crawler-movie-imdb 0.3.0 → 0.3.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.gitignore +2 -0
- data/crawler-movie-imdb.gemspec +2 -2
- data/lib/crawler/movie/providers/imdb.rb +10 -6
- data/lib/crawler/movie/providers/imdb/version.rb +1 -1
- metadata +10 -10
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 204e2f7ba0b7b2cbb810ed68e6928f16b372571be966e4ecd9a1a86fa94640eb
|
4
|
+
data.tar.gz: 863763956f0f3416722195495b4c1f0d7a44ac65a84598305f2e497a7e4dc915
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 8c6787a844d7fcf682bfca52f4b486a894a84b595a42a8783c8e86c0d28eeee82ed4f61349328af6726fb6a3946babd6e8971c5e3ba495714ae93a38ec089685
|
7
|
+
data.tar.gz: d978990c6aeb5df93e5a733e1f4716b3b36129c8ff28a1cc9d7fcaebfef9449dbd3f99301578386b2e4010fda16cd7af4f93b849683e20f9dcdcdb19fe36727e
|
data/.gitignore
CHANGED
data/crawler-movie-imdb.gemspec
CHANGED
@@ -26,8 +26,8 @@ Gem::Specification.new do |spec|
|
|
26
26
|
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
27
27
|
spec.require_paths = ['lib']
|
28
28
|
|
29
|
-
spec.add_development_dependency 'bundler', '~> 1
|
30
|
-
spec.add_development_dependency 'rake', '~>
|
29
|
+
spec.add_development_dependency 'bundler', '~> 2.1'
|
30
|
+
spec.add_development_dependency 'rake', '~> 13.0'
|
31
31
|
spec.add_runtime_dependency 'faraday', '>= 0.15'
|
32
32
|
spec.add_runtime_dependency 'nokogiri', '>= 1.4'
|
33
33
|
spec.add_runtime_dependency 'activesupport', '>= 3.0'
|
@@ -13,7 +13,7 @@ module Crawler
|
|
13
13
|
def self.find(id)
|
14
14
|
response = Faraday.get("https://www.imdb.com/title/#{id}/")
|
15
15
|
|
16
|
-
return if !response.success? ||
|
16
|
+
return if !response.success? || response.body.blank?
|
17
17
|
|
18
18
|
html = Nokogiri::HTML(response.body)
|
19
19
|
widget = html.css('#title-overview-widget')
|
@@ -21,15 +21,19 @@ module Crawler
|
|
21
21
|
original_title = widget.css('.title_wrapper .originalTitle > text()').text.presence
|
22
22
|
genres = (html.css('#titleStoryLine .see-more:contains("Genres:") a') || []).map { |genre| genre.text.strip }
|
23
23
|
poster = widget.css('.poster img')
|
24
|
-
poster_url = poster.
|
24
|
+
poster_url = poster.presence && "#{poster.attr('src').value.split('@').first}@._V1_.jpg"
|
25
25
|
overview = widget.css('.summary_text').text.sub(/See full (synopsis|summary) »/, '').strip
|
26
26
|
overview = nil if overview == 'Add a Plot »'
|
27
27
|
release_date_matches = html.css('#titleDetails .txt-block:contains("Release Date:") > text()').text.match(/(?<release_date>\d{1,2} \w+ \d{4})/)
|
28
28
|
release_date = release_date_matches && Date.parse(release_date_matches[:release_date])
|
29
|
-
original_languages = (html.css('#titleDetails .txt-block:contains("Language:") a') || []).
|
30
|
-
|
31
|
-
|
32
|
-
|
29
|
+
original_languages = (html.css('#titleDetails .txt-block:contains("Language:") a') || []).each_with_object([]) do |lang, acc|
|
30
|
+
begin
|
31
|
+
uri = URI(lang.attr('href'))
|
32
|
+
params = URI.decode_www_form(uri.query).to_h
|
33
|
+
accc << params['primary_language']
|
34
|
+
rescue StandardError
|
35
|
+
# Ignored
|
36
|
+
end
|
33
37
|
end
|
34
38
|
|
35
39
|
{
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: crawler-movie-imdb
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.3.
|
4
|
+
version: 0.3.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Jonathan PHILIPPE
|
8
|
-
autorequire:
|
8
|
+
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2020-11-11 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -16,28 +16,28 @@ dependencies:
|
|
16
16
|
requirements:
|
17
17
|
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: '1
|
19
|
+
version: '2.1'
|
20
20
|
type: :development
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
24
|
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version: '1
|
26
|
+
version: '2.1'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: rake
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
31
|
- - "~>"
|
32
32
|
- !ruby/object:Gem::Version
|
33
|
-
version: '
|
33
|
+
version: '13.0'
|
34
34
|
type: :development
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
38
|
- - "~>"
|
39
39
|
- !ruby/object:Gem::Version
|
40
|
-
version: '
|
40
|
+
version: '13.0'
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
42
|
name: faraday
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
@@ -119,7 +119,7 @@ metadata:
|
|
119
119
|
homepage_uri: https://crawler.cinema.paris
|
120
120
|
source_code_uri: https://github.com/cinema-paris/crawler-movie-imdb
|
121
121
|
changelog_uri: https://github.com/cinema-paris/crawler-movie-imdb/CHANGELOG.md
|
122
|
-
post_install_message:
|
122
|
+
post_install_message:
|
123
123
|
rdoc_options: []
|
124
124
|
require_paths:
|
125
125
|
- lib
|
@@ -134,8 +134,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
134
134
|
- !ruby/object:Gem::Version
|
135
135
|
version: '0'
|
136
136
|
requirements: []
|
137
|
-
rubygems_version: 3.
|
138
|
-
signing_key:
|
137
|
+
rubygems_version: 3.1.2
|
138
|
+
signing_key:
|
139
139
|
specification_version: 4
|
140
140
|
summary: ''
|
141
141
|
test_files: []
|