Add khanindex nevrax indexation

7 files changed, 83 insertions, 14 deletions

diff --git a/crawler/neodarznet/settings.py b/crawler/neodarznet/settings.py
deleted file mode 100644
index 2e5f184..0000000
--- a/crawler/neodarznet/settings.py
+++ /dev/null
@@ -1,12 +0,0 @@
-# -*- coding: utf-8 -*-
-
-BOT_NAME = 'neodarznet'
-
-SPIDER_MODULES = ['crawler.neodarznet.spiders']
-NEWSPIDER_MODULE = 'crawler.neodarznet.spiders'
-
-ROBOTSTXT_OBEY = True
-
-DEPTH_LIMIT = 0
-
-ITEM_PIPELINES = {'crawler.neodarznet.pipelines.NeodarznetPipeline': 0}
diff --git a/crawler/neodarznet/spiders/scrape.py b/crawler/neodarznet/spiders/scrape.py
index a32a3e4..e16ede2 100644
--- a/crawler/neodarznet/spiders/scrape.py
+++ b/crawler/neodarznet/spiders/scrape.py
@@ -4,8 +4,13 @@ from scrapy.spiders import CrawlSpider, Rule
 from scrapy.linkextractors import LinkExtractor
 from scrapy import Selector
 
-class ScrapSpider(CrawlSpider):
-    name = "scrape"
+class NeodarznetSpider(CrawlSpider):
+    name = "neodarznet"
+    custom_settings = {
+        'ITEM_PIPELINES': {
+            'crawler.neodarznet.pipelines.NeodarznetPipeline': 0
+        }
+    }
     allow_domains = ['neodarz.net']
     start_urls = [
         'https://neodarz.net/',
diff --git a/crawler/nevrax/__init__.py b/crawler/nevrax/__init__.py
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/crawler/nevrax/__init__.py
diff --git a/crawler/nevrax/pipelines.py b/crawler/nevrax/pipelines.py
new file mode 100644
index 0000000..775d5df
--- /dev/null
+++ b/crawler/nevrax/pipelines.py
@@ -0,0 +1,19 @@
+# -*- coding: utf-8 -*-
+import logging
+
+from database.models import Nevrax
+
+
+class NevraxPipeline(object):
+
+    def process_item(self, item, spider):
+        try:
+            page = Nevrax.get(Nevrax.url == item['url'])
+            q = Nevrax.update(**item).where(Nevrax.url == item['url'])
+            q.execute()
+            logging.info("Update item {}".format(page))
+        except Nevrax.DoesNotExist:
+            page = Nevrax.create(**item)
+            logging.info("Create item {}".format(page))
+        logging.info('Item {} stored in db'.format(page))
+        return item
diff --git a/crawler/nevrax/spiders/__init__.py b/crawler/nevrax/spiders/__init__.py
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/crawler/nevrax/spiders/__init__.py
diff --git a/crawler/nevrax/spiders/scrape.py b/crawler/nevrax/spiders/scrape.py
new file mode 100644
index 0000000..8a7b8ec
--- /dev/null
+++ b/crawler/nevrax/spiders/scrape.py
@@ -0,0 +1,45 @@
+# -*- coding: utf-8 -*-
+import scrapy
+from scrapy.spiders import CrawlSpider, Rule
+from scrapy.linkextractors import LinkExtractor
+from scrapy import Selector
+
+import config
+
+class NevraxSpider(CrawlSpider):
+    name = "nevrax"
+    custom_settings = {
+        'ITEM_PIPELINES': {
+            'crawler.nevrax.pipelines.NevraxPipeline': 0
+        }
+    }
+    allow_domains = [config.NEVRAX_URL]
+    start_urls = [
+        'http://'+config.NEVRAX_URL+'/',
+    ]
+
+    rules = [
+            Rule(
+                LinkExtractor(
+                    canonicalize=True,
+                    unique=True,
+                    allow_domains=config.NEVRAX_URL,
+                    #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("//body//text()").extract()).strip()
+        }
diff --git a/crawler/settings.py b/crawler/settings.py
new file mode 100644
index 0000000..2ccdc11
--- /dev/null
+++ b/crawler/settings.py
@@ -0,0 +1,12 @@
+# -*- coding: utf-8 -*-
+
+BOT_NAME = 'khanindex'
+
+SPIDER_MODULES = ['crawler.nevrax.spiders', 'crawler.neodarznet.spiders']
+#NEWSPIDER_MODULE = 'crawler.nevrax.spiders'
+
+ROBOTSTXT_OBEY = True
+
+DEPTH_LIMIT = 0
+
+#ITEM_PIPELINES = {'crawler.nevrax.pipelines.NevraxPipeline': 0, 'crawler.neodarznet.pipelines.NeodarznetPipeline': 0}