scrapers 0.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (40) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +18 -0
  3. data/.rspec-example +2 -0
  4. data/.watchr +27 -0
  5. data/Gemfile +4 -0
  6. data/Guardfile +6 -0
  7. data/LICENSE.txt +22 -0
  8. data/README.md +32 -0
  9. data/Rakefile +1 -0
  10. data/lib/scrapers/allrecipes.rb +49 -0
  11. data/lib/scrapers/discoverynews.rb +28 -0
  12. data/lib/scrapers/download.rb +37 -0
  13. data/lib/scrapers/gocomics.rb +43 -0
  14. data/lib/scrapers/imgur.rb +56 -0
  15. data/lib/scrapers/nasa_apod.rb +60 -0
  16. data/lib/scrapers/version.rb +7 -0
  17. data/lib/scrapers.rb +9 -0
  18. data/scrapers.gemspec +29 -0
  19. data/spec/scrapers/allrecipes_spec.rb +29 -0
  20. data/spec/scrapers/discoverynews_spec.rb +39 -0
  21. data/spec/scrapers/download_spec.rb +36 -0
  22. data/spec/scrapers/gocomics_spec.rb +46 -0
  23. data/spec/scrapers/imgur_spec.rb +31 -0
  24. data/spec/scrapers/nasa_apod_spec.rb +30 -0
  25. data/spec/scrapers_spec.rb +9 -0
  26. data/spec/spec_helper.rb +31 -0
  27. data/vcr_cassettes/allrecipes_morning-glory-muffins-i.yml +1047 -0
  28. data/vcr_cassettes/disconews_history-of-space.yml +385 -0
  29. data/vcr_cassettes/download_cassette.yml +431 -0
  30. data/vcr_cassettes/exampleatspecscrapersnasaapodspecrb16_cassette.yml +326 -0
  31. data/vcr_cassettes/exampleatspecscrapersnasaapodspecrb21_cassette.yml +326 -0
  32. data/vcr_cassettes/exampleatspecscrapersnasaapodspecrb22_cassette.yml +312 -0
  33. data/vcr_cassettes/gocomics_nonsequitur.yml +336 -0
  34. data/vcr_cassettes/shouldincludecontentencoded_cassette.yml +326 -0
  35. data/vcr_cassettes/shouldincludedescription_cassette.yml +326 -0
  36. data/vcr_cassettes/shouldincludeguid_cassette.yml +326 -0
  37. data/vcr_cassettes/shouldincludelink_cassette.yml +326 -0
  38. data/vcr_cassettes/shouldincludepubDate_cassette.yml +326 -0
  39. data/vcr_cassettes/shouldincludetitle_cassette.yml +326 -0
  40. metadata +203 -0
@@ -0,0 +1,326 @@
1
+ ---
2
+ http_interactions:
3
+ - request:
4
+ method: get
5
+ uri: http://apod.nasa.gov/apod/astropix.html
6
+ body:
7
+ encoding: US-ASCII
8
+ string: ''
9
+ headers:
10
+ Accept-Encoding:
11
+ - gzip,deflate,identity
12
+ Accept:
13
+ - '*/*'
14
+ User-Agent:
15
+ - Mechanize/2.7.2 Ruby/2.0.0p247 (http://github.com/sparklemotion/mechanize/)
16
+ Accept-Charset:
17
+ - ISO-8859-1,utf-8;q=0.7,*;q=0.7
18
+ Accept-Language:
19
+ - en-us,en;q=0.5
20
+ Host:
21
+ - apod.nasa.gov
22
+ Connection:
23
+ - keep-alive
24
+ Keep-Alive:
25
+ - 300
26
+ response:
27
+ status:
28
+ code: 200
29
+ message: OK
30
+ headers:
31
+ Date:
32
+ - Sun, 29 Sep 2013 04:05:40 GMT
33
+ Server:
34
+ - WebServer/1.0
35
+ Accept-Ranges:
36
+ - bytes
37
+ Content-Length:
38
+ - '4683'
39
+ Keep-Alive:
40
+ - timeout=5, max=100
41
+ Connection:
42
+ - Keep-Alive
43
+ Content-Type:
44
+ - text/html; charset=ISO-8859-1
45
+ body:
46
+ encoding: UTF-8
47
+ string: "<html>\n<head>\n<title>Astronomy Picture of the Day\n</title>\n<!--
48
+ gsfc meta tags -->\n<meta name=\"orgcode\" content=\"661\">\n<meta name=\"rno\"
49
+ content=\"phillip.a.newman\">\n<meta name=\"content-owner\" content=\"Jerry.T.Bonnell.1\">\n<meta
50
+ name=\"webmaster\" content=\"Stephen.F.Fantasia.1\">\n<meta name=\"description\"
51
+ content=\"A different astronomy and space science\nrelated image is featured
52
+ each day, along with a brief explanation.\">\n<!-- -->\n<meta name=\"keywords\"
53
+ content=\"Eagle Nebula, M16, dust pillar\">\n</head>\n<body BGCOLOR=\"#F4F4FF\"
54
+ text=\"#000000\" link=\"#0000FF\" vlink=\"#7F0F9F\"\nalink=\"#FF0000\">\n\n<center>\n<h1>
55
+ Astronomy Picture of the Day </h1>\n<p>\n\n<a href=\"archivepix.html\">Discover
56
+ the cosmos!</a>\nEach day a different image or photograph of our fascinating
57
+ universe is\nfeatured, along with a brief explanation written by a professional
58
+ astronomer.\n<p>\n\n2013 September 29 \n<br> \n<a href=\"image/1309/fairypillar_hubble_900.jpg\">\n<IMG
59
+ SRC=\"image/1309/fairypillar_hubble_900.jpg\"\nalt=\"See Explanation. Clicking
60
+ on the picture will download\n the highest resolution version available.\"></a>\n</center>\n\n<center>\n<b>
61
+ The Fairy of Eagle Nebula </b> <br> \n<b> Image Credit: </b> \n<a href=\n\"http://heritage.stsci.edu/commonpages/infoindex/ourproject/moreproject.html\"\n>The
62
+ Hubble Heritage Team</a>,\n(<a href=\"http://www.stsci.edu/resources/\">STScI</a>/<a
63
+ href=\"\nhttp://www.aura-astronomy.org/\">AURA</a>),\n<a href=\"http://www.esa.int/\">ESA</a>,\n<a
64
+ href=\"http://www.nasa.gov/\">NASA</a>\n\n</center> <p> \n\n<b> Explanation:
65
+ </b> \nThe dust sculptures of the Eagle Nebula are evaporating. \n\nAs powerful
66
+ starlight whittles away these\n<a href=\"ap031228.html\">cool cosmic mountains</a>,
67
+ the\n<a href=\"ap070218.html\">statuesque pillars</a> that remain\nmight be
68
+ imagined as <a href=\n\"http://www.pantheon.org/areas/bestiary/\">mythical
69
+ beasts</a>. \n\nPictured <a href=\n\"http://hubblesite.org/newscenter/newsdesk/archive/releases/2005/12/\"\n>above</a>
70
+ is one of <a href=\"ap061022.html\">several striking\ndust pillars</a> of
71
+ the\n<a href=\"http://en.wikipedia.org/wiki/Eagle_Nebula\">Eagle Nebula</a>\nthat
72
+ might be described as a gigantic alien\n<a href=\"http://en.wikipedia.org/wiki/Fairies\">fairy</a>.
73
+ \ \n\nThis fairy, however, is ten\n<a href=\"http://chandra.harvard.edu/photo/cosmic_distance.html\"\n>light
74
+ years</a> tall and spews radiation much hotter than\n<a href=\"ap130901.html\">common
75
+ fire</a>.\n\nThe <a href=\"ap041024.html\">greater Eagle Nebula</a>, M16,\nis
76
+ actually a giant evaporating shell of gas and\n<a href=\"ap030706.html\">dust</a>
77
+ inside of which is a growing\n<a href=\"http://kidshealth.org/kid/health_problems/teeth/cavity.html\"\n>cavity</a>
78
+ filled with a spectacular stellar nursery currently forming an\n<a href=\"http://www.seds.org/messier/open.html\">open
79
+ cluster</a> of stars. \n\nThe <a href=\"http://www.spacetelescope.org/images/html/heic0506b.html\"\n>above
80
+ image</a> in scientifically re-assigned colors was\n<a href=\"http://heritage.stsci.edu/2005/12b/index.html\">released</a>\nin
81
+ 2005 as part of the\n<a href=\"http://www.spacetelescope.org/news/html/heic0506.html\"\n>fifteenth
82
+ anniversary celebration</a> of the\n<a href=\"ap021124.html\">launch</a> of
83
+ the\n<a href=\"http://www.stsci.edu/hst/HST_overview/\">Hubble Space Telescope</a>.\n\n\n<p>
84
+ <center> \n<b> Note: </b>\n<a href=\"http://asterisk.apod.com/viewtopic.php?f=28&t=32210\"\n>How
85
+ to follow APOD if the US government shuts down.</a> <br>\n<b> Tomorrow's picture:
86
+ </b>the green unknown\n\n<p> <hr>\n<a href=\"ap130928.html\">&lt;</a>\n| <a
87
+ href=\"archivepix.html\">Archive</a>\n| <a href=\"lib/aptree.html\">Index</a>\n|
88
+ <a href=\"http://antwrp.gsfc.nasa.gov/cgi-bin/apod/apod_search\">Search</a>\n|
89
+ <a href=\"calendar/allyears.html\">Calendar</a>\n| <a href=\"/apod.rss\">RSS</a>\n|
90
+ <a href=\"lib/edlinks.html\">Education</a>\n| <a href=\"lib/about_apod.html\">About
91
+ APOD</a>\n| <a href=\n\"http://asterisk.apod.com/discuss_apod.php?date=130929\">Discuss</a>\n|
92
+ <a href=\"ap130930.html\">&gt;</a>\n\n<hr><p>\n<b> Authors & editors: </b>\n<a
93
+ href=\"http://www.phy.mtu.edu/faculty/Nemiroff.html\">Robert Nemiroff</a>\n(<a
94
+ href=\"http://www.phy.mtu.edu/\">MTU</a>) &\n<a href=\"http://antwrp.gsfc.nasa.gov/htmltest/jbonnell/www/bonnell.html\"\n>Jerry
95
+ Bonnell</a> (<a href=\"http://www.astro.umd.edu/\">UMCP</a>)<br>\n<b>NASA
96
+ Official: </b> Phillip Newman\n<a href=\"lib/about_apod.html#srapply\">Specific
97
+ rights apply</a>.<br>\n<a href=\"http://www.nasa.gov/about/highlights/HP_Privacy.html\">NASA
98
+ Web\nPrivacy Policy and Important Notices</a><br>\n<b>A service of:</b>\n<a
99
+ href=\"http://astrophysics.gsfc.nasa.gov/\">ASD</a> at\n<a href=\"http://www.nasa.gov/\">NASA</a>
100
+ /\n<a href=\"http://www.nasa.gov/centers/goddard/\">GSFC</a>\n<br><b>&</b>
101
+ <a href=\"http://www.mtu.edu/\">Michigan Tech. U.</a><br>\n</center>\n</body>\n</html>\n"
102
+ http_version:
103
+ recorded_at: Sun, 29 Sep 2013 04:05:40 GMT
104
+ - request:
105
+ method: get
106
+ uri: http://apod.nasa.gov/apod/ap130928.html
107
+ body:
108
+ encoding: US-ASCII
109
+ string: ''
110
+ headers:
111
+ Accept-Encoding:
112
+ - gzip,deflate,identity
113
+ Accept:
114
+ - '*/*'
115
+ User-Agent:
