def process_item(self, item, spider):
keywords = spider.search_terms
title = item['title'].lower()
#####
# We can pass in excluded words the same way as keywords later. Commented out for now.
# excluded_words = ['asp.net', 'java', 'c#', 'web developer', 'c++',
# 'windows', 'qa', 'support', '.net', 'manager', 'sales',
# 'marketing', 'senior', 'snr', 'salesforce', 'crm']
#####
#####
# if any(keyword in title for keyword in excluded_words):
# raise DropItem("Job title contained excluded word")
#####
if any(keyword in title for keyword in keywords):
return item
else:
raise DropItem("Job title doesn't contain our search terms")
评论列表
文章目录