husc 0.1.0 → 0.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 18698eb5d732d0d86377f031fd3dda73ff368c7ad4b10f9c7a5a45e08f325a98
-  data.tar.gz: 9907d28762adb13ac57ae7da4a530f23ce57794f71fb2a0c502a54a53d8b73f7
+  metadata.gz: 70da435ce2b15bb485ce958997a91488cf19f00b7faf5da3f25c92a891028508
+  data.tar.gz: b363fa06b547c1a5612889739465af7ea46cbeea6b6922aab0d484fa21169ce6
 SHA512:
-  metadata.gz: 698671388fa2b6da20b2af46e24d86eaad31f6d06a28633d83795eaf9b33473ad65c36a75791a7434414a9f64f895409b1097a786b9c79cb2e4669bb6d73140a
-  data.tar.gz: e856cb96440b8faa60f159becc6cdf26418462c57add0d46ffce5fb40f4d6193689fb05eff0867de144f5e175df60e398a1238b75bc1cf097eed21aa7ad6a875
+  metadata.gz: 2190d0269954730626eca1d142c8ffd00614bf98fb19d7ba4d595668e944d769636f26c151211a664ba775b2d9f1c3b5594bbd7d5cde05eec7af31e11f82dfff
+  data.tar.gz: 5f0ea49baf5d2fbf6a707f3b580e95364686c2a3e1439d8c3469c090335790ebeef062176e3d67e3afd7592b23e2256f92f6421a14e4b208c94b4e5a1e737a7f

data/README.md

@@ -1,7 +1,7 @@
-Crawler
+Husc
 =======
 
-Script for crawling in Ruby
+A simple crawling utility for Ruby.
 
 
 ## Description
@@ -16,29 +16,74 @@ This project enables site crawling and data extraction with xpath and css select
 ## Usage
 ### Simple Example
 ```ruby
-require './rbcrawl.rb'
+require 'husc'
 
 url = 'http://www.example.com/'
-doc = RbCrawl.new(url)
+doc = Husc(url)
 
-# Search for nodes by css
+# access another url
+doc.get('another url')
+
+# get current url
+doc.url
+
+# get current site's html
+doc.html
+
+# get <table> tags as dict
+doc.tables
+# ex) doc.tables['予約・お問い合わせ'] => 050-5596-6465
+```
+
+### Scraping Example
+```ruby
+# search for nodes by css selector
+# tag   : css('name')
+# class : css('.name')
+# id    : css('#name')
 doc.css('div')
 doc.css('.main-text')
 doc.css('#tadjs')
 
-# Search for nodes by xpath
+# search for nodes by xpath
 doc.xpath('//*[@id="top"]/div[1]')
 
-# Others
-doc.css('div').css('a')[2].attr('href')
-doc.css('p').innerText()
-doc.tables  # -> Table Tag to Dict
-
+# other example
+doc.css('div').css('a')[2].attr('href') # => string object
+doc.css('p').innerText() # => string object
 # You do not need to specify "[]" to access the first index
 ```
 
+### Submitting Form Example
+1. Specify target node's attribute
+2. Specify value(int or str) / check(bool) / file_name(str)
+3. call submit() with form attribute specified
+```ruby
+# login
+doc.send(id:'id attribute', value:'value to send')
+doc.send(id:'id attribute', value:'value to send')
+doc.submit(id:'id attribute') # submit
+
+# post file
+doc.send(id:'id attribute', file_name:'target file name')
+
+# checkbox
+doc.send(id:'id attribute', check:True)  # check
+doc.send(id:'id attribute', check:False) # uncheck
+
+# example of specify other attribute
+doc.send(name:'name attribute', value:'hello')
+doc.send(class:'class attribute', value:100)
+```
+
+
+
 
 ## Installation
 ```sh
 $ gem install husc
-```
+```
+
+
+## Contributing
+Bug reports and pull requests are welcome on GitHub at [https://github.com/AjxLab/PyCrawl](https://github.com/AjxLab/PyCrawl).

data/husc.gemspec

@@ -13,7 +13,7 @@ Gem::Specification.new do |spec|
   spec.required_ruby_version = Gem::Requirement.new(">= 2.3.0")
 
   spec.metadata["homepage_uri"] = spec.homepage
-  spec.metadata["source_code_uri"] = "https://github.com/AjxLab/Crawler."
+  spec.metadata["source_code_uri"] = "https://github.com/AjxLab/husc"
 
   # Specify which files should be added to the gem when it is released.
   # The `git ls-files -z` loads the files in the RubyGem that have been added into git.

data/lib/husc/version.rb

@@ -1,3 +1,3 @@
 module Husc
-  VERSION = "0.1.0"
+  VERSION = "0.1.1"
 end

data/lib/husc.rb

@@ -3,11 +3,12 @@ require 'mechanize'
 require 'nokogiri'
 require 'net/http'
 require 'kconv'
-require "husc/version"
+require 'husc/version'
 
 module Husc
   class Error < StandardError; end
-  class Husc
+
+  class Crawler
     attr_reader :url, :html, :tables, :params
 
     # 特殊配列
@@ -28,7 +29,7 @@ module Husc
 
       def method_missing(method, *args)
         if self == []
-          return eval("Husc.new(doc: nil).#{method}(*#{args})")
+          return eval("Crawler.new(doc: nil).#{method}(*#{args})")
         end
 
         return eval("self[0].#{method}(*#{args})")
@@ -118,7 +119,7 @@ module Husc
 
     def xpath(locator, single = false)
       ## -----*----- HTMLからXPath指定で要素取得 -----*----- ##
-      elements = CrawlArray.new(@doc.xpath(locator).map {|el| Husc.new(doc: el)})
+      elements = CrawlArray.new(@doc.xpath(locator).map {|el| Crawler.new(doc: el)})
       if single
         # シングルノード
         if elements[0] == nil
@@ -134,7 +135,7 @@ module Husc
 
     def css(locator, single = false)
       ## -----*----- HTMLからCSSセレクタで要素取得 -----*----- ##
-      elements = CrawlArray.new(@doc.css(locator).map {|el| Husc.new(doc: el)})
+      elements = CrawlArray.new(@doc.css(locator).map {|el| Crawler.new(doc: el)})
       if single
         # シングルノード
         if elements[0] == nil
@@ -211,3 +212,4 @@ module Husc
     end
   end
 end
+

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: husc
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
 platform: ruby
 authors:
 - Tatsuya Abe
@@ -1077,7 +1077,7 @@ licenses:
 - MIT
 metadata:
   homepage_uri: https://github.com/AjxLab/husc
-  source_code_uri: https://github.com/AjxLab/Crawler.
+  source_code_uri: https://github.com/AjxLab/husc
 post_install_message: 
 rdoc_options: []
 require_paths: