zhSieve 0.2.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 09ed25603348589c1d6143e3b2abbd385d14868c
+  data.tar.gz: c34c4681fc7c62385e4216cb4122e16d9ada77eb
+SHA512:
+  metadata.gz: 597563b7b3c9b360ed099bf48ac54e36146afeeea869286847abf71d98de2b5f5e6366f1bd0be18707cae9e40d9531911374782c398ec4282dc9ffb6d77334c1
+  data.tar.gz: c87182ee1d852b11301c7117f7cfe24891ecd8de7ffa9cb7f318162fa12220b8d8029ea345473f28466b25cd37819ccc43c90574304f33c84c671ccedb9def73

data/.gitignore

@@ -0,0 +1,14 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+# ignor local testing files
+localbackup
+cookies.txt
+/testfile

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.1.2
+before_install: gem install bundler -v 1.13.6

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,74 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at wxz138@case.edu. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in zhSieve.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2016 Wei Zhu
+
+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 +1,41 @@
+# zhSieve
+A ruby based zhihu content crawler
+
+[![license](https://img.shields.io/github/license/mashape/apistatus.svg)](https://github.com/gwzz/zhSieve/blob/master/LICENSE)
+[![Gem Version](https://badge.fury.io/rb/zhSieve.svg)](https://badge.fury.io/rb/zhSieve)
+###
+Status: under working :construction:
+
+### Pre-Request
+Create cookies.txt file and put it into root folder. (Mozilla cookies.txt-style)
+
+### Usage
+Crawler specific answer, and output it as markdown format.
+```shell
+$ zhSieve answer -q 'Your Question Id' -a 'Your Answer Id'
+```
+Crawler specific Zhuanlan article, and output it as markdown format.
+```shell
+$ zhSieve article -z 'Your Article Id'
+```
+### TO-DO List
+
+- [ ] Question :rotating_light:
+- [ ] Ansewer :checkered_flag:
+  - Use question_id and answer_id to crawler page information, and output a markdown file with ["question title and link", "author's avatar, name, biography", "answer content"].
+  - Testing:warning:!
+- [ ] People :construction:
+- [ ] ZhuanLan, cantains two components
+  -	1. Crawler single article :checkered_flag:
+  - 2. Crawler someone's zhuanlan category :rotating_light:
+
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/gwzz/zhSieve. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
+

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "zhSieve"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/exe/zhSieve

@@ -0,0 +1,3 @@
+#!/usr/bin/env ruby
+require 'zhSieve/cli'
+ZhSieve::CLI.start

data/lib/zhSieve.rb

@@ -0,0 +1,58 @@
+require "zhSieve/version"
+require "zhSieve/htmlpage"
+require "zhSieve/html2md"
+require 'mechanize'
+
+module ZhSieve
+	BASE_URL = "https://www.zhihu.com"
+	ZL_URI = "https://zhuanlan.zhihu.com/api/posts/"
+	def self.crawl_answer(options)
+		question_id = "#{options[:question_id]}"
+		question_uri = "/question/#{question_id}"
+		answer_id = "#{options[:answer_id]}"
+		answer_uri = "#answer-#{answer_id}"
+		search_uri = "#{BASE_URL}#{question_uri}#{answer_uri}"
+		agent = Mechanize.new
+		agent.user_agent = 'Chrome/53.0.2785.143'
+		agent.max_history = 1
+		# Dir.chdir(File.dirname(__FILE__))
+		agent.cookie_jar.load_cookiestxt("./cookies.txt")
+		search_page = agent.get("#{search_uri}")
+		haha = HTMLPage.new(contents:search_page,question_id:question_id,answer_id:answer_id).answerMarkdown
+	end
+
+	def self.crawl_zl_people(options)
+
+	end
+
+	def self.crawl_zl_article(options)
+		article_id = "#{options[:article_id]}"
+		search_uri = "#{ZL_URI}#{article_id}"
+		agent = Mechanize.new
+		agent.user_agent = 'Chrome/53.0.2785.143'
+		agent.max_history = 1
+		# Dir.chdir(File.dirname(__FILE__))
+		agent.cookie_jar.load_cookiestxt("./cookies.txt")
+		search_page = agent.get("#{search_uri}")
+		haha = HTMLPage.new(contents:search_page,article_id:article_id).articleMarkdown
+	end
+	# BASE_URL = "https://www.zhihu.com"
+	# question_id = "43830406"
+	# question_uri = "/question/#{question_id}"
+	# answer_id = "46959669"
+	# answer_uri = "#answer-#{answer_id}"
+	# PEOPLE_id = "/people/"
+	# LIST_URL = "#{BASE_URL}/question/51727516#answer-46414810"
+	# HEADERS_HASH = {"User-Agent" => "Chrome/53.0.2785.143"}
+
+	# arguments = ARGV
+
+	# agent = Mechanize.new
+	# agent.user_agent = 'Chrome/53.0.2785.143'
+	# agent.max_history = 1
+	# Dir.chdir(File.dirname(__FILE__))
+	# agent.cookie_jar.load_cookiestxt("../cookies.txt")
+	# # search_page = agent.get(BASE_URL+PEOPLE_URL)
+	# search_page = agent.get("https://www.zhihu.com#{question_uri}#{answer_uri}")
+	# haha = HTMLPage.new(contents:search_page,question_id:question_id,answer_id:answer_id)
+end

data/lib/zhSieve/answer.rb

@@ -0,0 +1,23 @@
+class Answer
+	attr_accessor :author,:bio,:avatar,:author_link,:content,:question,:link
+
+	def initialize
+		@author = 'NA'
+		@bio = 'NA'
+		@avatar = 'NA'
+		@link = 'NA'
+		@content = 'NA'
+		@question = 'NA'
+		@author_link = 'NA'
+	end
+
+	def format_markdown
+		res_file = "## " + "[#{@question}](" + @link + ")" + "\n"
+		res_file += "### "+@avatar + "[#{@author}](" + @author_link + ")"  + "\n"
+		res_file += "#### "+@bio + "\n"
+		res_file += "*****\n"
+		res_file += @content
+		res_file
+	end
+
+end

data/lib/zhSieve/article.rb

@@ -0,0 +1,26 @@
+class Article
+	attr_accessor :author,:bio,:avatar,:author_link,:content,:link,:title,:title_image,:published_time
+
+	def initialize
+		@author = 'NA'
+		@bio = 'NA'
+		@avatar = 'NA'
+		@link = 'NA'
+		@content = 'NA'
+		@author_link = 'NA'
+		@title = 'NA'
+		@title_image = 'NA'
+		@published_time = 'NA'
+	end
+
+	def format_markdown
+		res_file = "## [#{@title}](#{@link})" + "\n"
+		res_file += "### "+@avatar + "[#{@author}](" + @author_link + ")"  + "\n"
+		res_file += "#### "+ @bio + "\n"
+		res_file += "*****\n"
+		res_file += @title_image
+		res_file += @content
+		res_file
+	end
+
+end

data/lib/zhSieve/cli.rb

@@ -0,0 +1,25 @@
+require 'thor'
+require 'zhSieve'
+
+module ZhSieve
+  class CLI < Thor
+  desc "version", "Show current version"
+	def version
+		puts ZhSieve::VERSION
+	end
+
+	desc "answer", "Set the question id [Q], answer id [A]"
+	option :q, :required => true
+	option :a, :required => true
+	def answer
+		puts ZhSieve.crawl_answer(question_id:options[:q],answer_id:options[:a])
+	end
+
+  desc "article", "Set the zhuanlan article id [Z]"
+  option :z, :required => true
+  def article
+    puts ZhSieve.crawl_zl_article(article_id:options[:z])
+  end
+
+  end
+end

