Initial Commit.

.gitignore

@@ -0,0 +1,140 @@
+# Created by .ignore support plugin (hsz.mobi)
+### Windows template
+# Windows image file caches
+Thumbs.db
+ehthumbs.db
+
+# Folder config file
+Desktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Windows Installer files
+*.cab
+*.msi
+*.msm
+*.msp
+
+# Windows shortcuts
+*.lnk
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+### VirtualEnv template
+# Virtualenv
+# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
+.Python
+[Bb]in
+[Ii]nclude
+[Ll]ib
+[Ss]cripts
+pyvenv.cfg
+pip-selfcheck.json
+### JetBrains template
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio
+
+*.iml
+
+## Directory-based project format:
+.idea/
+# if you remove the above rule, at least ignore the following:
+
+# User-specific stuff:
+# .idea/workspace.xml
+# .idea/tasks.xml
+# .idea/dictionaries
+
+# Sensitive or high-churn files:
+# .idea/dataSources.ids
+# .idea/dataSources.xml
+# .idea/sqlDataSources.xml
+# .idea/dynamic.xml
+# .idea/uiDesigner.xml
+
+# Gradle:
+# .idea/gradle.xml
+# .idea/libraries
+
+# Mongo Explorer plugin:
+# .idea/mongoSettings.xml
+
+## File-based project format:
+*.ipr
+*.iws
+
+## Plugin-specific files:
+
+# IntelliJ
+/out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+### IPythonNotebook template
+# Temporary data
+.ipynb_checkpoints/
+

scraper.py

@@ -0,0 +1,32 @@
+import scrapy
+
+# From Monthly Update
+# print set(response.css('td[data-th="Bulletin ID"] a::attr("href")').extract())
+
+class BulletinSpider(scrapy.Spider):
+    name = 'BulletinSpider'
+    start_urls = ['https://technet.microsoft.com/library/security/ms13-095']
+
+    def parse(self, response):
+        download_pages = {x for x in response.css('td a::attr("href")').extract() if 'familyid' in x.lower()}
+        for download_page in download_pages:
+            yield scrapy.Request(response.urljoin(download_page), self.resolve_download_page)
+
+    def resolve_download_page(self, response):
+        yield scrapy.Request(response.urljoin(response.url.replace('details.aspx','confirmation.aspx')), self.download_updates)
+
+    def download_updates(self, response):
+        print response.css('td.file-link a::attr("href")').extract()
+
+
+
+
+
+
+
+#
+# {x for x in response.css('td a::attr("href")').extract() if 'familyid' in x.lower()}
+#
+# response.url.replace('details.aspx','confirmation.aspx')
+#
+# response.css('td.file-link a::attr("href")').extract()