crawler-movie-imdb 0.1.0 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/crawler-movie-imdb.gemspec +1 -0
- data/lib/crawler/movie/providers/imdb.rb +44 -1
- data/lib/crawler/movie/providers/imdb/version.rb +1 -1
- metadata +15 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: a261dfb1bad0cc3e1a762facb6167e2a67a907a592958300dbc4aaa81dfe7e84
|
4
|
+
data.tar.gz: b48fa5312d3c8a0cb44117fb91673b5cb35427f9bb21b13f4e3c4dca59091694
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 268656d0ec96de093ce2deace8b106599ee5a0db4e0353d94f47ac256c1bfecc5acab27213a6055a3e3102c32946eba0bb4e7e0f3808c3cd254faf4cbddf6768
|
7
|
+
data.tar.gz: 772e2dff81f70c34df0f6cb6fa9068fefe0f3b9829a7c865927744816d4a42417190ca04aa62964ec305ccf9c36b2de4cb5b59ebf2c5320bab862b0fe900a98b
|
data/crawler-movie-imdb.gemspec
CHANGED
@@ -2,11 +2,50 @@ require 'crawler/movie'
|
|
2
2
|
require 'faraday'
|
3
3
|
require 'nokogiri'
|
4
4
|
require 'date'
|
5
|
+
require 'active_support/core_ext/object/blank'
|
6
|
+
require 'uri'
|
7
|
+
require 'time'
|
5
8
|
|
6
9
|
module Crawler
|
7
10
|
module Movie
|
8
11
|
module Providers
|
9
12
|
module Imdb
|
13
|
+
def self.find(id)
|
14
|
+
response = Faraday.get("https://www.imdb.com/title/#{id}/")
|
15
|
+
|
16
|
+
return if !response.success? || !response.body
|
17
|
+
|
18
|
+
html = Nokogiri::HTML(response.body)
|
19
|
+
widget = html.css('#title-overview-widget')
|
20
|
+
title = widget.css('.title_wrapper h1 > text()').text.tr("\u00A0", '').strip
|
21
|
+
original_title = widget.css('.title_wrapper .originalTitle > text()').text.presence
|
22
|
+
genres = (html.css('#titleStoryLine .see-more:contains("Genres:") a') || []).map { |genre| genre.text.strip }
|
23
|
+
poster = widget.css('.poster img')
|
24
|
+
poster_url = poster.present? ? "#{poster.attr('src').value.split('@').first}@._V1_.jpg" : nil
|
25
|
+
overview = widget.css('.summary_text').text.sub(/See full (synopsis|summary) »/, '').strip
|
26
|
+
overview = nil if overview == 'Add a Plot »'
|
27
|
+
release_date_matches = html.css('#titleDetails .txt-block:contains("Release Date:") > text()').text.match(/(?<release_date>\d{1,2} \w+ \d{4})/)
|
28
|
+
release_date = release_date_matches && Date.parse(release_date_matches[:release_date])
|
29
|
+
original_languages = (html.css('#titleDetails .txt-block:contains("Language:") a') || []).map do |lang|
|
30
|
+
uri = URI(lang.attr('href'))
|
31
|
+
params = URI.decode_www_form(uri.query).to_h
|
32
|
+
params['primary_language']
|
33
|
+
end
|
34
|
+
|
35
|
+
{
|
36
|
+
id: id,
|
37
|
+
source: 'internet-movie-database',
|
38
|
+
title: title,
|
39
|
+
poster_url: poster_url,
|
40
|
+
backdrop_url: nil,
|
41
|
+
original_languages: original_languages,
|
42
|
+
original_titles: original_title,
|
43
|
+
genres: genres,
|
44
|
+
overview: overview,
|
45
|
+
release_date: release_date
|
46
|
+
}
|
47
|
+
end
|
48
|
+
|
10
49
|
def self.search(query)
|
11
50
|
movies = []
|
12
51
|
current_start = 1
|
@@ -29,11 +68,15 @@ module Crawler
|
|
29
68
|
overview = item_content.css('.text-muted')[2].text.sub(/See full (synopsis|summary) »/, '').strip
|
30
69
|
overview = nil if overview == 'Add a Plot'
|
31
70
|
year_matches = item_content.css('.lister-item-year').text.match(/\((?<year>\d+)\)/)
|
71
|
+
release_date = year_matches && Date.parse("#{year_matches[:year]}-1-1")
|
32
72
|
item_image = movie.css('.lister-item-image img')
|
33
73
|
id = item_image.attr('data-tconst').value
|
34
74
|
poster_url = item_image.attr('loadlate').value.split('@').first
|
35
75
|
poster_url = nil if poster_url.match?(%r{/nopicture/})
|
36
76
|
poster_url += '@._V1_.jpg' if poster_url
|
77
|
+
details = find(id)
|
78
|
+
|
79
|
+
next details if details
|
37
80
|
|
38
81
|
{
|
39
82
|
id: id,
|
@@ -45,7 +88,7 @@ module Crawler
|
|
45
88
|
original_title: nil,
|
46
89
|
genres: genres,
|
47
90
|
overview: overview,
|
48
|
-
release_date:
|
91
|
+
release_date: release_date
|
49
92
|
}
|
50
93
|
end
|
51
94
|
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: crawler-movie-imdb
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Jonathan PHILIPPE
|
@@ -66,6 +66,20 @@ dependencies:
|
|
66
66
|
- - ">="
|
67
67
|
- !ruby/object:Gem::Version
|
68
68
|
version: '1.4'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: activesupport
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '3.0'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '3.0'
|
69
83
|
description: ''
|
70
84
|
email:
|
71
85
|
- jonathan@cinema.paris
|