-
-
Save csakis/d99c7eecb3c55f8deeb42ef6727e8a07 to your computer and use it in GitHub Desktop.
Scrapy + Splash example
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 | |
# this example needs the scrapyjs package: pip install scrapyjs | |
# it also needs a splash instance running in your env or on Scrapy Cloud (https://github.com/scrapinghub/splash) | |
class SplashSpider(scrapy.Spider): | |
name = 'splash-spider' | |
download_delay = 3 | |
def start_requests(self): | |
yield scrapy.Request( | |
'http://quotes.toscrape.com/js', self.parse, | |
meta={ | |
'splash': { | |
'endpoint': 'render.html', | |
} | |
} | |
) | |
def parse(self, response): | |
print response.body | |
for quote in response.css('.quote'): | |
yield { | |
'text': quote.css('span::text').extract_first(), | |
'author': quote.css('small::text').extract_first(), | |
'tags': quote.css('.tags a::text').extract(), | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment