movie_spider 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 5f678d1d4e3479f2fa48b889671b7bc2d915208c
+  data.tar.gz: bdf47ebf540ed0cb9374e46038d5f2913b236dd0
+SHA512:
+  metadata.gz: fd34d70d9da3c88b3d38f2692949d2e07162d2a7fe8c860c98a580362ddf9c3670782a185f4dbbaf5f9ccabae310cc1f8af369a7bec01549e30225379a62e508
+  data.tar.gz: c75f433426d2f5425259a17d06238e8e3155ad2933d1a1ac37123c6ffd6e36a5a6a0b7cb82d9560112c40b87479d9f8e80a2c04d545ab5856e903d8c94ed1a4f

data/.gitignore

@@ -0,0 +1,15 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+*.bundle
+*.so
+*.o
+*.a
+mkmf.log
+*.gem

data/Gemfile

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

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2015 hzlu
+
+MIT License
+
+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 +1,31 @@
+# MovieSpider
+
+TODO: Write a gem description
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'movie_spider'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install movie_spider
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Contributing
+
+1. Fork it ( https://github.com/[my-github-username]/movie_spider/fork )
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create a new Pull Request

data/Rakefile

@@ -0,0 +1,2 @@
+require "bundler/gem_tasks"
+

data/lib/movie_spider/douban_fetcher.rb

@@ -0,0 +1,58 @@
+# coding: utf-8
+
+module MovieSpider
+  class DoubanMovie
+    UrlPrefix = "http://api.douban.com/v2/"
+    Key = "0c89712b2297db4e259c538167c791ea"
+    def get_subject(movie_id)
+      path = "movie/subject/#{movie_id}?apikey=#{Key}"
+      data = api_get(path)
+    end
+
+    def douban_search_movie(movie_name)
+      movie_name = movie_name.gsub(/\[.+\]/, "")
+      path = "movie/search?q=#{movie_name}&apikey=#{Key}"
+      data = api_get(path)["subjects"]
+    end
+
+    def api_get(path)
+      begin
+        data = RestClient.get URI.encode(UrlPrefix + path)
+        JSON.parse data
+      rescue Timeout::Error => e  
+        ExceptionNotifier::Notifier.background_exception_notification(e).deliver
+        Rails.logger.error "获取豆瓣API: #{UrlPrefix}movie/search?q=#{movie_name}超时出错..."
+      rescue JSON::JSONError => e
+        ExceptionNotifier::Notifier.background_exception_notification(e).deliver
+        Rails.logger.error "获取豆瓣API: #{UrlPrefix}movie/suject/#{movie_id}数据JSON.parse出错..."
+      end
+    end
+
+    def douban_movie_stills(douban_id)
+      fetch_img("http://movie.douban.com/subject/#{douban_id}/photos?type=S&start=0&sortby=vote&size=a&subtype=o")
+    end
+
+    def douban_movie_posters(douban_id)
+      fetch_img("http://movie.douban.com/subject/#{douban_id}/photos?type=R&start=0&sortby=vote&size=a&subtype=a")
+    end
+
+    def fetch_img(url) 
+      begin
+        doc = Nokogiri::HTML(open(url))
+      rescue
+        return []
+      end
+      as = doc.css("ul li div.cover a")
+      photos = []
+      as.each do |a|
+        photos << a.css("img").first.attributes["src"].value.sub("thumb", "photo") rescue next
+      end
+      if doc.css("span.next a").first.present?
+        url = doc.css("span.next a").first.attributes["href"].value
+        photos = photos + fetch_img(url)
+      end
+      photos.uniq
+    end
+
+  end
+end

