From 82746a2b76e5948333133bfe07c1042af2cd33b7 Mon Sep 17 00:00:00 2001
From: neodarz <neodarz@neodarz.net>
Date: Thu, 10 Jan 2019 23:54:18 +0100
Subject: Initial commit

---
 crawler/neodarznet/spiders/scrape.py | 38 ++++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)
 create mode 100644 crawler/neodarznet/spiders/scrape.py

(limited to 'crawler/neodarznet/spiders/scrape.py')

diff --git a/crawler/neodarznet/spiders/scrape.py b/crawler/neodarznet/spiders/scrape.py
new file mode 100644
index 0000000..a32a3e4
--- /dev/null
+++ b/crawler/neodarznet/spiders/scrape.py
@@ -0,0 +1,38 @@
+# -*- coding: utf-8 -*-
+import scrapy
+from scrapy.spiders import CrawlSpider, Rule
+from scrapy.linkextractors import LinkExtractor
+from scrapy import Selector
+
+class ScrapSpider(CrawlSpider):
+    name = "scrape"
+    allow_domains = ['neodarz.net']
+    start_urls = [
+        'https://neodarz.net/',
+    ]
+
+    rules = [
+            Rule(
+                LinkExtractor(
+                    canonicalize=True,
+                    unique=True,
+                    allow_domains="neodarz.net",
+                    deny=".*\.neodarz\.net.*"
+                ),
+                follow=True,
+                callback="parse_items"
+            )
+    ]
+
+
+    def start_requests(self):
+        for url in self.start_urls:
+            yield scrapy.Request(url, callback=self.parse, dont_filter=True)
+
+    def parse_items(self, response):
+        sel = Selector(response)
+        yield {
+                'url': response.url,
+                'title': response.css('title::text').extract_first(),
+                'content': ''.join(sel.select("//div[@class='bodya']//text()").extract()).strip()
+        }
-- 
cgit v1.2.1