cinch-url-scraper 1.0.0 → 1.1.0

data/README.md

@@ -1,3 +1,41 @@
 # Cinch Url Scraper plugin
 
 A Cinch plugin to get information about posted URLs.
+
+## Installation
+
+First install the gem by running:
+
+```bash
+gem install cinch-url-scrapper
+```
+
+Then load it in your bot:
+
+```ruby
+require "cinch"
+require "cinch/plugins/urlscraper"
+
+bot = Cinch::Bot.new do
+  configure do |c|
+    c.plugins.plugins = [Cinch::Plugins::UmlScraper]
+  end
+end
+
+bot.start
+```
+
+## Commands
+
+```irc
+<url> # display url title / information
+```
+
+## Example
+
+    <mpapis>: git@gist.github.com:3505088.git:
+    <smfbot>: Title: rvm setup for projects — Gist (at gist.github.com, mpapis on 2012-08-28 15:56), Url: https://gist.github.com/3505088
+
+## Development
+
+Run the `./test-run.sh` script to play with results of your changes in channel listed in `example/config.yaml`

data/lib/cinch/plugins/urlscraper.rb

@@ -8,7 +8,6 @@ module Cinch
   module Plugins
     class UrlScraper
       include Cinch::Plugin
-      set :react_on, :channel
 
       listen_to :channel
       def listen(m)
@@ -19,9 +18,15 @@ module Cinch
           @agent.max_history      = 0
         end
 
-        URI.extract(m.message, ["http", "https"]) do |link|
+        URI.extract(m.message.gsub(/git@(gist.github.com):/,'git://\1/'), ["http", "https", "git"]).map do |link|
+          link=~/^(.*?)[:;,\)]?$/
+          $1
+        end.each do |link|
           # Fetch data
           begin
+            if git = link =~ /^git:\/\/(gist.github.com\/.*)\.git$/
+              link = "https://#{$1}"
+            end
             uri  = URI.parse(link)
             page = @agent.get(link)
           rescue Mechanize::ResponseCodeError
@@ -69,12 +74,20 @@ module Cinch
               owner = page.search("//div[@class='name']/a").inner_html
 
               # Get time
-              age = Time.parse(page.search("//span[@class='date']/abbr").text)
-              age = age.strftime("%Y-%m-%d %H:%M")
-
-              m.reply "Title: %s (at %s, %s on %s)" % [
-                title, uri.host, owner, age
-              ]
+              age = page.search("//span[@class='date']/time")
+              age = age.first[:datetime] rescue age.text if age
+              age = Time.parse(age) rescue nil
+              age = age.strftime("%Y-%m-%d %H:%M") if age
+
+              if git
+                m.reply "Title: %s (at %s, %s on %s), Url: %s" % [
+                  title, uri.host, owner, age, link
+                ]
+              else
+                m.reply "Title: %s (at %s, %s on %s)" % [
+                  title, uri.host, owner, age
+                ]
+              end
             when "pastie.org"
               # Get time
               age = Time.parse(page.search("//span[@class='typo_date']").text)

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: cinch-url-scraper
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.1.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-06-26 00:00:00.000000000 Z
+date: 2012-08-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cinch