movie_spider 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +15 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +31 -0
- data/Rakefile +2 -0
- data/lib/movie_spider/douban_fetcher.rb +58 -0
- data/lib/movie_spider/mtime_fetcher.rb +85 -0
- data/lib/movie_spider/version.rb +3 -0
- data/lib/movie_spider.rb +56 -0
- data/movie_spider.gemspec +24 -0
- metadata +96 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 5f678d1d4e3479f2fa48b889671b7bc2d915208c
|
4
|
+
data.tar.gz: bdf47ebf540ed0cb9374e46038d5f2913b236dd0
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: fd34d70d9da3c88b3d38f2692949d2e07162d2a7fe8c860c98a580362ddf9c3670782a185f4dbbaf5f9ccabae310cc1f8af369a7bec01549e30225379a62e508
|
7
|
+
data.tar.gz: c75f433426d2f5425259a17d06238e8e3155ad2933d1a1ac37123c6ffd6e36a5a6a0b7cb82d9560112c40b87479d9f8e80a2c04d545ab5856e903d8c94ed1a4f
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2015 hzlu
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,31 @@
|
|
1
|
+
# MovieSpider
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'movie_spider'
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install movie_spider
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
TODO: Write usage instructions here
|
24
|
+
|
25
|
+
## Contributing
|
26
|
+
|
27
|
+
1. Fork it ( https://github.com/[my-github-username]/movie_spider/fork )
|
28
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
29
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
30
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
31
|
+
5. Create a new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,58 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
|
3
|
+
module MovieSpider
|
4
|
+
class DoubanMovie
|
5
|
+
UrlPrefix = "http://api.douban.com/v2/"
|
6
|
+
Key = "0c89712b2297db4e259c538167c791ea"
|
7
|
+
def get_subject(movie_id)
|
8
|
+
path = "movie/subject/#{movie_id}?apikey=#{Key}"
|
9
|
+
data = api_get(path)
|
10
|
+
end
|
11
|
+
|
12
|
+
def douban_search_movie(movie_name)
|
13
|
+
movie_name = movie_name.gsub(/\[.+\]/, "")
|
14
|
+
path = "movie/search?q=#{movie_name}&apikey=#{Key}"
|
15
|
+
data = api_get(path)["subjects"]
|
16
|
+
end
|
17
|
+
|
18
|
+
def api_get(path)
|
19
|
+
begin
|
20
|
+
data = RestClient.get URI.encode(UrlPrefix + path)
|
21
|
+
JSON.parse data
|
22
|
+
rescue Timeout::Error => e
|
23
|
+
ExceptionNotifier::Notifier.background_exception_notification(e).deliver
|
24
|
+
Rails.logger.error "获取豆瓣API: #{UrlPrefix}movie/search?q=#{movie_name}超时出错..."
|
25
|
+
rescue JSON::JSONError => e
|
26
|
+
ExceptionNotifier::Notifier.background_exception_notification(e).deliver
|
27
|
+
Rails.logger.error "获取豆瓣API: #{UrlPrefix}movie/suject/#{movie_id}数据JSON.parse出错..."
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
def douban_movie_stills(douban_id)
|
32
|
+
fetch_img("http://movie.douban.com/subject/#{douban_id}/photos?type=S&start=0&sortby=vote&size=a&subtype=o")
|
33
|
+
end
|
34
|
+
|
35
|
+
def douban_movie_posters(douban_id)
|
36
|
+
fetch_img("http://movie.douban.com/subject/#{douban_id}/photos?type=R&start=0&sortby=vote&size=a&subtype=a")
|
37
|
+
end
|
38
|
+
|
39
|
+
def fetch_img(url)
|
40
|
+
begin
|
41
|
+
doc = Nokogiri::HTML(open(url))
|
42
|
+
rescue
|
43
|
+
return []
|
44
|
+
end
|
45
|
+
as = doc.css("ul li div.cover a")
|
46
|
+
photos = []
|
47
|
+
as.each do |a|
|
48
|
+
photos << a.css("img").first.attributes["src"].value.sub("thumb", "photo") rescue next
|
49
|
+
end
|
50
|
+
if doc.css("span.next a").first.present?
|
51
|
+
url = doc.css("span.next a").first.attributes["href"].value
|
52
|
+
photos = photos + fetch_img(url)
|
53
|
+
end
|
54
|
+
photos.uniq
|
55
|
+
end
|
56
|
+
|
57
|
+
end
|
58
|
+
end
|
@@ -0,0 +1,85 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
module MovieSpider
|
3
|
+
class MtimeMovie
|
4
|
+
#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
|
5
|
+
def get_mtime_stills(movie_title, img_size="img_1000")
|
6
|
+
parse_mtime(movie_title, "officialstageimage", img_size)
|
7
|
+
end
|
8
|
+
#获取正式海报
|
9
|
+
def get_general_posters(movie_title, img_size="img_1000")
|
10
|
+
parse_mtime(movie_title, "generalposter", img_size)
|
11
|
+
end
|
12
|
+
#获取预告海报
|
13
|
+
def get_forecast_posters(movie_title, img_size="img_1000")
|
14
|
+
parse_mtime(movie_title, "forecastposter", img_size)
|
15
|
+
end
|
16
|
+
#获取角色海报
|
17
|
+
def get_role_posters(movie_title, img_size="img_1000")
|
18
|
+
parse_mtime(movie_title, "roleposter", img_size)
|
19
|
+
end
|
20
|
+
#全部海报
|
21
|
+
def get_mtime_posters(movie_title, img_size="img_1000")
|
22
|
+
posters = []
|
23
|
+
posters += get_general_posters(movie_title, img_size) + get_forecast_posters(movie_title,img_size) + get_role_posters(movie_title, img_size)
|
24
|
+
posters.delete(nil);posters.delete("")
|
25
|
+
posters
|
26
|
+
end
|
27
|
+
#获取时光网电影评分
|
28
|
+
def get_mtime_rating(movie_title)
|
29
|
+
fetch_result = parse_search(movie_title)
|
30
|
+
if fetch_result.is_a?(Hash)
|
31
|
+
movie_result = fetch_result['value']['movieResult']
|
32
|
+
if movie_result['directMovie'].empty?
|
33
|
+
#无法命中电影标题时
|
34
|
+
return "影片暂无评分" if movie_result['moreMovies'][0]['movieRating'].nil?
|
35
|
+
movie_result['moreMovies'][0]['movieRating']
|
36
|
+
else
|
37
|
+
#直接查找出电影
|
38
|
+
return "影片暂无评分" if movie_result['directMovie']['movieRating'].nil?
|
39
|
+
movie_result['directMovie']['movieRating']
|
40
|
+
end
|
41
|
+
else
|
42
|
+
"解析出错,暂无评分"
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
private
|
47
|
+
#解析时光网search API返回
|
48
|
+
def parse_search(movie_title)
|
49
|
+
begin
|
50
|
+
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
|
51
|
+
rescue
|
52
|
+
return ""
|
53
|
+
end
|
54
|
+
result_str.scan(/{.*}/) {|match| return JSON.parse(match)}
|
55
|
+
end
|
56
|
+
def get_mtime_movie_id_by_title(movie_title)
|
57
|
+
movie_result = {}
|
58
|
+
begin
|
59
|
+
movie_result = parse_search(movie_title)['value']['movieResult']
|
60
|
+
rescue
|
61
|
+
return ""
|
62
|
+
end
|
63
|
+
if movie_result['directMovie'].empty?
|
64
|
+
movie_result['moreMovies'][0]['movieId']
|
65
|
+
else
|
66
|
+
movie_result['directMovie']['movieId']
|
67
|
+
end
|
68
|
+
end
|
69
|
+
#解析时光网JS返回变量
|
70
|
+
def parse_mtime(movie_title, type, img_size)
|
71
|
+
movie_id = get_mtime_movie_id_by_title(movie_title)
|
72
|
+
begin
|
73
|
+
html_doc = Nokogiri::HTML(open("http://movie.mtime.com/#{movie_id}/posters_and_images/posters/hot.html"))
|
74
|
+
parser = ""
|
75
|
+
html_doc.css("body").search("script")[1].text.scan(/{"#{type}".*?}\]}/) {|match| parser = JSON.parse(match) }
|
76
|
+
parser[type].map do |item|
|
77
|
+
item[img_size]
|
78
|
+
end
|
79
|
+
rescue
|
80
|
+
return []
|
81
|
+
end
|
82
|
+
end
|
83
|
+
|
84
|
+
end
|
85
|
+
end
|
data/lib/movie_spider.rb
ADDED
@@ -0,0 +1,56 @@
|
|
1
|
+
require "movie_spider/version"
|
2
|
+
require "movie_spider/douban_fetcher"
|
3
|
+
require "movie_spider/mtime_fetcher"
|
4
|
+
require 'json'
|
5
|
+
require 'open-uri'
|
6
|
+
|
7
|
+
module MovieSpider
|
8
|
+
def self.get_title_from_douban_id(douban_id)
|
9
|
+
DoubanMovie.new.get_subject(douban_id)["title"]
|
10
|
+
end
|
11
|
+
|
12
|
+
def self.fetch_stills(douban_id,source)
|
13
|
+
title = get_title_from_douban_id(douban_id)
|
14
|
+
case source
|
15
|
+
when /douban/
|
16
|
+
stills = DoubanMovie.new.douban_movie_stills(douban_id)
|
17
|
+
when /mtime/
|
18
|
+
stills = MtimeMovie.new.get_mtime_stills(title)
|
19
|
+
when /all/
|
20
|
+
stills = DoubanMovie.new.douban_movie_stills(douban_id) + MtimeMovie.new.get_mtime_stills(title)
|
21
|
+
end
|
22
|
+
stills
|
23
|
+
end
|
24
|
+
|
25
|
+
def self.fetch_posters(douban_id,source)
|
26
|
+
title = get_title_from_douban_id(douban_id)
|
27
|
+
case source
|
28
|
+
when /douban/
|
29
|
+
posters = DoubanMovie.new.douban_movie_posters(douban_id)
|
30
|
+
when /mtime/
|
31
|
+
posters = MtimeMovie.new.get_mtime_posters(title)
|
32
|
+
when /all/
|
33
|
+
posters = DoubanMovie.new.douban_movie_posters(douban_id) + MtimeMovie.new.get_mtime_posters(title)
|
34
|
+
end
|
35
|
+
posters
|
36
|
+
end
|
37
|
+
|
38
|
+
def self.fetch_rating(douban_id, source)
|
39
|
+
title = get_title_from_douban_id(douban_id)
|
40
|
+
if source =~ /douban/
|
41
|
+
DoubanMovie.new.get_subject(douban_id)["rating"]["average"]
|
42
|
+
elsif source =~ /mtime/
|
43
|
+
MtimeMovie.new.get_mtime_rating(title)
|
44
|
+
else
|
45
|
+
"评分网站参数错误[douban|mtime]"
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
def self.get_subject(douban_id)
|
50
|
+
DoubanMovie.new.get_subject(douban_id)
|
51
|
+
end
|
52
|
+
|
53
|
+
def self.douban_search_movie(movie_name)
|
54
|
+
DoubanMovie.new.douban_search_movie(movie_name)
|
55
|
+
end
|
56
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'movie_spider/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "movie_spider"
|
8
|
+
spec.version = MovieSpider::VERSION
|
9
|
+
spec.authors = ["hzlu"]
|
10
|
+
spec.email = ["hzlu2010@163.com"]
|
11
|
+
spec.summary = %q{fetch movies' infomation}
|
12
|
+
spec.description = %q{fetch Mtime and Douban, movie posters, stills, and rating.}
|
13
|
+
spec.homepage = "http://www.dan-che.com"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0") + ["lib/movie_spider/douban_fetcher.rb", "lib/movie_spider/mtime_fetcher.rb"]
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.7"
|
22
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
23
|
+
spec.add_development_dependency "nokogiri", "~> 2.0"
|
24
|
+
end
|
metadata
ADDED
@@ -0,0 +1,96 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: movie_spider
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- hzlu
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-03-04 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.7'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.7'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ~>
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ~>
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: nokogiri
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ~>
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '2.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ~>
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '2.0'
|
55
|
+
description: fetch Mtime and Douban, movie posters, stills, and rating.
|
56
|
+
email:
|
57
|
+
- hzlu2010@163.com
|
58
|
+
executables: []
|
59
|
+
extensions: []
|
60
|
+
extra_rdoc_files: []
|
61
|
+
files:
|
62
|
+
- .gitignore
|
63
|
+
- Gemfile
|
64
|
+
- LICENSE.txt
|
65
|
+
- README.md
|
66
|
+
- Rakefile
|
67
|
+
- lib/movie_spider.rb
|
68
|
+
- lib/movie_spider/douban_fetcher.rb
|
69
|
+
- lib/movie_spider/mtime_fetcher.rb
|
70
|
+
- lib/movie_spider/version.rb
|
71
|
+
- movie_spider.gemspec
|
72
|
+
homepage: http://www.dan-che.com
|
73
|
+
licenses:
|
74
|
+
- MIT
|
75
|
+
metadata: {}
|
76
|
+
post_install_message:
|
77
|
+
rdoc_options: []
|
78
|
+
require_paths:
|
79
|
+
- lib
|
80
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
81
|
+
requirements:
|
82
|
+
- - '>='
|
83
|
+
- !ruby/object:Gem::Version
|
84
|
+
version: '0'
|
85
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - '>='
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
requirements: []
|
91
|
+
rubyforge_project:
|
92
|
+
rubygems_version: 2.4.5
|
93
|
+
signing_key:
|
94
|
+
specification_version: 4
|
95
|
+
summary: fetch movies' infomation
|
96
|
+
test_files: []
|