├── .gitignore ├── CHANGELOG ├── Gemfile ├── Gemfile.lock ├── MIT-LICENSE ├── README.rdoc ├── Rakefile ├── cheat ├── scrapi.html ├── scrapi.pdf └── scrapi.txt ├── lib ├── html │ ├── document.rb │ ├── htmlparser.rb │ ├── node.rb │ ├── node_ext.rb │ ├── selector.rb │ ├── tokenizer.rb │ └── version.rb ├── scraper │ ├── base.rb │ ├── microformats.rb │ └── reader.rb ├── scrapi.rb └── tidy │ ├── libtidy.dll │ └── libtidy.so ├── scrapi.gemspec └── test ├── mock_net_http.rb ├── node_ext_test.rb ├── reader_test.rb ├── scraper_test.rb └── selector_test.rb /.gitignore: -------------------------------------------------------------------------------- 1 | .bundle 2 | *.gem 3 | -------------------------------------------------------------------------------- /CHANGELOG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/CHANGELOG -------------------------------------------------------------------------------- /Gemfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/Gemfile -------------------------------------------------------------------------------- /Gemfile.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/Gemfile.lock -------------------------------------------------------------------------------- /MIT-LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/MIT-LICENSE -------------------------------------------------------------------------------- /README.rdoc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/README.rdoc -------------------------------------------------------------------------------- /Rakefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/Rakefile -------------------------------------------------------------------------------- /cheat/scrapi.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/cheat/scrapi.html -------------------------------------------------------------------------------- /cheat/scrapi.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/cheat/scrapi.pdf -------------------------------------------------------------------------------- /cheat/scrapi.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/cheat/scrapi.txt -------------------------------------------------------------------------------- /lib/html/document.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/lib/html/document.rb -------------------------------------------------------------------------------- /lib/html/htmlparser.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/lib/html/htmlparser.rb -------------------------------------------------------------------------------- /lib/html/node.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/lib/html/node.rb -------------------------------------------------------------------------------- /lib/html/node_ext.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/lib/html/node_ext.rb -------------------------------------------------------------------------------- /lib/html/selector.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/lib/html/selector.rb -------------------------------------------------------------------------------- /lib/html/tokenizer.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/lib/html/tokenizer.rb -------------------------------------------------------------------------------- /lib/html/version.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/lib/html/version.rb -------------------------------------------------------------------------------- /lib/scraper/base.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/lib/scraper/base.rb -------------------------------------------------------------------------------- /lib/scraper/microformats.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/lib/scraper/microformats.rb -------------------------------------------------------------------------------- /lib/scraper/reader.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/lib/scraper/reader.rb -------------------------------------------------------------------------------- /lib/scrapi.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/lib/scrapi.rb -------------------------------------------------------------------------------- /lib/tidy/libtidy.dll: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/lib/tidy/libtidy.dll -------------------------------------------------------------------------------- /lib/tidy/libtidy.so: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/lib/tidy/libtidy.so -------------------------------------------------------------------------------- /scrapi.gemspec: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/scrapi.gemspec -------------------------------------------------------------------------------- /test/mock_net_http.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/test/mock_net_http.rb -------------------------------------------------------------------------------- /test/node_ext_test.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/test/node_ext_test.rb -------------------------------------------------------------------------------- /test/reader_test.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/test/reader_test.rb -------------------------------------------------------------------------------- /test/scraper_test.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/test/scraper_test.rb -------------------------------------------------------------------------------- /test/selector_test.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/assaf/scrapi/HEAD/test/selector_test.rb --------------------------------------------------------------------------------