Initial scrapy project

6 files changed, 49 insertions, 0 deletions

diff --git a/israblog/israblog/__init__.py b/israblog/israblog/__init__.py
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/israblog/israblog/__init__.py
diff --git a/israblog/israblog/items.py b/israblog/israblog/items.py
new file mode 100644
index 0000000..706a41b
--- /dev/null
+++ b/israblog/israblog/items.py
@@ -0,0 +1,11 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+from scrapy.item import Item, Field
+
+class IsrablogItem(Item):
+    # define the fields for your item here like:
+    # name = Field()
+    pass
diff --git a/israblog/israblog/pipelines.py b/israblog/israblog/pipelines.py
new file mode 100644
index 0000000..55d0add
--- /dev/null
+++ b/israblog/israblog/pipelines.py
@@ -0,0 +1,8 @@
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+class IsrablogPipeline(object):
+    def process_item(self, item, spider):
+        return item
diff --git a/israblog/israblog/settings.py b/israblog/israblog/settings.py
new file mode 100644
index 0000000..ce238f2
--- /dev/null
+++ b/israblog/israblog/settings.py
@@ -0,0 +1,15 @@
+# Scrapy settings for israblog project
+#
+# For simplicity, this file contains only the most important settings by
+# default. All the other settings are documented here:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#
+
+BOT_NAME = 'israblog'
+
+SPIDER_MODULES = ['israblog.spiders']
+NEWSPIDER_MODULE = 'israblog.spiders'
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'israblog (+http://www.yourdomain.com)'
diff --git a/israblog/israblog/spiders/__init__.py b/israblog/israblog/spiders/__init__.py
new file mode 100644
index 0000000..ebd689a
--- /dev/null
+++ b/israblog/israblog/spiders/__init__.py
@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.
diff --git a/israblog/scrapy.cfg b/israblog/scrapy.cfg
new file mode 100644
index 0000000..783bd26
--- /dev/null
+++ b/israblog/scrapy.cfg
@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# http://doc.scrapy.org/en/latest/topics/scrapyd.html
+
+[settings]
+default = israblog.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = israblog