From 2e01fa166759266fe050fa2aa5952a86e3e08e59 Mon Sep 17 00:00:00 2001
From: elpolilla <none@none>
Date: Mon, 15 Dec 2008 13:44:42 +0000
Subject: [PATCH] Added part of the new scrapy tutorial

--HG--
extra : convert_revision : svn%3Ab85faa78-f9eb-468e-a121-7cced6da292c%40498
---
 sites/scrapy.org/docs/sources/index.rst       |  1 +
 .../docs/sources/tutorial2/index.rst          |  8 ++++
 .../docs/sources/tutorial2/tutorial1.rst      | 29 ++++++++++++++
 .../docs/sources/tutorial2/tutorial2.rst      | 38 +++++++++++++++++++
 4 files changed, 76 insertions(+)
 create mode 100644 sites/scrapy.org/docs/sources/tutorial2/index.rst
 create mode 100644 sites/scrapy.org/docs/sources/tutorial2/tutorial1.rst
 create mode 100644 sites/scrapy.org/docs/sources/tutorial2/tutorial2.rst

diff --git a/sites/scrapy.org/docs/sources/index.rst b/sites/scrapy.org/docs/sources/index.rst
index 0172bc036..59a7898b1 100644
--- a/sites/scrapy.org/docs/sources/index.rst
+++ b/sites/scrapy.org/docs/sources/index.rst
@@ -12,3 +12,4 @@ Contents:
    basics
    scrapy_intro
    tutorial/index
+   tutorial2/index
diff --git a/sites/scrapy.org/docs/sources/tutorial2/index.rst b/sites/scrapy.org/docs/sources/tutorial2/index.rst
new file mode 100644
index 000000000..944f5600c
--- /dev/null
+++ b/sites/scrapy.org/docs/sources/tutorial2/index.rst
@@ -0,0 +1,8 @@
+========
+Tutorial
+========
+
+.. toctree::
+
+   tutorial1
+   tutorial2
diff --git a/sites/scrapy.org/docs/sources/tutorial2/tutorial1.rst b/sites/scrapy.org/docs/sources/tutorial2/tutorial1.rst
new file mode 100644
index 000000000..2aadbd53a
--- /dev/null
+++ b/sites/scrapy.org/docs/sources/tutorial2/tutorial1.rst
@@ -0,0 +1,29 @@
+=====================
+Setting everything up
+=====================
+
+| In this tutorial, we'll teach you how to scrape http://www.dmoz.org, a websites directory.
+| We'll assume that you've checked and fulfilled the requirements specified in the Download page, and that Scrapy is already installed in your system.
+
+For starting a new project, enter the directory where you'd like your project to be located, and run::
+
+    scrapy-admin.py startproject dmoz
+
+As long as Scrapy is well installed and the path is set, this should create a directory called "dmoz"
+containing the following files:
+
+* *scrapy-ctl.py* - the project's control script. It's used for running the different tasks (like "crawl" and "parse"). We'll talk more about this later.
+* *scrapy_settings.py* - the project's settings file.
+* *items.py* - were you define the different kinds of items you're going to scrape.
+* *spiders* - directory where you'll later place your spiders.
+* *templates* - directory containing some templates for newly created spiders, and where you can put your own.
+
+| Ok, now that you have your project's structure defined, the last thing to do is to set your PYTHONPATH to your project's directory.
+| You can do this by adding this to your .bashrc file:
+
+::
+
+    export PYTHONPATH=/path/to/your/project
+
+
+Now you can continue with the next part of the tutorial.
diff --git a/sites/scrapy.org/docs/sources/tutorial2/tutorial2.rst b/sites/scrapy.org/docs/sources/tutorial2/tutorial2.rst
new file mode 100644
index 000000000..9539d4b77
--- /dev/null
+++ b/sites/scrapy.org/docs/sources/tutorial2/tutorial2.rst
@@ -0,0 +1,38 @@
+================
+Our first spider
+================
+
+| Ok, the time to write our first spider has come.
+| Make sure you're standing on your project's directory and run:
+
+::
+
+    ./scrapy-ctl genspider dmoz dmoz.org
+
+This should create a file called dmoz.py under the *spiders* directory looking similar to this::
+
+    # -*- coding: utf8 -*-<
+    import re
+    from scrapy.xpath import HtmlXPathSelector
+    from scrapy.item import ScrapedItem
+    from scrapy.link.extractors import RegexLinkExtractor
+    from scrapy.contrib.spiders import CrawlSpider, Rule
+
+    class DmozSpider(CrawlSpider):
+        domain_name = "dmoz.org"
+        start_urls = ['http://www.dmoz.org/']
+
+        rules = (
+            Rule(RegexLinkExtractor(allow=(r'Items/', ), 'parse_item', follow=True)
+        )
+
+        def parse_item(self, response):
+            #xs = HtmlXPathSelector(response)
+            #i = ScrapedItem()
+            #i.attribute('site_id', xs.x("//input[@id="sid"]/@value"))
+            #i.attribute('name', xs.x("//div[@id='name']"))
+            #i.attribute('description', xs.x("//div[@id='description']"))
+            #return [i]
+
+    SPIDER = DmozSpider()
+