116
+ - Mechanize/2.7.2 Ruby/2.0.0p247 (http://github.com/sparklemotion/mechanize/)
117
+ Accept-Charset:
118
+ - ISO-8859-1,utf-8;q=0.7,*;q=0.7
119
+ Accept-Language:
120
+ - en-us,en;q=0.5
121
+ Host:
122
+ - apod.nasa.gov
123
+ Referer:
124
+ - !ruby/object:URI::HTTP
125
+ scheme: http
126
+ user:
127
+ password:
128
+ host: apod.nasa.gov
129
+ port: 80
130
+ path: /apod/astropix.html
131
+ query:
132
+ opaque:
133
+ registry:
134
+ fragment:
135
+ parser:
136
+ Connection:
137
+ - keep-alive
138
+ Keep-Alive:
139
+ - 300
140
+ response:
141
+ status:
142
+ code: 200
143
+ message: OK
144
+ headers:
145
+ Date:
146
+ - Sun, 29 Sep 2013 04:05:40 GMT
147
+ Server:
148
+ - WebServer/1.0
149
+ Accept-Ranges:
150
+ - bytes
151
+ Content-Length:
152
+ - '4103'
153
+ Keep-Alive:
154
+ - timeout=5, max=100
155
+ Connection:
156
+ - Keep-Alive
157
+ Content-Type:
158
+ - text/html; charset=ISO-8859-1
159
+ body:
160
+ encoding: UTF-8
161
+ string: "<html>\n<head>\n<title> APOD: 2013 September 28 - Equinox Earth \n</title>\n<!--
162
+ gsfc meta tags -->\n<meta name=\"orgcode\" content=\"661\">\n<meta name=\"rno\"
163
+ content=\"phillip.a.newman\">\n<meta name=\"content-owner\" content=\"Jerry.T.Bonnell.1\">\n<meta
164
+ name=\"webmaster\" content=\"Stephen.F.Fantasia.1\">\n<meta name=\"description\"
165
+ content=\"A different astronomy and space science\nrelated image is featured
166
+ each day, along with a brief explanation.\">\n<!-- -->\n<meta name=\"keywords\"
167
+ content=\"equinox, earth, elektro-l, geosynchronous\">\n</head>\n<body BGCOLOR=\"#F4F4FF\"
168
+ text=\"#000000\" link=\"#0000FF\" vlink=\"#7F0F9F\"\nalink=\"#FF0000\">\n\n<center>\n<h1>
169
+ Astronomy Picture of the Day </h1>\n<p>\n\n<a href=\"archivepix.html\">Discover
170
+ the cosmos!</a>\nEach day a different image or photograph of our fascinating
171
+ universe is\nfeatured, along with a brief explanation written by a professional
172
+ astronomer.\n<p>\n\n2013 September 28\n<br>\n<a href=\"image/1309/EquinoxEarthElektroL900.jpg\">\n<IMG
173
+ SRC=\"image/1309/EquinoxEarthElektroL800.jpg\"\nalt=\"See Explanation. Clicking
174
+ on the picture will download\n the highest resolution version available.\"></a>\n</center>\n\n<center>\n<b>
175
+ Equinox Earth </b> <br> \n\n<b> Image Credit: </b>\n\n<a href=\"http://roscosmos.ru/\">Roscosmos</a>
176
+ / NTSOMZ /\n<a href=\"http://zelenyikot.livejournal.com/\n17213.html\">zelenyikot.livejournal.com</a>\n<br>\nCourtesy:\n<a
177
+ href=\"mailto: tirsky at gmail dot com\">Igor Tirsky</a>,\n<a href=\"mailto:
178
+ zelenyikoteyka at gmail dot com\">Vitaliy Egorov</a>\n\n</center> \n<p> \n\n<b>
179
+ Explanation: </b>\n\nFrom a geostationary orbit 36,000 kilometers above the
180
+ equator,\nRussian meteorological\n<a href=\"https://en.wikipedia.org/wiki/Elektro%E2%80%93L\">satellite\nElektro-L</a>
181
+ takes high-resolution images\n<a href=\"http://www.planetary.org/blogs/guest-blogs/2013/\n20130723-beautiful-science-by-elektro-l.html\">our
182
+ fair planet</a>\nevery 30 minutes.\n\nBut only twice\n<a href=\"ap130922.html\">a
183
+ year</a>, during an Equinox, can it capture an image\nlike this one, showing
184
+ an entire hemisphere bathed in sunlight.\n\n<a href=\"https://en.wikipedia.org/wiki/Equinox\">At
185
+ an Equinox</a>,\nthe Earth's axis of rotation is not tilted toward or\naway
186
+ from the Sun, so the\n<a href=\"http://earthobservatory.nasa.gov/IOTD/\nview.php?id=52248\">solar
187
+ illumination can extend</a>\nto both the planet's poles.\n\nOf course,\nthis
188
+ <a href=\"https://vk.com/electrol\">Elektro-L picture</a>\nwas recorded on
189
+ September 22nd,\nat the northern hemisphere's autumnal equinox.\n\nFor a moment
190
+ on that date, the Sun was behind\nthe <a href=\"ap100220.html\">geostationary
191
+ satellite</a> and a\ntelltale glint of reflected sunlight is seen crossing
192
+ the equator,\nat the location on the planet with satellite and sun directly
193
+ overhead\n(<a href=\"image/1309/130921-600ElektroL.gif\">5MB animated gif</a>).\n\n<p>
194
+ <center>\n<b> Tomorrow's picture: </b><a href=\"ap130929.html\">fairy big</a>\n\n<p>
195
+ <hr>\n<a href=\"ap130927.html\">&lt;</a>\n| <a href=\"archivepix.html\">Archive</a>\n|
196
+ <a href=\"lib/aptree.html\">Index</a>\n| <a href=\"http://antwrp.gsfc.nasa.gov/cgi-bin/apod/apod_search\">Search</a>\n|
197
+ <a href=\"calendar/allyears.html\">Calendar</a>\n| <a href=\"/apod.rss\">RSS</a>\n|
198
+ <a href=\"lib/edlinks.html\">Education</a>\n| <a href=\"lib/about_apod.html\">About
199
+ APOD</a>\n| <a href=\n\"http://asterisk.apod.com/discuss_apod.php?date=130928\">Discuss</a>\n|
200
+ <a href=\"ap130929.html\">&gt;</a>\n\n<hr><p>\n<b> Authors & editors: </b>\n<a
201
+ href=\"http://www.phy.mtu.edu/faculty/Nemiroff.html\">Robert Nemiroff</a>\n(<a
202
+ href=\"http://www.phy.mtu.edu/\">MTU</a>) &\n<a href=\"http://antwrp.gsfc.nasa.gov/htmltest/jbonnell/www/bonnell.html\"\n>Jerry
203
+ Bonnell</a> (<a href=\"http://www.astro.umd.edu/\">UMCP</a>)<br>\n<b>NASA
204
+ Official: </b> Phillip Newman\n<a href=\"lib/about_apod.html#srapply\">Specific
205
+ rights apply</a>.<br>\n<a href=\"http://www.nasa.gov/about/highlights/HP_Privacy.html\">NASA
206
+ Web\nPrivacy Policy and Important Notices</a><br>\n<b>A service of:</b>\n<a
207
+ href=\"http://astrophysics.gsfc.nasa.gov/\">ASD</a> at\n<a href=\"http://www.nasa.gov/\">NASA</a>
208
+ /\n<a href=\"http://www.nasa.gov/centers/goddard/\">GSFC</a>\n<br><b>&</b>
209
+ <a href=\"http://www.mtu.edu/\">Michigan Tech. U.</a><br>\n</center>\n</body>\n</html>\n"
210
+ http_version:
211
+ recorded_at: Sun, 29 Sep 2013 04:05:40 GMT
212
+ - request:
213
+ method: get
214
+ uri: http://apod.nasa.gov/apod/ap130929.html
215
+ body:
216
+ encoding: US-ASCII
217
+ string: ''
218
+ headers:
219
+ Accept-Encoding:
220
+ - gzip,deflate,identity
221
+ Accept:
222
+ - '*/*'
223
+ User-Agent:
224
+ - Mechanize/2.7.2 Ruby/2.0.0p247 (http://github.com/sparklemotion/mechanize/)
225
+ Accept-Charset:
226
+ - ISO-8859-1,utf-8;q=0.7,*;q=0.7
227
+ Accept-Language:
228
+ - en-us,en;q=0.5
229
+ Host:
230
+ - apod.nasa.gov
231
+ Referer:
232
+ - !ruby/object:URI::HTTP
233
+ scheme: http
234
+ user:
235
+ password:
236
+ host: apod.nasa.gov
237
+ port: 80
238
+ path: /apod/ap130928.html
239
+ query:
240
+ opaque:
241
+ registry:
242
+ fragment:
243
+ parser:
244
+ Connection:
245
+ - keep-alive
246
+ Keep-Alive:
247
+ - 300
248
+ response:
249
+ status:
250
+ code: 200
251
+ message: OK
252
+ headers:
253
+ Date:
254
+ - Sun, 29 Sep 2013 04:05:40 GMT
255
+ Server:
256
+ - WebServer/1.0
257
+ Accept-Ranges:
258
+ - bytes
259
+ Content-Length:
260
+ - '4736'
261
+ Keep-Alive:
262
+ - timeout=5, max=100
263
+ Connection:
264
+ - Keep-Alive
265
+ Content-Type:
266
+ - text/html; charset=ISO-8859-1
267
+ body:
268
+ encoding: UTF-8
269
+ string: "<html>\n<head>\n<title> APOD: 2013 September 29 - The Fairy of Eagle
270
+ Nebula \n</title>\n<!-- gsfc meta tags -->\n<meta name=\"orgcode\" content=\"661\">\n<meta
271
+ name=\"rno\" content=\"phillip.a.newman\">\n<meta name=\"content-owner\" content=\"Jerry.T.Bonnell.1\">\n<meta
272
+ name=\"webmaster\" content=\"Stephen.F.Fantasia.1\">\n<meta name=\"description\"
273
+ content=\"A different astronomy and space science\nrelated image is featured
274
+ each day, along with a brief explanation.\">\n<!-- -->\n<meta name=\"keywords\"
275
+ content=\"Eagle Nebula, M16, dust pillar\">\n</head>\n<body BGCOLOR=\"#F4F4FF\"
276
+ text=\"#000000\" link=\"#0000FF\" vlink=\"#7F0F9F\"\nalink=\"#FF0000\">\n\n<center>\n<h1>
277
+ Astronomy Picture of the Day </h1>\n<p>\n\n<a href=\"archivepix.html\">Discover
278
+ the cosmos!</a>\nEach day a different image or photograph of our fascinating
279
+ universe is\nfeatured, along with a brief explanation written by a professional
280
+ astronomer.\n<p>\n\n2013 September 29 \n<br> \n<a href=\"image/1309/fairypillar_hubble_900.jpg\">\n<IMG
281
+ SRC=\"image/1309/fairypillar_hubble_900.jpg\"\nalt=\"See Explanation. Clicking
282
+ on the picture will download\n the highest resolution version available.\"></a>\n</center>\n\n<center>\n<b>
283
+ The Fairy of Eagle Nebula </b> <br> \n<b> Image Credit: </b> \n<a href=\n\"http://heritage.stsci.edu/commonpages/infoindex/ourproject/moreproject.html\"\n>The
284
+ Hubble Heritage Team</a>,\n(<a href=\"http://www.stsci.edu/resources/\">STScI</a>/<a
285
+ href=\"\nhttp://www.aura-astronomy.org/\">AURA</a>),\n<a href=\"http://www.esa.int/\">ESA</a>,\n<a
286
+ href=\"http://www.nasa.gov/\">NASA</a>\n\n</center> <p> \n\n<b> Explanation:
287
+ </b> \nThe dust sculptures of the Eagle Nebula are evaporating. \n\nAs powerful
288
+ starlight whittles away these\n<a href=\"ap031228.html\">cool cosmic mountains</a>,
289
+ the\n<a href=\"ap070218.html\">statuesque pillars</a> that remain\nmight be
290
+ imagined as <a href=\n\"http://www.pantheon.org/areas/bestiary/\">mythical
291
+ beasts</a>. \n\nPictured <a href=\n\"http://hubblesite.org/newscenter/newsdesk/archive/releases/2005/12/\"\n>above</a>
292
+ is one of <a href=\"ap061022.html\">several striking\ndust pillars</a> of
293
+ the\n<a href=\"http://en.wikipedia.org/wiki/Eagle_Nebula\">Eagle Nebula</a>\nthat
294
+ might be described as a gigantic alien\n<a href=\"http://en.wikipedia.org/wiki/Fairies\">fairy</a>.
295
+ \ \n\nThis fairy, however, is ten\n<a href=\"http://chandra.harvard.edu/photo/cosmic_distance.html\"\n>light
296
+ years</a> tall and spews radiation much hotter than\n<a href=\"ap130901.html\">common
297
+ fire</a>.\n\nThe <a href=\"ap041024.html\">greater Eagle Nebula</a>, M16,\nis
298
+ actually a giant evaporating shell of gas and\n<a href=\"ap030706.html\">dust</a>
299
+ inside of which is a growing\n<a href=\"http://kidshealth.org/kid/health_problems/teeth/cavity.html\"\n>cavity</a>
300
+ filled with a spectacular stellar nursery currently forming an\n<a href=\"http://www.seds.org/messier/open.html\">open
301
+ cluster</a> of stars. \n\nThe <a href=\"http://www.spacetelescope.org/images/html/heic0506b.html\"\n>above
302
+ image</a> in scientifically re-assigned colors was\n<a href=\"http://heritage.stsci.edu/2005/12b/index.html\">released</a>\nin
303
+ 2005 as part of the\n<a href=\"http://www.spacetelescope.org/news/html/heic0506.html\"\n>fifteenth
304
+ anniversary celebration</a> of the\n<a href=\"ap021124.html\">launch</a> of
305
+ the\n<a href=\"http://www.stsci.edu/hst/HST_overview/\">Hubble Space Telescope</a>.\n\n\n<p>
306
+ <center> \n<b> Note: </b>\n<a href=\"http://asterisk.apod.com/viewtopic.php?f=28&t=32210\"\n>How
307
+ to follow APOD if the US government shuts down.</a> <br>\n<b> Tomorrow's picture:
308
+ </b><a href=\"ap130930.html\">the green unknown</a>\n\n<p> <hr>\n<a href=\"ap130928.html\">&lt;</a>\n|
309
+ <a href=\"archivepix.html\">Archive</a>\n| <a href=\"lib/aptree.html\">Index</a>\n|
310
+ <a href=\"http://antwrp.gsfc.nasa.gov/cgi-bin/apod/apod_search\">Search</a>\n|
311
+ <a href=\"calendar/allyears.html\">Calendar</a>\n| <a href=\"/apod.rss\">RSS</a>\n|
312
+ <a href=\"lib/edlinks.html\">Education</a>\n| <a href=\"lib/about_apod.html\">About
313
+ APOD</a>\n| <a href=\n\"http://asterisk.apod.com/discuss_apod.php?date=130929\">Discuss</a>\n|
314
+ <a href=\"ap130930.html\">&gt;</a>\n\n<hr><p>\n<b> Authors & editors: </b>\n<a
315
+ href=\"http://www.phy.mtu.edu/faculty/Nemiroff.html\">Robert Nemiroff</a>\n(<a
316
+ href=\"http://www.phy.mtu.edu/\">MTU</a>) &\n<a href=\"http://antwrp.gsfc.nasa.gov/htmltest/jbonnell/www/bonnell.html\"\n>Jerry
317
+ Bonnell</a> (<a href=\"http://www.astro.umd.edu/\">UMCP</a>)<br>\n<b>NASA
318
+ Official: </b> Phillip Newman\n<a href=\"lib/about_apod.html#srapply\">Specific
319
+ rights apply</a>.<br>\n<a href=\"http://www.nasa.gov/about/highlights/HP_Privacy.html\">NASA
320
+ Web\nPrivacy Policy and Important Notices</a><br>\n<b>A service of:</b>\n<a
321
+ href=\"http://astrophysics.gsfc.nasa.gov/\">ASD</a> at\n<a href=\"http://www.nasa.gov/\">NASA</a>
322
+ /\n<a href=\"http://www.nasa.gov/centers/goddard/\">GSFC</a>\n<br><b>&</b>
323
+ <a href=\"http://www.mtu.edu/\">Michigan Tech. U.</a><br>\n</center>\n</body>\n</html>\n"
324
+ http_version:
325
+ recorded_at: Sun, 29 Sep 2013 04:05:40 GMT
326
+ recorded_with: VCR 2.6.0
metadata ADDED
@@ -0,0 +1,203 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: scrapers
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.2.0
5
+ platform: ruby
6
+ authors:
7
+ - Tamara Temple
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2013-09-29 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: '0'
20
+ type: :development
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - '>='
