wcc 0.0.1 → 0.0.3

data/README.md

@@ -0,0 +1,47 @@
+web change checker
+==================
+
+This is a simple ruby script to track changes of websites and get notified via mail on
+change with configurable scope of adresses per website. All mails contain a unified diff
+from old content to new content so minor changes produce only few lines of text even on large sites.
+
+Note: wcc relies on native `diff` command to produce the unified diff shown in mails -
+plans are to remove this dependency by using [something like this](https://github.com/samg/diffy) later...
+
+Usage
+-----
+
+wcc is packaged as a gem named 'wcc' and provides it's main script as ´wcc´ via the
+command line. It can invoked by hand or automatically via *cron* on a server environment.
+
+For using wcc you need to specify some options:
+
+* either via the command line (see `wcc -h`)
+* or in a configuration file in [YAML](https://secure.wikimedia.org/wikipedia/en/wiki/YAML) format
+
+The location of the configuration file (usually called 'conf.yml' or something like this)
+can itself be given on command line as last argument. Each option has an hard-coded default
+(e.g. the configuration file name is assumed to be './conf.yml'). Command line options
+overwrite configuration file entries.
+
+The core option is the From: mail address and the SMTP configuration for sending emails.
+It is highly encouraged to use the configuration file for all rare changing things
+(even because you have to specify the list of tracked sites there anyways).
+
+An example crontab entry that runs wcc every 10 minutes might look like this:
+
+	*/10 *  * * *   root    cd /path/to/dir/with/conf;./wcc
+
+By default wcc only outputs ERROR messages to avoid your cron daemon spammin' around.
+It is recommended to place 'conf.yml' (and optionally the 'filter.d') within an separate 
+directory and use `cd` in cron entry.
+
+Setup
+-----
+
+You need Ruby (preferably version 1.8.7) and Rubygems installed
+(consider using [rvm](http://beginrescueend.com/)). Install wcc:
+
+	gem install wcc
+
+(If you *don't* use [rvm](http://beginrescueend.com/) you should add a 'sudo'.)

data/lib/wcc.rb

@@ -17,9 +17,11 @@ require 'yaml'
 require 'htmlentities'
 
 class String
+	# Remove all HTML <tags> with at least one character name and
+	# decode all HTML entities into utf-8 characters.
+	#
+	# @return [String] stripped string
 	def strip_html
-		# remove all HTML <tags> with at least 1 character name
-		# and decode all HTML entities into UTF-8 characters
 		HTMLEntities.new.decode(self.gsub(/<[^>]+>/, ' '))
 	end
 end
@@ -69,18 +71,19 @@ module WCC
 			@options = {}
 			
 			OptionParser.new do |opts|
-				opts.banner = "Usage: ruby wcc.rb [options] [config-yaml-file]"
+				opts.banner =  "Usage: ruby wcc.rb [options] [config-yaml-file]"
+				opts.banner += "\nOptions:\n"
 				opts.on('-v', '--verbose', 'Output more information') do self[:verbose] = true end
 				opts.on('-d', '--debug', 'Enable debug mode') do self[:debug] = true end
-				opts.on('-o', '--dir DIR', 'Save required files to DIR') do |dir| self[:dir] = dir end
-				opts.on('-s', '--simulate', 'Check for update but does not save any data') do self[:simulate] = true end
-				opts.on('-c', '--clean', 'Removes all hash and diff files') do self[:clean] = true end
-				opts.on('-t', '--tag TAG', 'Sets TAG used in output') do |t| self[:tag] = t end
-				opts.on('-n', '--no-mails', 'Does not send any emails') do self[:nomails] = true end
-				opts.on('-f', '--from MAIL', 'Set sender mail address') do |m| self[:from_mail] = m end
-				opts.on('--host HOST', 'Sets SMTP host') do |h| self[:host] = h end
-				opts.on('--port PORT', 'Sets SMTP port') do |p| self[:port] = p end
-				opts.on('--show-config', 'Show config after loading config file.') do self[:show_config] = true end
+				opts.on('-o', '--dir DIR', 'Save hash and diff files to DIR') do |dir| self[:dir] = dir end
+				opts.on('-s', '--simulate', 'Check for update but do not save hash or diff files') do self[:simulate] = true end
+				opts.on('-c', '--clean', 'Remove all saved hash and diff files') do self[:clean] = true end
+				opts.on('-t', '--tag TAG', 'Set TAG used in output') do |t| self[:tag] = t end
+				opts.on('-n', '--no-mails', 'Do not send any emails') do self[:nomails] = true end
+				opts.on('-f', '--from MAIL', 'Set From: mail address') do |m| self[:from_mail] = m end
+				opts.on('--host HOST', 'Set SMTP host') do |h| self[:host] = h end
+				opts.on('--port PORT', 'Set SMTP port') do |p| self[:port] = p end
+				opts.on('--show-config', 'Show config after loading config file (debug purposes)') do self[:show_config] = true end
 				opts.on('-h', '-?', '--help', 'Display this screen') do
 					puts opts
 					exit
@@ -94,7 +97,7 @@ module WCC
 			WCC.logger.level = Logger::INFO if self[:verbose]
 			WCC.logger.level = Logger::DEBUG if self[:debug]
 			
