Final version

This commit is contained in:
Renne Rocha 2024-05-07 16:17:43 -03:00
parent d7fd3dd578
commit 63e275fa2f
30 changed files with 2918 additions and 5 deletions

17
code/pyconus2024-css.py Normal file
View file

@ -0,0 +1,17 @@
import scrapy
class PyConUS2024Spider(scrapy.Spider):
name = "pyconus"
start_urls = [
"https://us.pycon.org/2024/schedule/tutorials/",
]
def parse(self, response):
for tutorial in response.css(".presentation"):
yield {
"speaker": tutorial.css(".speaker::text").get().strip(),
"url": response.urljoin(tutorial.css(".title a::attr(href)").get()),
"title": tutorial.css(".title a::text").get(),
}