data/lib/zhSieve/html2md.rb

@@ -0,0 +1,135 @@
+require 'nokogiri'
+require 'json'
+require_relative 'people'
+require_relative 'answer'
+require_relative 'article'
+
+module ZhSieve
+  module Converter
+    def to_markdown string_contents
+      raise NoContents unless string_contents!=nil 
+      doc = Nokogiri::HTML(string_contents,'UTF-8')
+      doc.children.map { |ele| parse_element(ele) }.join
+    end
+
+    def people_to_markdown string_contents
+      raise NoContents unless string_contents!=nil 
+      doc = Nokogiri::HTML(string_contents,'UTF-8')
+      search_user = People.new
+      # set people info
+    end
+
+    def answer_to_markdown string_contents,question_id,answer_id
+      raise NoContents unless string_contents!=nil
+      doc = Nokogiri::HTML(string_contents,'UTF-8')
+      answer_node = doc.search '[data-aid="'+answer_id.to_s+'"]'
+      search_answer = Answer.new
+      # search and set question infomations
+      avatar_raw = answer_node.search '[class="zm-list-avatar avatar"]'
+      author_raw = answer_node.search '[class="author-link"]'
+      bio_raw = answer_node.search '[class="bio"]'
+      content_raw = answer_node.search '[class="zm-editable-content clearfix"]'
+      search_answer.question = doc.title.strip
+      search_answer.link = "https://www.zhihu.com/people/#{question_id}#answer-#{answer_id}"
+      search_answer.avatar= parse_element(avatar_raw.first)
+      search_answer.bio = parse_element(bio_raw.first)
+      search_answer.content = parse_element(content_raw.first)
+      author_info = parse_element(author_raw.first).split(/[\[\]\(\)]/)
+      search_answer.author = author_info[1]
+      search_answer.author_link = "https://www.zhihu.com" + author_info[3]
+      markdown_text = search_answer.format_markdown
+    end
+
+    def article_to_markdown string_contents,article_id
+      raise NoContents unless string_contents!=nil
+      doc_hash = JSON.parse(string_contents)
+      search_article = Article.new
+      search_article.title = doc_hash["title"]
+      search_article.title_image = "![](#{doc_hash["titleImage"]})"
+      search_article.published_time = doc_hash['publishedTime']
+      search_article.link = "https://zhuanlan.zhihu.com/p/#{article_id}"
+      search_article.content = doc_hash["content"]
+      search_article.author = doc_hash["author"]["name"]
+      search_article.bio = doc_hash["author"]["bio"] || "No Bio!"
+      search_article.author_link = doc_hash["author"]["profileUrl"]
+      avatar_template = doc_hash["author"]["avatar"]["template"].gsub('{size}','s')
+      avatar_id = doc_hash["author"]["avatar"]["id"]
+      avatar_uri = avatar_template.gsub('{id}', "#{avatar_id}")
+      search_article.avatar = "![](#{avatar_uri})"
+      markdown_text = search_article.format_markdown
+    end
+
+    def parse_element(ele)
+      if ele.is_a? Nokogiri::XML::Text
+        return "#{ele.text}\n"
+      else
+        if (children = ele.children).count > 0 
+          return wrap_node(ele,children.map {|ele| parse_element(ele)}.join )
+        else
+          return wrap_node(ele,ele.text)
+        end
+      end
+    end
+
+    # wrap node with markdown
+    def wrap_node(node,contents=nil)
+      result = ''
+      contents.strip! unless contents==nil
+      # check if there is a custom parse exist
+      if respond_to? "parse_#{node.name}"
+        return self.send("parse_#{node.name}",node,contents)
+      end
+      # skip hidden node
+      return '' if node['style'] and node['style'] =~ /display:\s*none/
+      # default parse
+      case node.name.downcase
+      when 'i'
+      when 'script'
+      when 'style'
+      when 'li'
+        result << "*#{contents}\n"
+      when 'blockquote'
+        contents.split('\n').each do |part|
+          result << ">#{contents}\n"
+        end
+      when 'p'
+        result << "\n#{contents}\n"
+      when 'strong'
+        result << "**#{contents}**\n"
+      when 'h1'
+        result << "# #{contents}\n"
+      when 'h2'
+        result << "## #{contents}\n"
+      when 'h3'
+        result << "### #{contents}\n"
+      when 'hr'
+        result << "****\n"
+      when 'br'
+        result << "\n"
+      when 'img'
+        result << "![#{node['alt']}](#{node['src']})"
+      when 'a'
+        result << "[#{contents}](#{node['href']})"
+      else
+        result << contents unless contents == nil
+      end
+      result
+    end
+
+    # define custom node processor
+    def method_missing(name,*args,&block)
+      self.class.send :define_method,"parse_#{name}" do |node,contents|
+        block.call node,contents
+      end
+    end
+
+    def debug
+      puts '----------------------------------'
+      puts yield
+      puts '----------------------------------'
+    end
+
+  end
+
+  class NoContents < Exception;end
+end

