Class: GoogleClient
- Inherits:
-
BaseApiClient
- Object
- Base
- BaseApiClient
- GoogleClient
- Defined in:
- lib/whos_using_what/api_clients/google_client.rb
Instance Attribute Summary collapse
-
#results ⇒ Object
readonly
Returns the value of attribute results.
Attributes inherited from Base
Instance Method Summary collapse
- #extractUrls(rawInput, mustContainUrl) ⇒ Object
-
#initialize ⇒ GoogleClient
constructor
A new instance of GoogleClient.
-
#perform_search(queries, site_url, search_query_url_generator_closure) ⇒ Object
performs a search engine search that is restricted to a company’s website and then attempts to determine if they have job listings for a given technology.
Methods inherited from BaseApiClient
arraySearch, arry_to_str_delim, cleanup_url, #determineIfUsesTechnology, prepare_params_from_map_helper, starts_with?
Methods inherited from Base
Constructor Details
#initialize ⇒ GoogleClient
Returns a new instance of GoogleClient.
10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 |
# File 'lib/whos_using_what/api_clients/google_client.rb', line 10 def initialize @negativeMatchUrlPatterns = ['google', 'youtube', 'duckduckgo', 'bing', 'yahoo'] @positiveMatchUrlPatterns = ['http', 'www'] @technologiesToSearchFor = ['ruby', 'java', 'javascript', 'python'] @jobPageTokens = ['job', 'hiring', 'career'] @results = Hash.new @mechanize = Mechanize.new headless = Headless.new headless.start @browser = Watir::Browser.new :firefox end |
Instance Attribute Details
#results ⇒ Object (readonly)
Returns the value of attribute results.
8 9 10 |
# File 'lib/whos_using_what/api_clients/google_client.rb', line 8 def results @results end |
Instance Method Details
#extractUrls(rawInput, mustContainUrl) ⇒ Object
32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 |
# File 'lib/whos_using_what/api_clients/google_client.rb', line 32 def extractUrls (rawInput, mustContainUrl) acceptedUrls = Array.new if (rawInput == nil) return acceptedUrls end urls = [] begin urls = URI.extract(rawInput) end if urls.size < 1 return acceptedUrls end mustContainUrl = BaseApiClient.cleanup_url mustContainUrl urls.each do |url| url = BaseApiClient.cleanup_url url accept_url_bool = false @positiveMatchUrlPatterns.each do |token| if (BaseApiClient.starts_with? url, token) || (BaseApiClient.starts_with? url, mustContainUrl) accept_url_bool = true break end end if !accept_url_bool next end if !(url.include? mustContainUrl) accept_url_bool = false end @negativeMatchUrlPatterns.each do |token| if url.include? token accept_url_bool = false break end end url = BaseApiClient.cleanup_url url if accept_url_bool && url != nil && !(acceptedUrls.include? url) acceptedUrls.push url end end acceptedUrls end |
#perform_search(queries, site_url, search_query_url_generator_closure) ⇒ Object
performs a search engine search that is restricted to a company’s website and then attempts to determine if they have job listings for a given technology. If an ad exists it is returned as part of map
95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 |
# File 'lib/whos_using_what/api_clients/google_client.rb', line 95 def perform_search queries, site_url, search_query_url_generator_closure ret_map = Hash.new @technologiesToSearchFor.each do |search_keyword| url = "" raw_html = "" begin url = search_query_url_generator_closure.call( site_url, search_keyword ) #perform initial search engine search @browser.goto url raw_html = @browser.html puts "successfully queried url:" << url rescue Exception => e puts "exception:" << e. << " when querying url: " << url end urls = extractUrls(raw_html, site_url) urls.each do |cur_url| begin @browser.goto cur_url html = @browser.html #strip all html tags, for human readability and to cut down on some errors that could arise # TODO this was causing an exception # html = html.gsub!(/(<[^>]*>)|\n|\t/s) { " " } uses_technology = determineIfUsesTechnology(search_keyword, html) if (uses_technology) ret_map[search_keyword] = cur_url end rescue Exception => e puts e. end end end #throttle queries to avoid being black-listed by search engine sleep_seconds = rand(1-5) sleep sleep_seconds ret_map end |