Skip to content

Instantly share code, notes, and snippets.

@gileno gileno/
Last active Aug 29, 2015

What would you like to do?
Scrapy blog post V
# -*- coding: utf-8 -*-
import scrapy
class OlxSpider(scrapy.Spider):
name = "olx"
allowed_domains = [""]
start_urls = (
def parse(self, response):
items = response.xpath(
for item in items:
url = item.xpath(
yield scrapy.Request(url=url, callback=self.parse_detail)
next_page = response.xpath(
'//li[contains(@class,"item next")]//a/@href'
if next_page:
self.log('Next Page: {0}'.format(next_page))
yield scrapy.Request(url=next_page, callback=self.parse)
def parse_detail(self, response):
self.log(u'Imóvel URL: {0}'.format(response.url))
title = response.xpath('normalize-space(//h1[contains(@id,"ad_title")]//.)').extract_first()
self.log(u'Título: {0}'.format(title))
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.