This is the BaseSpider example from the Scrapy tutorial:
from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
from dmoz.items import DmozItem
class DmozSpider(BaseSpider):
domain_name = "dmoz.org"
start_urls = [
"http://www.dmoz.org/Computers/Programming/Languages/Python/Books/",
"http://www.dmoz.org/Computers/Programming/Languages/Python/Resources/"
]
def parse(self, response):
hxs = HtmlXPathSelector(response)
sites = hxs.select('//ul[2]/li')
items = []
for site in sites:
item = DmozItem()
item['title'] = site.select('a/text()').extract()
item['link'] = site.select('a/@href').extract()
item['desc'] = site.select('text()').extract()
items.append(item)
return items
SPIDER = DmozSpider()
I copied it with changes for my project:
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.selector import HtmlXPathSelector
from scrapy.item import Item
from firm.items import FirmItem
class Spider1(CrawlSpider):
domain_name = 'wc2'
start_urls = ['http://www.whitecase.com/Attorneys/List.aspx?LastName=A']
def parse(self, response):
hxs = HtmlXPathSelector(response)
sites = hxs.select('//td[@class="altRow"][1]/a/@href').re('/.a\w+')
items = []
for site in sites:
item = FirmItem
item['school'] = hxs.select('//td[@class="mainColumnTDa"]').re('(JD)(.*?)(\d+)')
items.append(item)
return items
SPIDER = Spider1()
and I get the error
[wc2] ERROR: Spider exception caught while processing
<http://www.whitecase.com/Attorneys/List.aspx?LastName=A> (referer: <None>):
[Failure instance: Traceback: <type 'exceptions.TypeError'>:
'ItemMeta' object does not support item assignment
I would greatly appreciate it if experts here take a look at the code and give me a clue about where I am going wrong.
Thank you