Created
December 27, 2015 17:07
-
-
Save bjpcjp/b8a2f6204652f6452590 to your computer and use it in GitHub Desktop.
This file contains hidden or 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 StackOverflowSpider(scrapy.Spider): | |
name = 'stackoverflow' | |
start_urls = ['http://stackoverflow.com/questions?sort=votes'] | |
def parse(self, response): | |
for href in response.css('.question-summary h3 a::attr(href)'): | |
full_url = response.urljoin(href.extract()) | |
yield scrapy.Request(full_url, callback=self.parse_question) | |
def parse_question(self, response): | |
yield { | |
'title': response.css('h1 a::text').extract()[0], | |
'votes': response.css('.question .vote-count-post::text').extract()[0], | |
'body': response.css('.question .post-text').extract()[0], | |
'tags': response.css('.question .post-tag::text').extract(), | |
'link': response.url, | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
From the intro to Scrapy v1.0.3.