Class: WWDCDownloader
- Inherits:
-
Object
- Object
- WWDCDownloader
- Defined in:
- lib/wwdcdownloader.rb
Constant Summary collapse
- BASE_URI =
'https://devimages-cdn.apple.com/wwdc-services/h8a19f8f/049CCC2F-0D8A-4F7D-BAB9-2D8F5BAA7030/contents.json'- WWDC_LIBRARIES =
[{:base => 'https://developer.apple.com/library/content', :lib => '/navigation/library.json'}]
Instance Attribute Summary collapse
-
#dl_dir ⇒ Object
Returns the value of attribute dl_dir.
-
#downloaded_files ⇒ Object
Returns the value of attribute downloaded_files.
-
#min_date ⇒ Object
Returns the value of attribute min_date.
-
#proxy_uri ⇒ Object
Returns the value of attribute proxy_uri.
Class Method Summary collapse
Instance Method Summary collapse
- #download_file(url, filename, dest_dir, duplicates_ok = true) ⇒ Object
- #download_sample_code_from_book_json(book_json_url, code_base_url, dest_dir, duplicates_ok) ⇒ Object
-
#initialize(dl_dir, min_date) ⇒ WWDCDownloader
constructor
A new instance of WWDCDownloader.
- #load ⇒ Object
-
#mkdir(dir) ⇒ Object
Creates the given directory if it doesn’t exist already.
- #read_url(url) ⇒ Object
Constructor Details
#initialize(dl_dir, min_date) ⇒ WWDCDownloader
Returns a new instance of WWDCDownloader.
32 33 34 35 36 37 38 39 40 41 42 |
# File 'lib/wwdcdownloader.rb', line 32 def initialize(dl_dir, min_date) self.dl_dir = dl_dir self.min_date = min_date self.downloaded_files = [] self.proxy_uri = nil if ENV['http_proxy'] || ENV['HTTP_PROXY'] uri = (ENV['http_proxy']) ? ENV['http_proxy'] : ENV['HTTP_PROXY'] self.proxy_uri = URI.parse(uri) end end |
Instance Attribute Details
#dl_dir ⇒ Object
Returns the value of attribute dl_dir.
30 31 32 |
# File 'lib/wwdcdownloader.rb', line 30 def dl_dir @dl_dir end |
#downloaded_files ⇒ Object
Returns the value of attribute downloaded_files.
30 31 32 |
# File 'lib/wwdcdownloader.rb', line 30 def downloaded_files @downloaded_files end |
#min_date ⇒ Object
Returns the value of attribute min_date.
30 31 32 |
# File 'lib/wwdcdownloader.rb', line 30 def min_date @min_date end |
#proxy_uri ⇒ Object
Returns the value of attribute proxy_uri.
30 31 32 |
# File 'lib/wwdcdownloader.rb', line 30 def proxy_uri @proxy_uri end |
Class Method Details
.run!(*args) ⇒ Object
228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 |
# File 'lib/wwdcdownloader.rb', line 228 def self.run!(*args) puts "WWDC 2017 Session Material Downloader" puts "by Johannes Fahrenkrug, @jfahrenkrug, springenwerk.com" puts "See you next year!" puts puts "Usage: wwdcdownloader [<target-dir>]" puts dl_dir = if args.size == 1 args.last else 'wwdc2017-assets' end w = WWDCDownloader.new(dl_dir, '2017-06-01') w.load return 0 end |
Instance Method Details
#download_file(url, filename, dest_dir, duplicates_ok = true) ⇒ Object
94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 |
# File 'lib/wwdcdownloader.rb', line 94 def download_file(url, filename, dest_dir, duplicates_ok = true) did_download = false outfilename = dest_dir + "/" + filename if duplicates_ok or (!File.exists?(outfilename) and !self.downloaded_files.include?(url)) # remember what we downloaded self.downloaded_files << url puts " Downloading #{url}" begin self.read_url(url) do |downloaded_file| open(outfilename, 'wb') do |file| file.write(downloaded_file) end did_download = true end rescue Exception => e puts " Download failed #{e}" end elsif !duplicates_ok puts " Already downloaded this file, skipping." end did_download end |
#download_sample_code_from_book_json(book_json_url, code_base_url, dest_dir, duplicates_ok) ⇒ Object
77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 |
# File 'lib/wwdcdownloader.rb', line 77 def download_sample_code_from_book_json(book_json_url, code_base_url, dest_dir, duplicates_ok) did_download = false self.read_url(book_json_url) do |book_json| if book_json[0,1] == '<' puts " Sorry, this samplecode apparently isn't available yet: #{code_base_url}/book.json" else book_res = JSON.parse(book_json) filename = book_res["sampleCode"] url = "#{code_base_url}/#{filename}" did_download = download_file(url, filename, dest_dir, duplicates_ok) end end did_download end |
#load ⇒ Object
119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 |
# File 'lib/wwdcdownloader.rb', line 119 def load mkdir(dl_dir) # get the sessions JSON self.read_url(BASE_URI) do |body| res = JSON.parse(body) sessions = res['contents'] resources = res['resources'] if sessions.size > 0 sessions.each do |session| if session['type'] == 'Session' && session['eventId'] == 'wwdc2017' title = session['title'] session_id = session['id'].gsub('wwdc2017-', '') puts "Session #{session_id} '#{title}'..." if session['related'] && session['related']['resources'] # Iterate over the resources = session['related']['resources'] did_download = false # get the files dirname = "#{dl_dir}/#{session_id}-#{title.gsub(/\/|&|!/, '')}" puts " Creating #{dirname}" did_create_dir = mkdir(dirname) resources.each do |resource| if resource['resource_type'] == 'samplecode' && .include?(resource['id']) puts " Found related resource #{resource['url']}" # Zip file? download right away if resource['url'] =~ /(\w+\.zip)$/ uri = URI.parse(resource['url']) filename = File.basename(uri.path) if download_file(resource['url'], filename, dirname, true) did_download = true end # Sample code landing page? else # Sanitize URL url = resource['url'].split('/Introduction/Intro.html')[0] if download_sample_code_from_book_json("#{url}/book.json", url, dirname, false) did_download = true end end end end if !did_download and did_create_dir Dir.delete(dirname) end end end end else print "No sessions :(.\n" end end # scrape the WWDC libraries... puts puts "Scraping the WWDC libraries..." WWDC_LIBRARIES.each do |lib_hash| lib = "#{lib_hash[:base]}#{lib_hash[:lib]}" puts puts "Library #{lib}" self.read_url(lib) do |body| body = body.gsub("''", '""') # Fix misformatted JSON body = body.gsub(/\"platform\"\s*:\s*12,$\s*\}/, "\"platform\": 12\n}") res = JSON.parse(body) docs = res['documents'] if docs.size > 0 docs.each do |doc| if doc[2] == 5 and doc[3] >= self.min_date # sample code and newer or equal to min date title = doc[0] puts "Sample Code '#{title}'..." # get the files dirname = "#{dl_dir}/#{title.gsub(/\/|&|!|:/, '')}" did_create_dir = mkdir(dirname) puts " Created #{dirname}" if did_create_dir segments = doc[9].split('/') url = "#{lib_hash[:base]}/samplecode/#{segments[2]}/book.json" #puts url did_download = download_sample_code_from_book_json(url, "#{lib_hash[:base]}/samplecode/#{segments[2]}", dirname, false) if !did_download and did_create_dir Dir.delete( dirname ) end end end else print "No code samples :(.\n" end end end puts "Done." end |
#mkdir(dir) ⇒ Object
Creates the given directory if it doesn’t exist already.
45 46 47 48 49 50 51 52 |
# File 'lib/wwdcdownloader.rb', line 45 def mkdir(dir) if File.directory?(dir) false else Dir.mkdir dir true end end |
#read_url(url) ⇒ Object
54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 |
# File 'lib/wwdcdownloader.rb', line 54 def read_url(url) uri = URI.parse(url) http = nil if self.proxy_uri http = Net::HTTP.new(uri.host, uri.port, self.proxy_uri.host, self.proxy_uri.port, self.proxy_uri.user, self.proxy_uri.password) else http = Net::HTTP.new(uri.host, uri.port) end http.use_ssl = true http.start do |http| request = Net::HTTP::Get.new(uri.request_uri) response = http.request(request) if response.code == '200' yield(response.body) end end end |