Last active
April 20, 2018 07:03
-
-
Save arunshaji95/1ff481d577fd8c12a98eaad7659a3a7d to your computer and use it in GitHub Desktop.
Basic scrapy tutorial
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
import scrapy | |
class BookSpider(scrapy.Spider): | |
name = 'bookspider' | |
start_urls = [ | |
'http://books.toscrape.com/' | |
] | |
def parse(self, response): | |
for link in response.xpath('//article[@class="product_pod"]/div/a/@href').extract(): | |
yield response.follow(link, callback=self.parse_detail) | |
next_page = response.xpath('//li[@class="next"]/a/@href').extract_first() | |
if next_page: | |
yield response.follow(next_page, callback=self.parse) | |
def parse_detail(self, response): | |
title = response.xpath('//div[contains(@class, "product_main")]/h1/text()').extract_first() | |
price = response.xpath('//div[contains(@class, "product_main")]/' | |
'p[@class="price_color"]/text()').extract_first() | |
availability = response.xpath('//div[contains(@class, "product_main")]/' | |
'p[contains(@class, "availability")]/text()').extract() | |
availability = ''.join(availability).strip() | |
upc = response.xpath('//th[contains(text(), "UPC")]/' | |
'following-sibling::td/text()').extract_first() | |
yield { | |
'title': title, | |
'price': price, | |
'availability': availability, | |
'upc': upc | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment