Last active
August 7, 2017 19:57
-
-
Save jluczak/0b382010196e7f3bfd6e53b304640613 to your computer and use it in GitHub Desktop.
Write a Scrapy parser for Human Talks
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 | |
from human.items import HumanItem | |
class HumanSpider(scrapy.Spider): | |
start_urls = [ | |
'http://humantalks.com/talks/' | |
] | |
name = 'human' | |
def parse(self, response): | |
for talk in response.css('.card-deck a'): | |
href = talk.css('a::attr(href)').extract_first() | |
full_url = response.urljoin(href) | |
yield scrapy.Request(full_url, callback=self.parse_book) | |
for href in response.css('a.page-link'): | |
yield response.follow(href, self.parse) | |
def parse_book(self, response): | |
title = response.css('h1::text').extract_first() | |
name = response.css('.speaker_name a::text').extract_first() | |
description = response.css('.offset-md-2 p::text').extract() | |
slide = response.css('.btn-primary::attr(href)').extract_first() | |
slide2 = response.css('.player iframe::attr(src)').extract_first() | |
video = response.css('.yt-uix-sessionlink a::attr(href)').extract_first() | |
yield HumanItem(title=title, description=description, name=name, slide2=slide2,slide=slide,video=video) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment