lakes 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/CODE_OF_CONDUCT.md +49 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +46 -0
- data/Rakefile +10 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lakes.gemspec +25 -0
- data/lakes.json +71634 -0
- data/lib/lakes/texas.rb +290 -0
- data/lib/lakes.rb +4 -0
- data/lib/try.rb +78 -0
- metadata +113 -0
data/lib/lakes/texas.rb
ADDED
@@ -0,0 +1,290 @@
|
|
1
|
+
require 'net/http'
|
2
|
+
require 'nokogiri'
|
3
|
+
require 'date'
|
4
|
+
require 'try'
|
5
|
+
|
6
|
+
module Lakes
|
7
|
+
class Texas
|
8
|
+
attr_reader :lake_data
|
9
|
+
|
10
|
+
def initialize
|
11
|
+
@lake_data = {}
|
12
|
+
end
|
13
|
+
|
14
|
+
def list
|
15
|
+
return @lake_data.keys unless @lake_data.empty?
|
16
|
+
|
17
|
+
base_url = 'http://tpwd.texas.gov/fishboat/fish/recreational/lakes/'
|
18
|
+
uri = URI("#{base_url}lakelist.phtml")
|
19
|
+
content = Net::HTTP.get(uri)
|
20
|
+
html_doc = Nokogiri::HTML(content)
|
21
|
+
|
22
|
+
# remove elements not needed to make parsing easier
|
23
|
+
html_doc.search('div.announce, div.alert, div#bottomwrapper').each do |src|
|
24
|
+
src.remove
|
25
|
+
end
|
26
|
+
|
27
|
+
html_doc.search('div#maincontent ul li a').each do |lake_html|
|
28
|
+
lake_name = cleanup_data(lake_html.text)
|
29
|
+
@lake_data[lake_name] = { details_uri: "#{base_url}#{lake_html[:href]}" }
|
30
|
+
end
|
31
|
+
@lake_data.keys
|
32
|
+
end
|
33
|
+
|
34
|
+
def get_details(lake_name)
|
35
|
+
list
|
36
|
+
data = lake_data[lake_name]
|
37
|
+
raise 'Lake not found' if data.nil?
|
38
|
+
|
39
|
+
parse_lake_details(data)
|
40
|
+
end
|
41
|
+
|
42
|
+
protected
|
43
|
+
|
44
|
+
def parse_lake_details(lake_data)
|
45
|
+
uri = URI(lake_data[:details_uri] + '/')
|
46
|
+
content = Net::HTTP.get(uri).encode('UTF-8', 'Windows-1252')
|
47
|
+
|
48
|
+
html_doc = Nokogiri::HTML(content)
|
49
|
+
main_div = html_doc.at('div#maincontent')
|
50
|
+
|
51
|
+
parse_lake_characteristics(main_div, lake_data)
|
52
|
+
parse_water_conditions(main_div, lake_data)
|
53
|
+
parse_reservoir_controlling_authority(main_div, lake_data)
|
54
|
+
parse_aquatic_vegetation(main_div, lake_data)
|
55
|
+
parse_predominant_fish_species(main_div, lake_data)
|
56
|
+
parse_lake_records(main_div, lake_data)
|
57
|
+
parse_current_fishing_report(main_div, lake_data)
|
58
|
+
parse_stocking_history(main_div, lake_data)
|
59
|
+
parse_lake_surveys(main_div, lake_data)
|
60
|
+
parse_lake_maps(main_div, lake_data)
|
61
|
+
parse_fishing_regulations(main_div, lake_data)
|
62
|
+
parse_angling_opportunities(main_div, lake_data)
|
63
|
+
parse_fishing_structure(main_div, lake_data)
|
64
|
+
parse_tips_and_tactics(main_div, lake_data)
|
65
|
+
lake_data
|
66
|
+
end
|
67
|
+
|
68
|
+
def parse_tips_and_tactics(main_div, lake_data)
|
69
|
+
data = main_div.xpath('//h6[contains(text(), "Tips & Tactics")]').first
|
70
|
+
content = data.try(:next_element).try(:text)
|
71
|
+
lake_data[:tips_and_tactics] = content
|
72
|
+
end
|
73
|
+
|
74
|
+
def parse_fishing_structure(main_div, lake_data)
|
75
|
+
data = main_div.xpath('//h6[contains(text(), "Fishing Cover/Structure")]').first
|
76
|
+
content = data.try(:next_element).try(:to_html)
|
77
|
+
lake_data[:structure_and_cover_description] = content
|
78
|
+
end
|
79
|
+
|
80
|
+
def parse_angling_opportunities(main_div, lake_data)
|
81
|
+
data = main_div.xpath('//h6[contains(text(), "Angling Opportunities")]').first
|
82
|
+
description = data.try(:next_element).try(:text)
|
83
|
+
lake_data[:angling_opportunities_description] = description
|
84
|
+
|
85
|
+
table = main_div.css('#Ratings')
|
86
|
+
quality = ['Poor', 'Fair', 'Good', 'Excellent']
|
87
|
+
|
88
|
+
fish_species_elements = table.css('tr th.highlight2')
|
89
|
+
lake_data[:angling_opportunities_details] = {}
|
90
|
+
fish_species_elements.each do |fish_species_element|
|
91
|
+
rating_index = 0
|
92
|
+
species = cleanup_data(fish_species_element.text)
|
93
|
+
while fish_species_element = fish_species_element.next_element
|
94
|
+
if fish_species_element.css('img').count == 0
|
95
|
+
rating_index += 1
|
96
|
+
next
|
97
|
+
else
|
98
|
+
lake_data[:angling_opportunities_details][species] = quality[rating_index]
|
99
|
+
break
|
100
|
+
end
|
101
|
+
end
|
102
|
+
end
|
103
|
+
end
|
104
|
+
|
105
|
+
def parse_fishing_regulations(main_div, lake_data)
|
106
|
+
data = main_div.xpath('//h6[contains(text(), "Fishing Regulations")]').first
|
107
|
+
content = data.try(:next_element).try(:to_html)
|
108
|
+
lake_data[:fishing_regulations] = content
|
109
|
+
end
|
110
|
+
|
111
|
+
def parse_lake_maps(main_div, lake_data)
|
112
|
+
data = main_div.xpath('//h6[contains(text(), "Lake Maps")]').first
|
113
|
+
content = data.try(:next_element).try(:text)
|
114
|
+
lake_data[:lake_maps] = content
|
115
|
+
end
|
116
|
+
|
117
|
+
def parse_lake_characteristics(main_div, lake_data)
|
118
|
+
data = main_div.xpath('//h6[contains(text(), "Lake Characteristics")]').first
|
119
|
+
content = data.try(:next_element).try(:text)
|
120
|
+
lake_data[:lake_characteristics] = content
|
121
|
+
end
|
122
|
+
|
123
|
+
def parse_water_conditions(main_div, lake_data)
|
124
|
+
data = main_div.xpath('//h6[contains(text(), "Water Conditions")]').first
|
125
|
+
content = data.try(:next_element).try(:to_html)
|
126
|
+
lake_data[:water_conditions] = content
|
127
|
+
end
|
128
|
+
|
129
|
+
def parse_reservoir_controlling_authority(main_div, lake_data)
|
130
|
+
data = main_div.xpath('//h6[contains(text(), "Reservoir Controlling Authority")]').first
|
131
|
+
content = data.try(:next_element).try(:text)
|
132
|
+
lake_data[:reservoir_controlling_authority] = content
|
133
|
+
end
|
134
|
+
|
135
|
+
def parse_aquatic_vegetation(main_div, lake_data)
|
136
|
+
data = main_div.xpath('//h6[contains(text(), "Aquatic Vegetation")]').first
|
137
|
+
content = data.try(:next_element).try(:text)
|
138
|
+
lake_data[:aquatic_vegetation] = content
|
139
|
+
end
|
140
|
+
|
141
|
+
def parse_predominant_fish_species(main_div, lake_data)
|
142
|
+
element = main_div.xpath('//h6[contains(text(), "Predominant Fish Species")]').first
|
143
|
+
species_root = element.try(:next_element)
|
144
|
+
species = species_root.nil? ? nil : species_root.css('li').map{ |e| cleanup_data(e.text) }
|
145
|
+
lake_data[:predominant_fish_species] = species
|
146
|
+
end
|
147
|
+
|
148
|
+
def parse_lake_surveys(main_div, lake_data)
|
149
|
+
link = main_div.xpath('p/a[contains(text(), "Latest Survey Report")]').first
|
150
|
+
stocking_history = if link.nil?
|
151
|
+
nil
|
152
|
+
else
|
153
|
+
uri = link['href']
|
154
|
+
lake_data[:latest_survey_report] = convert_relative_href(uri, lake_data[:details_uri])
|
155
|
+
end
|
156
|
+
end
|
157
|
+
|
158
|
+
def parse_stocking_history(main_div, lake_data)
|
159
|
+
link = main_div.xpath('p/a[contains(text(), "Stocking History")]').first
|
160
|
+
stocking_history = if link.nil?
|
161
|
+
nil
|
162
|
+
else
|
163
|
+
uri = link['href']
|
164
|
+
lake_data[:stocking_history_uri] = convert_relative_href(uri, lake_data[:details_uri])
|
165
|
+
|
166
|
+
uri = URI(lake_data[:stocking_history_uri])
|
167
|
+
content = Net::HTTP.get(uri).encode('UTF-8', 'Windows-1252')
|
168
|
+
stocking_history_doc = Nokogiri::HTML(content)
|
169
|
+
|
170
|
+
stocking_history_table = stocking_history_doc.at('div#maincontent table')
|
171
|
+
headers = stocking_history_table.xpath('tr/th').map{ |r| r.text }
|
172
|
+
rows = stocking_history_table.xpath('tr/td').map{ |r| r.text }
|
173
|
+
|
174
|
+
table_data = process_data_table(headers, rows)
|
175
|
+
lake_data[:stocking_history] = table_data
|
176
|
+
end
|
177
|
+
end
|
178
|
+
|
179
|
+
def parse_current_fishing_report(main_div, lake_data)
|
180
|
+
link = main_div.xpath('p/a[contains(text(), "Fishing Report")]').first
|
181
|
+
fishing_report = if link.nil?
|
182
|
+
nil
|
183
|
+
else
|
184
|
+
uri = link['href']
|
185
|
+
lake_data[:current_fishing_report_uri] = convert_relative_href(uri, lake_data[:details_uri])
|
186
|
+
|
187
|
+
uri = URI(lake_data[:current_fishing_report_uri])
|
188
|
+
content = Net::HTTP.get(uri).encode('UTF-8', 'Windows-1252')
|
189
|
+
current_fishing_report_doc = Nokogiri::HTML(content)
|
190
|
+
current_fishing_report_dl = current_fishing_report_doc.at('div.row.report div.container dl')
|
191
|
+
|
192
|
+
date = cleanup_data(current_fishing_report_dl.at('dt span.title').text)
|
193
|
+
report = cleanup_data(current_fishing_report_dl.xpath('dd').text)
|
194
|
+
{date: date, report: report}
|
195
|
+
end
|
196
|
+
|
197
|
+
lake_data[:current_fishing_report] = fishing_report
|
198
|
+
end
|
199
|
+
|
200
|
+
def parse_lake_records(main_div, lake_data)
|
201
|
+
link = main_div.xpath('//a[contains(text(), "Lake Records")]').first
|
202
|
+
if link.nil?
|
203
|
+
lake_data[:fishing_records_uri] = nil
|
204
|
+
return
|
205
|
+
end
|
206
|
+
uri = link['href']
|
207
|
+
lake_data[:fishing_records_uri] = convert_relative_href(uri, lake_data[:details_uri])
|
208
|
+
|
209
|
+
uri = URI(lake_data[:fishing_records_uri])
|
210
|
+
content = Net::HTTP.get(uri).encode('UTF-8', 'Windows-1252')
|
211
|
+
lake_records_doc = Nokogiri::HTML(content)
|
212
|
+
lake_records_main_div = lake_records_doc.at('div#maincontent')
|
213
|
+
|
214
|
+
# H2's are record types like:
|
215
|
+
# - weight records
|
216
|
+
# - catch and release records (by length)
|
217
|
+
|
218
|
+
element = lake_records_main_div.children.first
|
219
|
+
current_record_type = nil # Weight or Length
|
220
|
+
current_age_group = nil # all ages, youth, etc
|
221
|
+
fishing_records_data = {}
|
222
|
+
while element = element.next_element
|
223
|
+
case element.name
|
224
|
+
when 'h2'
|
225
|
+
current_record_type = cleanup_data(element.text)
|
226
|
+
fishing_records_data[current_record_type] = {}
|
227
|
+
when 'h3'
|
228
|
+
current_age_group = cleanup_data(element.text)
|
229
|
+
fishing_records_data[current_record_type][current_age_group] = {}
|
230
|
+
when 'table'
|
231
|
+
fishing_method = cleanup_data(element.xpath('caption/big').text)
|
232
|
+
|
233
|
+
if fishing_records_data[current_record_type][current_age_group][fishing_method].nil?
|
234
|
+
fishing_records_data[current_record_type][current_age_group][fishing_method] = []
|
235
|
+
end
|
236
|
+
|
237
|
+
headers = element.xpath('tr/th').map{ |r| r.text }
|
238
|
+
rows = element.xpath('tr/td').map{ |r| r.text }
|
239
|
+
|
240
|
+
table_data = process_data_table(headers, rows)
|
241
|
+
fishing_records_data[current_record_type][current_age_group][fishing_method] = table_data
|
242
|
+
end
|
243
|
+
end
|
244
|
+
lake_data[:fishing_records] = fishing_records_data
|
245
|
+
end
|
246
|
+
|
247
|
+
# converts a html table with headers and rows into
|
248
|
+
# an array of hashes with header => value
|
249
|
+
def process_data_table(headers, rows)
|
250
|
+
data = []
|
251
|
+
header_count = headers.length
|
252
|
+
row_count = rows.count / header_count
|
253
|
+
|
254
|
+
row_data_index = 0
|
255
|
+
row_count.times do |row_index|
|
256
|
+
|
257
|
+
entry = {}
|
258
|
+
header_count.times do |header_index|
|
259
|
+
header = cleanup_data(headers[header_index])
|
260
|
+
table_data = cleanup_data(rows[row_data_index])
|
261
|
+
row_data_index += 1
|
262
|
+
entry[header] = table_data
|
263
|
+
end
|
264
|
+
data << entry
|
265
|
+
end
|
266
|
+
data
|
267
|
+
end
|
268
|
+
|
269
|
+
# converts this:
|
270
|
+
# ../../../action/waterecords.php?WB_code=0001
|
271
|
+
# into this:
|
272
|
+
# http://tpwd.texas.gov/fishboat/fish/action/waterecords.php?WB_code=0001
|
273
|
+
# based on this:
|
274
|
+
# http://tpwd.texas.gov/fishboat/fish/recreational/lakes/abilene
|
275
|
+
def convert_relative_href(href, current_url)
|
276
|
+
relative_depth = href.split('..').count - 1
|
277
|
+
url_parts = current_url.split('/')
|
278
|
+
url_parts.slice!(-relative_depth, relative_depth)
|
279
|
+
fixed_href = href.gsub('../', '')
|
280
|
+
url_parts.join('/') + '/' + fixed_href
|
281
|
+
end
|
282
|
+
|
283
|
+
# texas lake websites use lots of non breaking spaces
|
284
|
+
def cleanup_data(value)
|
285
|
+
nbsp = 160.chr('UTF-8')
|
286
|
+
value = value.strip.gsub(nbsp, '')
|
287
|
+
value.empty? ? nil : value
|
288
|
+
end
|
289
|
+
end
|
290
|
+
end
|
data/lib/lakes.rb
ADDED
data/lib/try.rb
ADDED
@@ -0,0 +1,78 @@
|
|
1
|
+
class Object
|
2
|
+
# Invokes the public method whose name goes as first argument just like
|
3
|
+
# +public_send+ does, except that if the receiver does not respond to it the
|
4
|
+
# call returns +nil+ rather than raising an exception.
|
5
|
+
#
|
6
|
+
# This method is defined to be able to write
|
7
|
+
#
|
8
|
+
# @person.try(:name)
|
9
|
+
#
|
10
|
+
# instead of
|
11
|
+
#
|
12
|
+
# @person ? @person.name : nil
|
13
|
+
#
|
14
|
+
# +try+ returns +nil+ when called on +nil+ regardless of whether it responds
|
15
|
+
# to the method:
|
16
|
+
#
|
17
|
+
# nil.try(:to_i) # => nil, rather than 0
|
18
|
+
#
|
19
|
+
# Arguments and blocks are forwarded to the method if invoked:
|
20
|
+
#
|
21
|
+
# @posts.try(:each_slice, 2) do |a, b|
|
22
|
+
# ...
|
23
|
+
# end
|
24
|
+
#
|
25
|
+
# The number of arguments in the signature must match. If the object responds
|
26
|
+
# to the method the call is attempted and +ArgumentError+ is still raised
|
27
|
+
# otherwise.
|
28
|
+
#
|
29
|
+
# If +try+ is called without arguments it yields the receiver to a given
|
30
|
+
# block unless it is +nil+:
|
31
|
+
#
|
32
|
+
# @person.try do |p|
|
33
|
+
# ...
|
34
|
+
# end
|
35
|
+
#
|
36
|
+
# Please also note that +try+ is defined on +Object+, therefore it won't work
|
37
|
+
# with instances of classes that do not have +Object+ among their ancestors,
|
38
|
+
# like direct subclasses of +BasicObject+. For example, using +try+ with
|
39
|
+
# +SimpleDelegator+ will delegate +try+ to the target instead of calling it on
|
40
|
+
# delegator itself.
|
41
|
+
def try(*a, &b)
|
42
|
+
if a.empty? && block_given?
|
43
|
+
yield self
|
44
|
+
else
|
45
|
+
public_send(*a, &b) if respond_to?(a.first)
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
# Same as #try, but will raise a NoMethodError exception if the receiving is not nil and
|
50
|
+
# does not implement the tried method.
|
51
|
+
def try!(*a, &b)
|
52
|
+
if a.empty? && block_given?
|
53
|
+
yield self
|
54
|
+
else
|
55
|
+
public_send(*a, &b)
|
56
|
+
end
|
57
|
+
end
|
58
|
+
end
|
59
|
+
|
60
|
+
class NilClass
|
61
|
+
# Calling +try+ on +nil+ always returns +nil+.
|
62
|
+
# It becomes specially helpful when navigating through associations that may return +nil+.
|
63
|
+
#
|
64
|
+
# nil.try(:name) # => nil
|
65
|
+
#
|
66
|
+
# Without +try+
|
67
|
+
# @person && !@person.children.blank? && @person.children.first.name
|
68
|
+
#
|
69
|
+
# With +try+
|
70
|
+
# @person.try(:children).try(:first).try(:name)
|
71
|
+
def try(*args)
|
72
|
+
nil
|
73
|
+
end
|
74
|
+
|
75
|
+
def try!(*args)
|
76
|
+
nil
|
77
|
+
end
|
78
|
+
end
|
metadata
ADDED
@@ -0,0 +1,113 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: lakes
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Shane Sherman
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-11-14 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: '1.11'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.11'
|
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: minitest
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '5.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '5.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: nokogiri
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '1.6'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '1.6'
|
69
|
+
description: I wrote this gem to originally parse texas lake data
|
70
|
+
email:
|
71
|
+
- shane.sherman@gmail.com
|
72
|
+
executables: []
|
73
|
+
extensions: []
|
74
|
+
extra_rdoc_files: []
|
75
|
+
files:
|
76
|
+
- ".gitignore"
|
77
|
+
- CODE_OF_CONDUCT.md
|
78
|
+
- Gemfile
|
79
|
+
- LICENSE.txt
|
80
|
+
- README.md
|
81
|
+
- Rakefile
|
82
|
+
- bin/console
|
83
|
+
- bin/setup
|
84
|
+
- lakes.gemspec
|
85
|
+
- lakes.json
|
86
|
+
- lib/lakes.rb
|
87
|
+
- lib/lakes/texas.rb
|
88
|
+
- lib/try.rb
|
89
|
+
homepage:
|
90
|
+
licenses:
|
91
|
+
- mit
|
92
|
+
metadata: {}
|
93
|
+
post_install_message:
|
94
|
+
rdoc_options: []
|
95
|
+
require_paths:
|
96
|
+
- lib
|
97
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
98
|
+
requirements:
|
99
|
+
- - ">="
|
100
|
+
- !ruby/object:Gem::Version
|
101
|
+
version: '0'
|
102
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
103
|
+
requirements:
|
104
|
+
- - ">="
|
105
|
+
- !ruby/object:Gem::Version
|
106
|
+
version: '0'
|
107
|
+
requirements: []
|
108
|
+
rubyforge_project:
|
109
|
+
rubygems_version: 2.5.1
|
110
|
+
signing_key:
|
111
|
+
specification_version: 4
|
112
|
+
summary: This gem parses lake details from various government websites
|
113
|
+
test_files: []
|