data/lib/movie_spider/mtime_fetcher.rb

@@ -0,0 +1,85 @@
+# coding: utf-8
+module MovieSpider
+  class MtimeMovie
+    #获取官方剧照，三种参数选择img_200 img_235 img_1000,注意235的尺寸可能会fetch不到，期望使用220或1000
+    def get_mtime_stills(movie_title, img_size="img_1000")
+      parse_mtime(movie_title, "officialstageimage", img_size)
+    end
+    #获取正式海报
+    def get_general_posters(movie_title, img_size="img_1000")
+      parse_mtime(movie_title, "generalposter", img_size)
+    end
+    #获取预告海报
+    def get_forecast_posters(movie_title, img_size="img_1000")
+      parse_mtime(movie_title, "forecastposter", img_size)
+    end
+    #获取角色海报
+    def get_role_posters(movie_title, img_size="img_1000")
+      parse_mtime(movie_title, "roleposter", img_size)
+    end
+    #全部海报
+    def get_mtime_posters(movie_title, img_size="img_1000")
+      posters = []
+      posters += get_general_posters(movie_title, img_size) + get_forecast_posters(movie_title,img_size) + get_role_posters(movie_title, img_size)
+      posters.delete(nil);posters.delete("")
+      posters
+    end
+    #获取时光网电影评分
+    def get_mtime_rating(movie_title)
+      fetch_result = parse_search(movie_title)
+      if fetch_result.is_a?(Hash)
+        movie_result = fetch_result['value']['movieResult']
+        if movie_result['directMovie'].empty?
+        #无法命中电影标题时
+          return "影片暂无评分" if movie_result['moreMovies'][0]['movieRating'].nil?
+          movie_result['moreMovies'][0]['movieRating']
+        else
+        #直接查找出电影
+          return "影片暂无评分" if movie_result['directMovie']['movieRating'].nil?
+          movie_result['directMovie']['movieRating']
+        end
+      else
+        "解析出错，暂无评分"
+      end
+    end
+
+    private
+    #解析时光网search API返回
+    def parse_search(movie_title)
+      begin
+        result_str = open(URI::encode("http://service.channel.mtime.com/Search.api?Ajax_CallBack=true&Ajax_CallBackType=Mtime.Channel.Services&Ajax_CallBackMethod=GetSearchResult&Ajax_CrossDomain=1&Ajax_CallBackArgument0=#{movie_title}")).read
+      rescue
+        return ""
+      end
+      result_str.scan(/{.*}/) {|match| return JSON.parse(match)}
+    end
+    def get_mtime_movie_id_by_title(movie_title)
+      movie_result = {}
+      begin
+        movie_result = parse_search(movie_title)['value']['movieResult']
+      rescue
+        return ""
+      end
+      if movie_result['directMovie'].empty?
+        movie_result['moreMovies'][0]['movieId']
+      else
+        movie_result['directMovie']['movieId']
+      end
+    end
+    #解析时光网JS返回变量
+    def parse_mtime(movie_title, type, img_size)
+      movie_id = get_mtime_movie_id_by_title(movie_title)
+      begin
+        html_doc = Nokogiri::HTML(open("http://movie.mtime.com/#{movie_id}/posters_and_images/posters/hot.html"))
+        parser = ""
+        html_doc.css("body").search("script")[1].text.scan(/{"#{type}".*?}\]}/) {|match| parser = JSON.parse(match) }
+        parser[type].map do |item|
+          item[img_size]
+        end
+      rescue
+        return []
+      end
+    end
+
+  end
+end

data/lib/movie_spider/version.rb

@@ -0,0 +1,3 @@
+module MovieSpider
+  VERSION = "0.0.1"
+end

data/lib/movie_spider.rb

@@ -0,0 +1,56 @@
+require "movie_spider/version"
+require "movie_spider/douban_fetcher"
+require "movie_spider/mtime_fetcher"
+require 'json'
+require 'open-uri'
+
+module MovieSpider
+  def self.get_title_from_douban_id(douban_id)
+    DoubanMovie.new.get_subject(douban_id)["title"]
+  end
+
+  def self.fetch_stills(douban_id,source)
+    title = get_title_from_douban_id(douban_id)
+    case source
+    when /douban/
+      stills = DoubanMovie.new.douban_movie_stills(douban_id)
+    when /mtime/
+      stills = MtimeMovie.new.get_mtime_stills(title)
+    when /all/
+      stills = DoubanMovie.new.douban_movie_stills(douban_id) + MtimeMovie.new.get_mtime_stills(title)
+    end
+    stills
+  end
+
+  def self.fetch_posters(douban_id,source)
+    title = get_title_from_douban_id(douban_id)
+    case source
+    when /douban/
+      posters = DoubanMovie.new.douban_movie_posters(douban_id)
+    when /mtime/
+      posters = MtimeMovie.new.get_mtime_posters(title)
+    when /all/
+      posters = DoubanMovie.new.douban_movie_posters(douban_id) + MtimeMovie.new.get_mtime_posters(title)
+    end
+    posters
+  end
+
+  def self.fetch_rating(douban_id, source)
+    title = get_title_from_douban_id(douban_id)
+    if source =~ /douban/
+      DoubanMovie.new.get_subject(douban_id)["rating"]["average"]
+    elsif source =~ /mtime/
+      MtimeMovie.new.get_mtime_rating(title)
+    else
+      "评分网站参数错误[douban|mtime]"
+    end
+  end
+
+  def self.get_subject(douban_id)
+    DoubanMovie.new.get_subject(douban_id)
+  end
+
+  def self.douban_search_movie(movie_name)
+    DoubanMovie.new.douban_search_movie(movie_name)
+  end
+end

data/movie_spider.gemspec

@@ -0,0 +1,24 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'movie_spider/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "movie_spider"
+  spec.version       = MovieSpider::VERSION
+  spec.authors       = ["hzlu"]
+  spec.email         = ["hzlu2010@163.com"]
+  spec.summary       = %q{fetch movies' infomation}
+  spec.description   = %q{fetch Mtime and Douban, movie posters, stills, and rating.}
+  spec.homepage      = "http://www.dan-che.com"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0") + ["lib/movie_spider/douban_fetcher.rb", "lib/movie_spider/mtime_fetcher.rb"]
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.7"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "nokogiri", "~> 2.0"
+end

metadata

@@ -0,0 +1,96 @@
+--- !ruby/object:Gem::Specification
+name: movie_spider
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- hzlu
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-03-04 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.7'
+- !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: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.0'
+description: fetch Mtime and Douban, movie posters, stills, and rating.
+email:
+- hzlu2010@163.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/movie_spider.rb
+- lib/movie_spider/douban_fetcher.rb
+- lib/movie_spider/mtime_fetcher.rb
+- lib/movie_spider/version.rb
+- movie_spider.gemspec
+homepage: http://www.dan-che.com
+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: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.5
+signing_key: 
+specification_version: 4
+summary: fetch movies' infomation
+test_files: []