-			WCC.logger.formatter = MyFormatter.new((self[:verbose] or self[:debug]))
+			WCC.logger.formatter = LogFormatter.new((self[:verbose] or self[:debug]))
 
 			# main
 			WCC.logger.info "No config file given, using default 'conf.yml' file" if ARGV.length == 0
@@ -187,7 +190,7 @@ module WCC
 					filterrefs,
 					yaml_site['auth'] || {},
 					cookie)
-			end if yaml
+			end if not yaml.nil?
 			
 			WCC.logger.debug @sites.length.to_s + (@sites.length == 1 ? ' site' : ' sites') + " loaded\n" +
 				@sites.map { |s| "  #{s.uri.host.to_s}\n    url: #{s.uri.to_s}\n    id: #{s.id}" }.join("\n")
@@ -274,6 +277,25 @@ module WCC
 			@content = content
 			File.open(Conf.file(@id + '.site'), 'w') { |f| f.write(@content) } unless Conf.simulate?
 		end
+
+		def fetch
+			http = Net::HTTP.new(@uri.host, @uri.port)
+			if @uri.is_a?(URI::HTTPS)
+				http.use_ssl = true
+				http.verify_mode = OpenSSL::SSL::VERIFY_NONE
+			end
+			http.start do |http|
+				req = Net::HTTP::Get.new(@uri.request_uri)
+				if @auth['type'] == 'basic'
+					WCC.logger.debug "Doing basic auth"
+					req.basic_auth(@auth['username'], @auth['password'])
+				end
+				if not @cookie.nil?
+					req.add_field("Cookie", @cookie)
+				end
+				http.request(req)
+			end
+		end
 	end
 
 	class MailAddress
@@ -353,17 +375,14 @@ module WCC
 			return true if filters.nil?
 			
 			WCC.logger.info "Testing with filters: #{filters.join(', ')}"
-			
-			filters.each do |filterref|
-				block = @@filters[filterref.id]
-				
+			filters.each do |fref|
+				block = @@filters[fref.id]
 				if block.nil?
-					WCC.logger.error "Requested filter '#{filterref.id}' not found, skipping it."
+					WCC.logger.error "Requested filter '#{fref.id}' not found, skipping it."
 					next
 				end
-				
-				if not block.call(data, filterref.arguments)
-					WCC.logger.info "Filter #{filterref.id} failed!"
+				if not block.call(data, fref.arguments)
+					WCC.logger.info "Filter #{fref.id} failed!"
 					return false
 				end
 			end
@@ -371,7 +390,7 @@ module WCC
 		end
 	end
 
-	class MyFormatter
+	class LogFormatter
 		def initialize(use_color = true)
 			@color = use_color
 		end
@@ -398,32 +417,14 @@ module WCC
 	end
 
 	class Prog
-
-		# TODO: move to Site
-		def self.fetch(site)
-			http = Net::HTTP.new(site.uri.host, site.uri.port)
-			if site.uri.is_a?(URI::HTTPS)
-				http.use_ssl = true
-				http.verify_mode = OpenSSL::SSL::VERIFY_NONE
-			end
-			http.start do |http|
-				req = Net::HTTP::Get.new(site.uri.request_uri)
-				if site.auth['type'] == 'basic'
-					WCC.logger.debug "Doing basic auth"
-					req.basic_auth(site.auth['username'], site.auth['password'])
-				end
-				if not site.cookie.nil?
-					req.add_field("Cookie", site.cookie)
-				end
-				http.request(req)
-			end
-		end
-
 		def self.checkForUpdate(site)
 			WCC.logger.info "Requesting '#{site.uri.to_s}'"
 			begin
-				res = fetch(site)
-			rescue StandardError, Timeout::Error => ex
+				res = site.fetch
+			rescue Timeout::Error => ex
+				# don't claim on this
+				return false
+			rescue => ex
 				WCC.logger.error "Cannot connect to #{site.uri.to_s} : #{ex.to_s}"
 				return false
 			end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: wcc
 version: !ruby/object:Gem::Version 
-  hash: 29
+  hash: 25
   prerelease: 
   segments: 
   - 0
   - 0
-  - 1
-  version: 0.0.1
+  - 3
+  version: 0.0.3
 platform: ruby
 authors: 
 - Christian Nicolai
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-09-30 00:00:00 Z
+date: 2011-10-01 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: htmlentities
@@ -42,6 +42,7 @@ extra_rdoc_files: []
 files: 
 - bin/wcc
 - lib/wcc.rb
+- README.md
 homepage: https://github.com/cmur2/wcc
 licenses: []