sutch-anemone 0.7.2 → 0.7.2.1

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    YWExNTI1ZGRiMjA0NTZhNzk3Y2YyMDYzNDcxMDQwNTk4NDJkMGI2NQ==
+    OGEwMGMxZjNmMDdkNmUxNmU3ZGM2ZTNiNDAzMmRhZDlhNzQ1MmIyYg==
   data.tar.gz: !binary |-
-    YWE2MDg1OTQzNTEyOTZiZTJjMTUzNWZiMzgxNTBjMDJmMzBkYjYzZQ==
+    ZTcxMGJlZTgyNmEzY2U4OTA3MmUxYTY1MjQwYjRmYWViNzhmODhiMA==
 !binary "U0hBNTEy":
   metadata.gz: !binary |-
-    YWY1MjliMGJjMzRhZGQ1OTVmYWVlYzI3YmU3YTI1ZGVjMDk5NjAwZGEwZmJh
-    MzA0Y2Q4ZWMwODM3MzgyMTU5ZTk2NTE3ZDFhNDc4MDBmOWZjNWViOWQ1Nzlk
-    ZDU4OTA4Y2VkNWI1MDA1ZjUyNWQ2YzJkMDA3YmJiNGQwZTczMGM=
+    NTFhOWRjMzk5NjE4MmU4Zjk5ODYyNmQzN2U2OWRiZGQ0OWI0YTE0NmNiMzhi
+    MTQ5MmQwOWUyYWJjMDkxYTBmY2RiN2QwOTAwYmI3YzY1NjM2YWI0ZTU2ZDAy
+    OGI2YjJmMjUwYmRhZjNlYWI3ZjYxMzAxNzdlOWQzYzQwNDZiZjA=
   data.tar.gz: !binary |-
-    MjYzODE4ZTIwYjM5OTljMDY2NTdkNzRiY2FlOWJkOGMxNmZjNzE4M2JkN2Fk
-    YjQ4MjE5NjM2NjllZmJhODc4M2UzYjYwYTZhY2ZhZWRiYzgwZjk4MDZmYzEy
-    N2FkMjZiZjdiMmI2NWI2N2I3MDUyNWM2YmI0YTIyODAzZmQ1Yzg=
+    M2ZkNzkyZmNmMTNkMDJkYjc2ODIwNWNlOGM3OTdlOWFkZjJmMjg1ZTJiYzkz
+    YmVlYTYzZGNlZDA0M2I5MzA4MTk5NjVmYmI5ZDBhOTg0MGVlODE2ZjYyNmRm
+    MDAyZTVhNDc0NWU2M2I0YzM1ZmRhZWFkOTMxNjZjNmNmZmQwOWU=

data/CHANGELOG.rdoc

@@ -2,6 +2,8 @@
 
 == sutch's branch
 
+  * Changed SQLite3 timeout to allow for other clients to read from database
+  * Changed for wmonk: allow restarting of spider by not checking starting URLs
   * Added Anemone::Resource to provide for spidering of resources other than HTML pages
 
 == 0.7.2 / 2012-05-30

data/README.rdoc

@@ -6,6 +6,8 @@ write your own specialized spider tasks quickly and easily.
 
 See http://anemone.rubyforge.org for more information.
 
+This branch of Anemone, sutch-anemone, has been enhanced for {wmonk}[https://github.com/sutch/wmonk].
+
 == Features
 * Multi-threaded design for high performance
 * Tracks 301 HTTP redirects

data/lib/anemone/core.rb

@@ -168,8 +168,9 @@ module Anemone
     def run
       process_options
 
-      @urls.delete_if { |url| !visit_link?(url) }
-      return if @urls.empty?
+      # trust that we're provided with URLs that have not yet been requested
+      #@urls.delete_if { |url| !visit_link?(url) }
+      #return if @urls.empty?
 
       link_queue = build_queue(@opts[:link_queue_size_limit])
       page_queue = build_queue(@opts[:page_queue_size_limit])

data/lib/anemone/storage/sqlite3.rb

@@ -11,6 +11,7 @@ module Anemone
 
       def initialize(file)
         @db = ::SQLite3::Database.new(file)
+        @db.busy_timeout = 4000
         create_schema
       end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: sutch-anemone
 version: !ruby/object:Gem::Version
-  version: 0.7.2
+  version: 0.7.2.1
 platform: ruby
 authors:
 - Chris Kite (Dennis Sutch's fork)
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-08-01 00:00:00.000000000 Z
+date: 2013-08-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri