Created
October 2, 2017 12:34
-
-
Save ijharulislam/e016d29d53023936bc6bc5285aaa0d98 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # -*- coding: utf-8 -*- | |
| import scrapy | |
| from nafdac.items import NafdacItem | |
| class NafDacCrawlerSpider(scrapy.Spider): | |
| name = 'nafdac' | |
| def start_requests(self): | |
| for i in range(0, 20702, 10): | |
| url = 'http://www.nafdac.gov.ng/index.php/product-registration/registered-drugs?resetfilters=0&limitstart10={}'.format(i) | |
| yield scrapy.Request(url=url, callback=self.parse) | |
| def parse(self, response): | |
| tr = response.xpath('//*[@id="list_10_com_fabrik_10"]/tbody//tr') | |
| for t in tr: | |
| output = NafdacItem() | |
| product_type = t.xpath("td[1]/text()").extract_first().strip() | |
| product_name = t.xpath("td[2]/text()").extract_first() | |
| active_ingredients = t.xpath("td[3]/text()").extract_first() | |
| manufacturer = t.xpath("td[4]/text()").extract_first() | |
| if product_name: | |
| output = { | |
| "product_type": product_type, | |
| "product_name": product_name, | |
| "active_ingredients": active_ingredients, | |
| "manufacturer": manufacturer | |
| } | |
| print("product_type: {}, product_name: {}, active_ingredients:{}, manufacturer:{}".format(product_type, product_name, active_ingredients, manufacturer)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment