buoy_data 1.0.0.beta.1 → 1.0.0.beta.2
Sign up to get free protection for your applications and to get access to all the features.
- data/VERSION +1 -1
- data/buoy_data.gemspec +7 -2
- data/lib/buoy_data/buoy_list.rb +11 -6
- data/lib/buoy_data/field_map.rb +3 -0
- data/lib/buoy_data/noaa.rb +5 -0
- data/lib/buoy_data/noaa_buoy_list.rb +5 -6
- data/lib/buoy_data/noaa_field_map.rb +15 -0
- data/lib/buoy_data/noaa_station.rb +111 -14
- data/lib/buoy_data.rb +3 -0
- data/spec/noaa_buoy_list_spec.rb +0 -5
- data/spec/noaa_station_spec.rb +22 -0
- metadata +8 -3
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
1.0.0.beta.
|
1
|
+
1.0.0.beta.2
|
data/buoy_data.gemspec
CHANGED
@@ -5,11 +5,11 @@
|
|
5
5
|
|
6
6
|
Gem::Specification.new do |s|
|
7
7
|
s.name = %q{buoy_data}
|
8
|
-
s.version = "1.0.0.beta.
|
8
|
+
s.version = "1.0.0.beta.2"
|
9
9
|
|
10
10
|
s.required_rubygems_version = Gem::Requirement.new("> 1.3.1") if s.respond_to? :required_rubygems_version=
|
11
11
|
s.authors = ["Adam Weller"]
|
12
|
-
s.date = %q{2011-
|
12
|
+
s.date = %q{2011-05-06}
|
13
13
|
s.description = %q{The goal of this gem is to provide marine buoy data from a variety of sources}
|
14
14
|
s.email = %q{minch@trazzler.com}
|
15
15
|
s.extra_rdoc_files = [
|
@@ -27,14 +27,18 @@ Gem::Specification.new do |s|
|
|
27
27
|
"lib/buoy_data.rb",
|
28
28
|
"lib/buoy_data/buoy_list.rb",
|
29
29
|
"lib/buoy_data/buoy_reading.rb",
|
30
|
+
"lib/buoy_data/field_map.rb",
|
31
|
+
"lib/buoy_data/noaa.rb",
|
30
32
|
"lib/buoy_data/noaa_buoy_forecast.rb",
|
31
33
|
"lib/buoy_data/noaa_buoy_list.rb",
|
32
34
|
"lib/buoy_data/noaa_buoy_observation.rb",
|
33
35
|
"lib/buoy_data/noaa_buoy_reading.rb",
|
36
|
+
"lib/buoy_data/noaa_field_map.rb",
|
34
37
|
"lib/buoy_data/noaa_station.rb",
|
35
38
|
"spec/noaa_buoy_forecast_spec.rb",
|
36
39
|
"spec/noaa_buoy_list_spec.rb",
|
37
40
|
"spec/noaa_buoy_observation_spec.rb",
|
41
|
+
"spec/noaa_station_spec.rb",
|
38
42
|
"spec/spec_helper.rb"
|
39
43
|
]
|
40
44
|
s.homepage = %q{http://github.com/minch/buoy_data}
|
@@ -46,6 +50,7 @@ Gem::Specification.new do |s|
|
|
46
50
|
"spec/noaa_buoy_forecast_spec.rb",
|
47
51
|
"spec/noaa_buoy_list_spec.rb",
|
48
52
|
"spec/noaa_buoy_observation_spec.rb",
|
53
|
+
"spec/noaa_station_spec.rb",
|
49
54
|
"spec/spec_helper.rb"
|
50
55
|
]
|
51
56
|
|
data/lib/buoy_data/buoy_list.rb
CHANGED
@@ -3,7 +3,7 @@ module BuoyData
|
|
3
3
|
require 'nokogiri'
|
4
4
|
|
5
5
|
class BuoyList
|
6
|
-
def get
|
6
|
+
def get(limit = 0)
|
7
7
|
stats = {
|
8
8
|
:stations => [],
|
9
9
|
:station_count => 0,
|
@@ -13,15 +13,20 @@ module BuoyData
|
|
13
13
|
@doc = doc
|
14
14
|
@station_list = stations doc
|
15
15
|
|
16
|
+
# Only relevant for testing
|
17
|
+
@station_list = @station_list[0..limit] if limit > 0
|
18
|
+
|
16
19
|
@station_list.each do |station_url|
|
17
|
-
|
20
|
+
#p station_url
|
21
|
+
|
22
|
+
#begin
|
18
23
|
h = scrape_station(station_url)
|
19
24
|
stats[:stations].push h
|
20
25
|
stats[:station_count] += 1
|
21
|
-
rescue => e
|
22
|
-
stats[:error_count] += 1
|
23
|
-
stats[:errors].push({ :url =>
|
24
|
-
end
|
26
|
+
#rescue => e
|
27
|
+
#stats[:error_count] += 1
|
28
|
+
#stats[:errors].push({ :url => station_url, :error => e.backtrace })
|
29
|
+
#end
|
25
30
|
end
|
26
31
|
|
27
32
|
stats
|
@@ -5,7 +5,11 @@ module BuoyData
|
|
5
5
|
end
|
6
6
|
|
7
7
|
def base_url
|
8
|
-
|
8
|
+
Noaa::BASE_URL
|
9
|
+
end
|
10
|
+
|
11
|
+
def scrape_station(url)
|
12
|
+
NoaaStation.new.scrape(url)
|
9
13
|
end
|
10
14
|
|
11
15
|
private
|
@@ -15,10 +19,5 @@ module BuoyData
|
|
15
19
|
|
16
20
|
doc.xpath(xpath).map{|element| element['href']}
|
17
21
|
end
|
18
|
-
|
19
|
-
def scrape_station(url)
|
20
|
-
url = [ base_url, url ].join('/')
|
21
|
-
NoaaStation.new.scrape(url)
|
22
|
-
end
|
23
22
|
end
|
24
23
|
end
|
@@ -0,0 +1,15 @@
|
|
1
|
+
class NoaaFieldMap < FieldMap
|
2
|
+
def self.field_map
|
3
|
+
f = {
|
4
|
+
:wvht => ['Wave Height', 'ft'],
|
5
|
+
:dpd => ['Dominant Wave Period', 's'],
|
6
|
+
:apd => ['Average Period', 's'],
|
7
|
+
:gst => ['Wind Gust', 'kts'],
|
8
|
+
:wspd => ['Wind Speed', 'kts'],
|
9
|
+
:wdir => ['Wind Direction', 'deg'],
|
10
|
+
#:wtmp => ['Water Temperature',"#{String.new('U+00B0')} F"],
|
11
|
+
:wtmp => ['Water Temperature',"F"],
|
12
|
+
:atmp => ['Air Temperature', "F"]
|
13
|
+
}
|
14
|
+
end
|
15
|
+
end
|
@@ -2,8 +2,23 @@ module BuoyData
|
|
2
2
|
require 'open-uri'
|
3
3
|
require 'nokogiri'
|
4
4
|
|
5
|
+
# This class scrapes readings from noaa stations.
|
6
|
+
# A station in this parlance is an noaa resource that does
|
7
|
+
# not have wave data (in other words is not necessarily
|
8
|
+
# a floating buoy).
|
9
|
+
#
|
10
|
+
# There is no super class for this model as we don't yet
|
11
|
+
# know if this set up will apply for other data sources.
|
12
|
+
#
|
13
|
+
# NOTE: This class can currently be used to scrape the latest
|
14
|
+
# readings for buoys as well. The reason it exists however
|
15
|
+
# is that we can't fetch data for the stations from the .bull
|
16
|
+
# files (they don't exists for stations only buoys).
|
17
|
+
|
5
18
|
class NoaaStation
|
6
19
|
def scrape(url)
|
20
|
+
url = normalize_url url
|
21
|
+
|
7
22
|
h = {}
|
8
23
|
xpath = "//h1"
|
9
24
|
|
@@ -27,29 +42,83 @@ module BuoyData
|
|
27
42
|
element = elements.find{|e| /\d{2,3}\.\d{2,3}/.match(e)}
|
28
43
|
latlng = lat_lng_from element
|
29
44
|
|
30
|
-
unless latlng.
|
45
|
+
unless latlng.blank?
|
31
46
|
h[:lat] = normal_lat latlng.first
|
32
47
|
h[:lng] = normal_lng latlng.last
|
33
48
|
end
|
34
49
|
|
35
50
|
# Latest reading
|
36
|
-
|
51
|
+
current_reading = {}
|
52
|
+
|
53
|
+
current_reading = latest_reading doc
|
54
|
+
|
55
|
+
# If we couldn't get a water temp from this station then it's not of use
|
56
|
+
return {} unless valid_reading? current_reading
|
57
|
+
h.merge! current_reading
|
58
|
+
|
59
|
+
h
|
60
|
+
end
|
61
|
+
|
62
|
+
# Do the best we can but get something
|
63
|
+
def latest_reading(doc)
|
64
|
+
# Check the current reading
|
65
|
+
reading = current_reading doc
|
66
|
+
|
67
|
+
# If we don't have a wave height (:wvht) then let's check the previous reading
|
68
|
+
unless reading[:wvht]
|
69
|
+
p_reading = previous_reading doc
|
70
|
+
reading = p_reading if p_reading[:wvht]
|
71
|
+
end
|
72
|
+
|
73
|
+
reading
|
74
|
+
end
|
75
|
+
|
76
|
+
# Reding from the 'Conditions at..as of..' table
|
77
|
+
def current_reading(doc)
|
78
|
+
reading = {}
|
79
|
+
|
80
|
+
xpath = "//table/caption[@class='titleDataHeader']["
|
81
|
+
xpath += "contains(text(),'Conditions')"
|
82
|
+
xpath += " and "
|
83
|
+
xpath += "not(contains(text(),'Solar Radiation'))"
|
84
|
+
xpath += "]"
|
85
|
+
|
86
|
+
# Get the reading timestamp
|
87
|
+
source_updated_at = reading_timestamp(doc, xpath)
|
88
|
+
reading[:source_updated_at] = source_updated_at
|
89
|
+
|
90
|
+
# Get the reading data
|
37
91
|
xpath += "/../tr"
|
38
92
|
elements = doc.xpath xpath
|
39
93
|
|
40
|
-
current_reading = {}
|
41
94
|
unless elements.empty?
|
42
95
|
elements.each do |element|
|
43
|
-
|
44
|
-
|
96
|
+
r = scrape_condition_from_element(element)
|
97
|
+
reading.merge! r unless r.blank?
|
45
98
|
end
|
46
99
|
end
|
47
100
|
|
48
|
-
|
49
|
-
|
50
|
-
h.merge! current_reading
|
101
|
+
reading
|
102
|
+
end
|
51
103
|
|
52
|
-
|
104
|
+
# Most recent observation from the 'Previous observations' table
|
105
|
+
# This is unfinished, will need to capture the markup when the
|
106
|
+
# current reading is not avaliable and stub it w/fakeweb...
|
107
|
+
def previous_reading(doc)
|
108
|
+
reading = {}
|
109
|
+
text = 'Previous observations'
|
110
|
+
xpath = "//table/caption[@class='dataHeader'][text()[contains(.,'#{text}')]]"
|
111
|
+
|
112
|
+
xpath += "/../tr/td"
|
113
|
+
elements = doc.xpath xpath
|
114
|
+
|
115
|
+
#unless elements.empty?
|
116
|
+
#elements.each do |element|
|
117
|
+
#p element.text
|
118
|
+
#end
|
119
|
+
#end
|
120
|
+
|
121
|
+
reading
|
53
122
|
end
|
54
123
|
|
55
124
|
private
|
@@ -60,10 +129,7 @@ module BuoyData
|
|
60
129
|
|
61
130
|
def scrape_condition_from_element(element)
|
62
131
|
reading = {}
|
63
|
-
|
64
|
-
#regexp = /\(([A-Z]+)\):\n\t ?(.*)\n$/
|
65
|
-
# (no units)
|
66
|
-
regexp = /\(([A-Z]+)\):\n\t ?([0-9.-]+).*\n$/
|
132
|
+
regexp = /\(([A-Z]+)\):\n\n?\t? ?(.*)\n$/m
|
67
133
|
text = element.text
|
68
134
|
|
69
135
|
if regexp.match(text)
|
@@ -72,6 +138,7 @@ module BuoyData
|
|
72
138
|
key = key.downcase.to_sym
|
73
139
|
value = $2
|
74
140
|
return reading unless value
|
141
|
+
value = $1 if value =~ /([0-9.]+)/
|
75
142
|
value = value.lstrip.rstrip.to_f
|
76
143
|
reading = { key => value }
|
77
144
|
end
|
@@ -80,7 +147,8 @@ module BuoyData
|
|
80
147
|
end
|
81
148
|
|
82
149
|
def lat_lng_from(text)
|
83
|
-
text = text.sub(/ \(.*$/, '')
|
150
|
+
text = text.sub(/ \(.*$/, '') rescue nil
|
151
|
+
return unless text
|
84
152
|
matches = /([0-9\.]+ ?[NESW]) ([0-9\.]+ ?[NESW])/.match(text)
|
85
153
|
|
86
154
|
matches && matches.size == 3 ? [ $1, $2 ] : []
|
@@ -101,5 +169,34 @@ module BuoyData
|
|
101
169
|
|
102
170
|
lng
|
103
171
|
end
|
172
|
+
|
173
|
+
def normalize_url(url)
|
174
|
+
base_url = Noaa::BASE_URL
|
175
|
+
/^#{base_url}/.match(url) ? url : [Noaa::BASE_URL, url].join('/')
|
176
|
+
end
|
177
|
+
|
178
|
+
def logger
|
179
|
+
RAILS_DEFAULT_LOGGER if defined? RAILS_DEFAULT_LOGGER
|
180
|
+
end
|
181
|
+
|
182
|
+
def reading_timestamp(doc, xpath)
|
183
|
+
elements = doc.xpath(xpath).children rescue []
|
184
|
+
unless elements.empty?
|
185
|
+
begin
|
186
|
+
elements = elements.to_a
|
187
|
+
elements.reject!{|e|e.name == 'br'}
|
188
|
+
s = elements.last.text.sub(/ ?:$/, '')
|
189
|
+
time, date = s.split(/ on /)
|
190
|
+
month, day, year = date.split(/\//)
|
191
|
+
date = [ day, month, year ].join('-')
|
192
|
+
hour = time[0..1]
|
193
|
+
minutes = time[2..3]
|
194
|
+
time = [ hour, minutes ].join(':')
|
195
|
+
s = [ date, time ].join('T')
|
196
|
+
t = Time.parse s if s
|
197
|
+
rescue
|
198
|
+
end
|
199
|
+
end
|
200
|
+
end
|
104
201
|
end
|
105
202
|
end
|
data/lib/buoy_data.rb
CHANGED
@@ -1,8 +1,11 @@
|
|
1
1
|
require 'httparty'
|
2
2
|
require 'buoy_data/buoy_list'
|
3
3
|
require 'buoy_data/buoy_reading'
|
4
|
+
require 'buoy_data/noaa'
|
4
5
|
require 'buoy_data/noaa_buoy_reading'
|
5
6
|
require 'buoy_data/noaa_station'
|
6
7
|
require 'buoy_data/noaa_buoy_list'
|
7
8
|
require 'buoy_data/noaa_buoy_observation'
|
8
9
|
require 'buoy_data/noaa_buoy_forecast'
|
10
|
+
require 'buoy_data/field_map'
|
11
|
+
require 'buoy_data/noaa_field_map'
|
data/spec/noaa_buoy_list_spec.rb
CHANGED
@@ -13,11 +13,6 @@ describe BuoyData::NoaaBuoyList do
|
|
13
13
|
results[:errors].should be_empty
|
14
14
|
stations = results[:stations]
|
15
15
|
stations.compact.should_not be_empty
|
16
|
-
station = stations.first
|
17
|
-
|
18
|
-
# Verify we have water temp value
|
19
|
-
wtmp = station[:wtmp]
|
20
|
-
wtmp.should be_kind_of Float
|
21
16
|
end
|
22
17
|
end
|
23
18
|
|
@@ -0,0 +1,22 @@
|
|
1
|
+
require File.join(File.dirname(__FILE__), 'spec_helper')
|
2
|
+
|
3
|
+
describe BuoyData::NoaaStation do
|
4
|
+
let (:station) { BuoyData::NoaaStation.new }
|
5
|
+
|
6
|
+
it "should scrape station" do
|
7
|
+
data = station.scrape station_url
|
8
|
+
data.should_not be_empty
|
9
|
+
data.should be_a(Hash)
|
10
|
+
|
11
|
+
data[:wtmp].should be_a(Float)
|
12
|
+
data[:source_updated_at].should be_a(Time)
|
13
|
+
end
|
14
|
+
|
15
|
+
def station_url
|
16
|
+
"station_page.php?station=sauf1"
|
17
|
+
end
|
18
|
+
|
19
|
+
def buoy_url
|
20
|
+
"station_page.php?station=41012"
|
21
|
+
end
|
22
|
+
end
|
metadata
CHANGED
@@ -7,8 +7,8 @@ version: !ruby/object:Gem::Version
|
|
7
7
|
- 0
|
8
8
|
- 0
|
9
9
|
- beta
|
10
|
-
-
|
11
|
-
version: 1.0.0.beta.
|
10
|
+
- 2
|
11
|
+
version: 1.0.0.beta.2
|
12
12
|
platform: ruby
|
13
13
|
authors:
|
14
14
|
- Adam Weller
|
@@ -16,7 +16,7 @@ autorequire:
|
|
16
16
|
bindir: bin
|
17
17
|
cert_chain: []
|
18
18
|
|
19
|
-
date: 2011-
|
19
|
+
date: 2011-05-06 00:00:00 -04:00
|
20
20
|
default_executable:
|
21
21
|
dependencies:
|
22
22
|
- !ruby/object:Gem::Dependency
|
@@ -91,14 +91,18 @@ files:
|
|
91
91
|
- lib/buoy_data.rb
|
92
92
|
- lib/buoy_data/buoy_list.rb
|
93
93
|
- lib/buoy_data/buoy_reading.rb
|
94
|
+
- lib/buoy_data/field_map.rb
|
95
|
+
- lib/buoy_data/noaa.rb
|
94
96
|
- lib/buoy_data/noaa_buoy_forecast.rb
|
95
97
|
- lib/buoy_data/noaa_buoy_list.rb
|
96
98
|
- lib/buoy_data/noaa_buoy_observation.rb
|
97
99
|
- lib/buoy_data/noaa_buoy_reading.rb
|
100
|
+
- lib/buoy_data/noaa_field_map.rb
|
98
101
|
- lib/buoy_data/noaa_station.rb
|
99
102
|
- spec/noaa_buoy_forecast_spec.rb
|
100
103
|
- spec/noaa_buoy_list_spec.rb
|
101
104
|
- spec/noaa_buoy_observation_spec.rb
|
105
|
+
- spec/noaa_station_spec.rb
|
102
106
|
- spec/spec_helper.rb
|
103
107
|
has_rdoc: true
|
104
108
|
homepage: http://github.com/minch/buoy_data
|
@@ -138,4 +142,5 @@ test_files:
|
|
138
142
|
- spec/noaa_buoy_forecast_spec.rb
|
139
143
|
- spec/noaa_buoy_list_spec.rb
|
140
144
|
- spec/noaa_buoy_observation_spec.rb
|
145
|
+
- spec/noaa_station_spec.rb
|
141
146
|
- spec/spec_helper.rb
|