Files
dt_audio/quotes_spider.py
alsesa b10fd0e112 merge
2024-10-14 17:39:25 +08:00

19 lines
616 B
Python
Executable File

import scrapy
class QuoteSpider(scrapy.Spider):
name = "quotes"
start_urls = [
'http://quotes.toscrape.com/tag/humor/',
]
def parse(self, response):
for quote in response.css('div.quote'):
yield {
'author': quote.css('small.author::text').get(),
'text': quote.css('span.text::text').get(),
# 'tags': quote.css('div.tags a.tag::text').getall(),
}
next_page = response.css('li.next a::attr(href)').get()
if next_page is not None:
yield response.follow(next_page, callback=self.parse)