Add spider for Crunchbase

exa/exa/spiders/cb.py

+# -*- coding: utf-8 -*-
+import scrapy
+
+from .base import BaseSpider
+
+
+from ..items import ExaItem
+
+
+class CbSpider(BaseSpider):
+    name = "cb"
+    allowed_domains = ["www.crunchbase.com"]
+    start_urls = ['http://www.crunchbase.com/organization/sense-ly/press/']
+
+    def parse(self, response):
+        rows = response.xpath("//table/tr")[1:]
+        print(rows)
+        for i in rows:
+            item = ExaItem()
+            item['date'] = i.xpath("//td[contains(@class, 'date')]/text()").extract_first()
+            item['title'] = i.xpath("//td/a/text()").extract_first()
+            item['url'] = i.xpath("//td/a/@href").extract_first()
+            print(item)
+