Last active
October 21, 2019 07:06
-
-
Save chrisdietr/b6e8f86adaebd5820ed0766cd44ec37b to your computer and use it in GitHub Desktop.
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
# -*- coding: utf-8 -*- | |
import scrapy | |
from scrapy.http import FormRequest, Request | |
class QuotesSpider(scrapy.Spider): | |
name = 'quoteslogin' | |
allowed_domains = ['quotes.toscrape.com'] | |
start_urls = [ | |
'http://quotes.toscrape.com/login' | |
] | |
directory_url = 'http://quotes.toscrape.com/page/1/' | |
def parse(self, response): | |
csrf_token = response.xpath("//input[@name='csrf_token']/@value").get() | |
yield FormRequest.from_response(response, formxpath="//form", formdata={ | |
'csrf_token': csrf_token, | |
'username': 'admin', | |
'password': 'admin' | |
}, callback=self.go_to_directory) | |
def go_to_directory(self, response): | |
return Request(url='http://quotes.toscrape.com/page/3/', callback=self.after_login) | |
def after_login(self, response): | |
for href in response.xpath('//a[contains(.,"(about)")]/@href'): | |
yield response.follow(href, callback=self.parse_items) | |
# for quote in response.xpath("//div[@class='quote']"): | |
# yield { | |
# 'quote': quote.xpath(".//span[@class='text']/text()").get() | |
# } | |
next_page = response.xpath("//li[@class='next']/a/@href").get() | |
if next_page: | |
yield response.follow(url=next_page, callback=self.after_login) | |
def parse_items(self, response): | |
yield { | |
'year': response.xpath('//span[@class="author-born-date"]').get() | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment