wcrawler 0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 3edfb127df16c0d081013257c89526ddf3c80b91
+  data.tar.gz: 972479202985b4f9fea112ea9ebb881a15cfa6e1
+SHA512:
+  metadata.gz: 16df66e728189400c2488238913fb8026957eac78fcd96e7e5cf195978d3108af6aa10ff40e459ee206860608577ce204fc6eb549359e33f60f7f80b3cdb33e4
+  data.tar.gz: 099de1e9c2e6362cab78212a13759832e177f560c047b18d99318e2746fd6bfa83a6a6de0f1f5dcdb83dd1b22b0c36599bd392bb173827804cca86757f9e88bd

data/LICENSE.md

@@ -0,0 +1,20 @@
+Copyright (c) 2010 J.K et al.
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,5 @@
+# This tool is for downloading file from weipan.
+
+## To do list:
+ - Support to directory. Example: http://vdisk.weibo.com/u/3262874910
+ - Good Test case 2554082943

data/bin/wcrawler

@@ -0,0 +1,6 @@
+#!/usr/bin/env ruby
+# -*- mode: ruby -*-
+
+require "wei_disk_crawler_cli"
+
+WeiDiskCrawlerCLI.start(ARGV)

data/lib/version.rb

@@ -0,0 +1,3 @@
+class WeiDiskCrawler
+  VERSION = "0.1"
+end

data/lib/wcrawler/wei_disk_crawler.rb

@@ -0,0 +1,87 @@
+require 'nokogiri'
+require 'open-uri'
+require 'typhoeus'
+require 'json'
+
+class WeiDiskCrawler
+
+  WEI_DISK_PREFIX = "http://vdisk.weibo.com/u/"
+
+  def initialize(params = {})
+    raise "Missing User ID" if params[:uid].nil?
+    @uid = params[:uid]
+    @resources = {}
+    @page_total = 0
+  end
+
+  def max_page_number
+    return @page_total unless @page_total.eql? 0
+    request = Typhoeus::Request.new(WEI_DISK_PREFIX + "#{@uid}")
+    request.run
+    response_body = Nokogiri::HTML(request.response.response_body)
+    return @page_total = 1 if response_body.css('.vd_page_main .vd_page').empty?
+    @page_total = response_body.css('.vd_page a:nth-last-child(2)').text.to_i
+  end
+
+  def list_all_resources
+    (1..max_page_number).each do |page_number|
+      @resources = @resources.merge(list_resources_on_page page_number)
+    end
+    @resources
+  end
+
+  def list_resources_on_page page_number
+    hydra = Typhoeus::Hydra.new
+
+    page_request = Typhoeus::Request.new(WEI_DISK_PREFIX + "#{@uid}" + "?page=#{page_number}")
+
+    page_request.on_complete do |response|
+      page_doc = Nokogiri::HTML(response.response_body)
+
+      resource_urls = page_doc.css('td.sort_name_m div.sort_name_pic a').map { |x| x.attr('href') }
+      resource_ids = resource_urls.map { |url| url.split(/\//).last }
+
+      requests = resource_ids.map do |resource_id|
+        now_timestamp = Time.now.to_datetime.strftime '%Q'
+        request = Typhoeus::Request.new(
+            "http://vdisk.weibo.com/api/weipan/fileopsStatCount?link=#{resource_id}&ops=download&_=#{now_timestamp}",
+            :method => :get,
+            headers: {
+                :Accept => "application/json, text/javascript, */*; q=0.01",
+                :Referer => "http://vdisk.weibo.com/s/#{resource_id}",
+                :'X-Requested-With' => "XMLHttpRequest",
+                :'Connection' => "keep-alive",
+                :'x-response-version' => "2"
+            }
+        )
+        request.on_complete do |ajax_response|
+            p "#{JSON.parse(ajax_response.response_body)['name']} has been parsed successfully."
+        end
+
+        hydra.queue request
+        request
+      end
+
+      hydra.run
+
+      requests.each do |request|
+        json = JSON.parse(request.response.response_body)
+        @resources[json["name"]] = json["download_list"].first
+      end
+
+    end
+
+    hydra.queue page_request
+    hydra.run
+    p "#"*50
+    p "Page #{page_number} has been parsed successfully."
+    p "#"*50
+    @resources
+  end
+
+  def write_resources_to_file file_name
+    File.open("downloads/#{file_name}", 'a') { |file| file.write(list_all_resources) }
+  end
+end
+
+

data/lib/wei_disk_crawler_cli.rb

@@ -0,0 +1,30 @@
+require 'wcrawler/wei_disk_crawler'
+require 'thor'
+
+class WeiDiskCrawlerCLI < Thor
+  desc "crawl UID", "crawl resources from UID"
+  option :uid, :required => true
+  def crawl
+    crawler = WeiDiskCrawler.new({:uid => options[:uid]})
+    crawler.list_all_resources
+  end
+
+  desc "list <page-number>", "list resources from all pages / specific page number"
+  option :uid, :required => true
+  def list(page_number=nil)
+    crawler = WeiDiskCrawler.new({:uid => options[:uid]})
+    if page_number
+      p crawler.list_resources_on_page page_number
+    else
+      p crawler.list_all_resources
+    end
+  end
+
+  desc "max_page_num", "list max page number"
+  option :uid, :required => true
+  def max_page_num
+    crawler = WeiDiskCrawler.new({:uid => options[:uid]})
+    p "There's #{crawler.max_page_number} pages in #{options[:uid]}'s resource"
+  end
+end
+

data/wcrawler.gemspec

@@ -0,0 +1,20 @@
+# coding: utf-8
+lib = File.expand_path("../lib/", __FILE__)
+$LOAD_PATH.unshift lib unless $LOAD_PATH.include?(lib)
+require "version"
+
+Gem::Specification.new do |spec|
+  spec.add_development_dependency "bundler", "~> 1.0"
+  spec.authors = ["J.K"]
+  spec.summary     = "Downloader Gem No.1"
+  spec.description = "This is a tool to provide a easy way to download the resources from weipan"
+  spec.email = "jiukunz@gmail.com"
+  spec.executables = %w[wcrawler]
+  spec.files = %w[wcrawler.gemspec] + Dir['*.md', 'bin/*', 'lib/**/*.rb']
+  spec.licenses = %w[MIT]
+  spec.name = "wcrawler"
+  spec.homepage = "http://jiukunz.github.io/"
+  spec.require_paths = %w[lib]
+  spec.required_rubygems_version = ">= 1.3.5"
+  spec.version = WeiDiskCrawler::VERSION
+end

metadata

@@ -0,0 +1,65 @@
+--- !ruby/object:Gem::Specification
+name: wcrawler
+version: !ruby/object:Gem::Version
+  version: '0.1'
+platform: ruby
+authors:
+- J.K
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-02-04 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+description: This is a tool to provide a easy way to download the resources from weipan
+email: jiukunz@gmail.com
+executables:
+- wcrawler
+extensions: []
+extra_rdoc_files: []
+files:
+- LICENSE.md
+- README.md
+- bin/wcrawler
+- lib/version.rb
+- lib/wcrawler/wei_disk_crawler.rb
+- lib/wei_disk_crawler_cli.rb
+- wcrawler.gemspec
+homepage: http://jiukunz.github.io/
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 1.3.5
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.5
+signing_key: 
+specification_version: 4
+summary: Downloader Gem No.1
+test_files: []