scripts/crawler/tbc_web_crawler/spiders/items.py


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18

import scrapy


class TbcErrorItems(scrapy.Item):


	chapter_name = scrapy.Field()
	chapter_urls = scrapy.Field()
	completed_book_urls = scrapy.Field()
	number_of_errors = scrapy.Field()
	error_messages = scrapy.Field()
	
	
class TbcBrokenItems(scrapy.Item):
	
	broken_url = scrapy.Field()
	broken_status = scrapy.Field()