data/lib/zhSieve/htmlpage.rb

@@ -0,0 +1,39 @@
+require_relative 'html2md'
+module ZhSieve
+  class HTMLPage
+  include ZhSieve::Converter
+    attr_accessor :contents,:question_id,:answer_id,:article_id
+
+    def initialize(options)
+      @contents = options[:contents].body
+      @question_id = options[:question_id]
+      @answer_id = options[:answer_id]
+      @article_id = options[:article_id]
+    end
+
+    def peopleMarkdown
+      @markdown = people_to_markdown(@contents)
+    end
+
+    def answerMarkdown
+      @markdown = answer_to_markdown(@contents,@question_id,@answer_id)
+    end
+
+    def articleMarkdown
+      @markdown = article_to_markdown(@contents,@article_id)
+    end
+
+    def to_html
+      @html =  @contents
+    end
+
+    def markdown
+      @markdown ||= markdown!
+    end
+
+    def markdown!
+      @markdown = to_markdown(@contents)
+    end
+
+  end
+end

data/lib/zhSieve/people.rb

@@ -0,0 +1,14 @@
+class People
+	attr_accessor :name,:bio,:avatar,:location,:business,:education,:detail
+
+	def initialize
+		@name = 'NA'
+		@avatar = 'NA'
+		@location = 'NA'
+		@business = 'NA'
+		@education = 'NA'
+		@detail = 'NA'
+		@bio = 'NA'
+	end
+
+end

data/lib/zhSieve/version.rb

@@ -0,0 +1,3 @@
+module ZhSieve
+  VERSION = "0.2.0"
+end

data/lib/zhSieve/zhuanlan.rb

@@ -0,0 +1,12 @@
+class Zhuanlan
+	attr_accessor :author,:bio,:avatar,:author_link,:content,:link
+
+	def initialize
+
+	end
+
+	def format_markdown
+
+	end
+
+end

data/zhSieve.gemspec

@@ -0,0 +1,41 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'zhSieve/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "zhSieve"
+  spec.version       = ZhSieve::VERSION
+  spec.authors       = ["Wei Zhu"]
+  spec.email         = ["zhucyw@gmail.com"]
+
+  spec.summary       = "A ruby based zhihu content crawler."
+  spec.description   = "A ruby based zhihu content crawler."
+  spec.homepage      = "https://github.com/gwzz/zhSieve"
+  spec.license       = "MIT"
+
+  # Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
+  # to allow pushing to a single host or delete this section to allow pushing to any host.
+  if spec.respond_to?(:metadata)
+    spec.metadata['allowed_push_host'] = "https://rubygems.org"
+  else
+    raise "RubyGems 2.0 or newer is required to protect against " \
+      "public gem pushes."
+  end
+
+  spec.files         = `git ls-files -z`.split("\x0").reject do |f|
+    f.match(%r{^(test|spec|features)/})
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.13"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+  spec.add_development_dependency "cucumber"
+  spec.add_development_dependency "aruba"
+  spec.add_dependency "activesupport", "~> 4.2.0"
+  spec.add_dependency "thor"
+  spec.add_dependency "mechanize"
+end

metadata

@@ -0,0 +1,179 @@
+--- !ruby/object:Gem::Specification
+name: zhSieve
+version: !ruby/object:Gem::Version
+  version: 0.2.0
+platform: ruby
+authors:
+- Wei Zhu
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2016-11-04 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.13'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.13'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: cucumber
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: aruba
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: activesupport
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 4.2.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 4.2.0
+- !ruby/object:Gem::Dependency
+  name: thor
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: mechanize
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: A ruby based zhihu content crawler.
+email:
+- zhucyw@gmail.com
+executables:
+- zhSieve
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- exe/zhSieve
+- lib/zhSieve.rb
+- lib/zhSieve/answer.rb
+- lib/zhSieve/article.rb
+- lib/zhSieve/cli.rb
+- lib/zhSieve/html2md.rb
+- lib/zhSieve/htmlpage.rb
+- lib/zhSieve/people.rb
+- lib/zhSieve/version.rb
+- lib/zhSieve/zhuanlan.rb
+- zhSieve.gemspec
+homepage: https://github.com/gwzz/zhSieve
+licenses:
+- MIT
+metadata:
+  allowed_push_host: https://rubygems.org
+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: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.2.2
+signing_key: 
+specification_version: 4
+summary: A ruby based zhihu content crawler.
+test_files: []