yayimdbs 0.2.1 → 0.2.2
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/yay_imdbs.rb +9 -11
- metadata +18 -5
data/lib/yay_imdbs.rb
CHANGED
|
@@ -31,7 +31,7 @@ class YayImdbs
|
|
|
31
31
|
class << self
|
|
32
32
|
|
|
33
33
|
def search_for_imdb_id(name, year=nil, type=nil)
|
|
34
|
-
search_results =
|
|
34
|
+
search_results = search_imdb(name)
|
|
35
35
|
|
|
36
36
|
search_results.each do |result|
|
|
37
37
|
# Ensure result is the correct video type
|
|
@@ -46,7 +46,7 @@ class YayImdbs
|
|
|
46
46
|
def search_imdb(search_term)
|
|
47
47
|
search_results = []
|
|
48
48
|
|
|
49
|
-
doc =
|
|
49
|
+
doc = get_search_page(search_term)
|
|
50
50
|
|
|
51
51
|
# If the search is an exact match imdb will redirect to the movie page not search results page
|
|
52
52
|
# we uses the title meta element to determine if we got an exact match
|
|
@@ -79,14 +79,14 @@ class YayImdbs
|
|
|
79
79
|
def scrap_movie_info(imdb_id)
|
|
80
80
|
info_hash = {:imdb_id => imdb_id}.with_indifferent_access
|
|
81
81
|
|
|
82
|
-
doc =
|
|
82
|
+
doc = get_movie_page(imdb_id)
|
|
83
83
|
title, year = get_title_and_year_from_meta(doc)
|
|
84
84
|
info_hash[:title], info_hash[:year] = title, year
|
|
85
85
|
if info_hash['title'].nil?
|
|
86
86
|
#If we cant get title and year something is wrong
|
|
87
87
|
raise "Unable to find title or year for imdb id #{imdb_id}"
|
|
88
88
|
end
|
|
89
|
-
info_hash[:video_type] =
|
|
89
|
+
info_hash[:video_type] = video_type_from_meta(doc)
|
|
90
90
|
|
|
91
91
|
info_hash[:plot] = doc.xpath("//td[@id='overview-top']/p[2]").inner_text.strip
|
|
92
92
|
info_hash[:rating] = doc.at_css('.rating-rating').content.gsub(/\/.*/, '').to_f rescue nil
|
|
@@ -99,7 +99,7 @@ class YayImdbs
|
|
|
99
99
|
info_hash[PROPERTY_ALIAS[key]] = info_hash[key] if PROPERTY_ALIAS[key]
|
|
100
100
|
end
|
|
101
101
|
|
|
102
|
-
|
|
102
|
+
unless found_info_divs
|
|
103
103
|
#If we don't find any info divs assume parsing failed
|
|
104
104
|
raise "No info divs found for imdb id #{imdb_id}"
|
|
105
105
|
end
|
|
@@ -107,12 +107,10 @@ class YayImdbs
|
|
|
107
107
|
# Hack: tv shows can have a year property, which is a list, fixing ...
|
|
108
108
|
info_hash[:year] = year
|
|
109
109
|
|
|
110
|
-
|
|
110
|
+
scrap_images(doc, info_hash)
|
|
111
111
|
|
|
112
112
|
#scrap episodes if tv series
|
|
113
|
-
if info_hash.has_key?('season')
|
|
114
|
-
self.scrap_episodes(info_hash)
|
|
115
|
-
end
|
|
113
|
+
scrap_episodes(info_hash) if info_hash.has_key?('season')
|
|
116
114
|
|
|
117
115
|
return info_hash
|
|
118
116
|
end
|
|
@@ -167,7 +165,7 @@ class YayImdbs
|
|
|
167
165
|
|
|
168
166
|
def scrap_episodes(info_hash)
|
|
169
167
|
episodes = []
|
|
170
|
-
doc =
|
|
168
|
+
doc = get_episodes_page(info_hash[:imdb_id])
|
|
171
169
|
|
|
172
170
|
doc.css(".filter-all").each do |e_div|
|
|
173
171
|
next unless e_div.at_css('h3').inner_text =~ /Season (\d+), Episode (\d+):/
|
|
@@ -204,7 +202,7 @@ class YayImdbs
|
|
|
204
202
|
title_text = doc.at_css("meta[name='title']").try(:[], 'content')
|
|
205
203
|
# Matches 'Movie Name (2010)' or 'Movie Name (2010/I)' or 'Lost (TV Series 2004–2010)'
|
|
206
204
|
if title_text && title_text =~ /(.*) \([^\)0-9]*(\d{4})((\/\w*)|(.\d{4}))?\)/
|
|
207
|
-
movie_title =
|
|
205
|
+
movie_title = clean_title($1)
|
|
208
206
|
movie_year = $2.to_i
|
|
209
207
|
end
|
|
210
208
|
return movie_title, movie_year
|
metadata
CHANGED
|
@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
|
|
|
5
5
|
segments:
|
|
6
6
|
- 0
|
|
7
7
|
- 2
|
|
8
|
-
-
|
|
9
|
-
version: 0.2.
|
|
8
|
+
- 2
|
|
9
|
+
version: 0.2.2
|
|
10
10
|
platform: ruby
|
|
11
11
|
authors:
|
|
12
12
|
- Sam Cavenagh
|
|
@@ -14,7 +14,7 @@ autorequire:
|
|
|
14
14
|
bindir: bin
|
|
15
15
|
cert_chain: []
|
|
16
16
|
|
|
17
|
-
date: 2011-03-
|
|
17
|
+
date: 2011-03-07 00:00:00 +11:00
|
|
18
18
|
default_executable:
|
|
19
19
|
dependencies:
|
|
20
20
|
- !ruby/object:Gem::Dependency
|
|
@@ -46,9 +46,22 @@ dependencies:
|
|
|
46
46
|
type: :runtime
|
|
47
47
|
version_requirements: *id002
|
|
48
48
|
- !ruby/object:Gem::Dependency
|
|
49
|
-
name:
|
|
49
|
+
name: i18n
|
|
50
50
|
prerelease: false
|
|
51
51
|
requirement: &id003 !ruby/object:Gem::Requirement
|
|
52
|
+
none: false
|
|
53
|
+
requirements:
|
|
54
|
+
- - ">="
|
|
55
|
+
- !ruby/object:Gem::Version
|
|
56
|
+
segments:
|
|
57
|
+
- 0
|
|
58
|
+
version: "0"
|
|
59
|
+
type: :runtime
|
|
60
|
+
version_requirements: *id003
|
|
61
|
+
- !ruby/object:Gem::Dependency
|
|
62
|
+
name: rspec
|
|
63
|
+
prerelease: false
|
|
64
|
+
requirement: &id004 !ruby/object:Gem::Requirement
|
|
52
65
|
none: false
|
|
53
66
|
requirements:
|
|
54
67
|
- - ">="
|
|
@@ -59,7 +72,7 @@ dependencies:
|
|
|
59
72
|
- 0
|
|
60
73
|
version: 2.0.0
|
|
61
74
|
type: :development
|
|
62
|
-
version_requirements: *
|
|
75
|
+
version_requirements: *id004
|
|
63
76
|
description: A simple imdb scraper built on Nokogiri for ruby 1.9+
|
|
64
77
|
email: cavenaghweb@hotmail.com
|
|
65
78
|
executables: []
|