is greatly appreciated!
Error Message:
File"C:\Anaconda2\propub\propub\spiders\propub_spider.py", line 4, in <module>
from propub.items import propubItem
ImportError: cannot import name propubItem
items.py
:
import scrapy
from scrapy.item import Item, Field
class PropubItem(scrapy.Item):
payee = scrapy.Field()
link = scrapy.Field()
city = scrapy.Field()
state = scrapy.Field()
company = scrapy.Field()
amount = scrapy.Field()
pass
propub_spiders.py
:
import scrapy
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from propub.items import propubItem
class propubSpider(CrawlSpider):
name = 'prop$'
allowed_domains = ['https://projects.org']
start_urls = [
'https://projects/search?state%5Bid%5D=33',
'https://projects/search?page=2&state%5Bid%5D=33',
'https://projects/search?page=3&state%5Bid%5D=33']
rules = (Rule(SgmlLinkExtractor(allow=('\\search?page=\\d')), 'parse_start_url', follow=True),)
def parse(self, response):
for sel in response.xpath('//*[@id="payments_list"]/tbody'):
item = propubItem()
item['payee'] = sel.xpath('tr[1]/td[1]/a[2]/text()').extract()
item['link'] = sel.xpath('tr[1]/td[1]/a[1]/@href').extract()
item['city'] = sel.xpath('tr[1]/td[2]/text()').extract()
item['state'] = sel.xpath('tr[1]/td[3]/text()').extract()
item['company'] = sel.xpath('tr[1]/td[4]').extract()
item['amount'] = sel.xpath('tr[1]/td[7]/span/text()').extract()
yield item