25
+ - !ruby/object:Gem::Version
26
+ version: '0'
27
+ - !ruby/object:Gem::Dependency
28
+ name: rake
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - '>='
32
+ - !ruby/object:Gem::Version
33
+ version: '0'
34
+ type: :development
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - '>='
39
+ - !ruby/object:Gem::Version
40
+ version: '0'
41
+ - !ruby/object:Gem::Dependency
42
+ name: rspec
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - '>='
46
+ - !ruby/object:Gem::Version
47
+ version: '0'
48
+ type: :development
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - '>='
53
+ - !ruby/object:Gem::Version
54
+ version: '0'
55
+ - !ruby/object:Gem::Dependency
56
+ name: mechanize
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - '>='
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ type: :runtime
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - '>='
67
+ - !ruby/object:Gem::Version
68
+ version: '0'
69
+ - !ruby/object:Gem::Dependency
70
+ name: guard
71
+ requirement: !ruby/object:Gem::Requirement
72
+ requirements:
73
+ - - '>='
74
+ - !ruby/object:Gem::Version
75
+ version: '0'
76
+ type: :development
77
+ prerelease: false
78
+ version_requirements: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - '>='
81
+ - !ruby/object:Gem::Version
82
+ version: '0'
83
+ - !ruby/object:Gem::Dependency
84
+ name: guard-rspec
85
+ requirement: !ruby/object:Gem::Requirement
86
+ requirements:
87
+ - - '>='
88
+ - !ruby/object:Gem::Version
89
+ version: '0'
90
+ type: :development
91
+ prerelease: false
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - '>='
95
+ - !ruby/object:Gem::Version
96
+ version: '0'
97
+ - !ruby/object:Gem::Dependency
98
+ name: webmock
99
+ requirement: !ruby/object:Gem::Requirement
100
+ requirements:
101
+ - - '>='
102
+ - !ruby/object:Gem::Version
103
+ version: '0'
104
+ type: :development
105
+ prerelease: false
106
+ version_requirements: !ruby/object:Gem::Requirement
107
+ requirements:
108
+ - - '>='
109
+ - !ruby/object:Gem::Version
110
+ version: '0'
111
+ - !ruby/object:Gem::Dependency
112
+ name: vcr
113
+ requirement: !ruby/object:Gem::Requirement
114
+ requirements:
115
+ - - '>='
116
+ - !ruby/object:Gem::Version
117
+ version: '0'
118
+ type: :development
119
+ prerelease: false
120
+ version_requirements: !ruby/object:Gem::Requirement
121
+ requirements:
122
+ - - '>='
123
+ - !ruby/object:Gem::Version
124
+ version: '0'
125
+ description: A library of web site scrapers utilizing mechanize and other goodies.
126
+ Helpful in gathering images, moving things, saving things, etc.
127
+ email:
128
+ - tamouse@gmail.com
129
+ executables: []
130
+ extensions: []
131
+ extra_rdoc_files: []
132
+ files:
133
+ - .gitignore
134
+ - .rspec-example
135
+ - .watchr
136
+ - Gemfile
137
+ - Guardfile
138
+ - LICENSE.txt
139
+ - README.md
140
+ - Rakefile
141
+ - lib/scrapers.rb
142
+ - lib/scrapers/allrecipes.rb
143
+ - lib/scrapers/discoverynews.rb
144
+ - lib/scrapers/download.rb
145
+ - lib/scrapers/gocomics.rb
146
+ - lib/scrapers/imgur.rb
147
+ - lib/scrapers/nasa_apod.rb
148
+ - lib/scrapers/version.rb
149
+ - scrapers.gemspec
150
+ - spec/scrapers/allrecipes_spec.rb
151
+ - spec/scrapers/discoverynews_spec.rb
152
+ - spec/scrapers/download_spec.rb
153
+ - spec/scrapers/gocomics_spec.rb
154
+ - spec/scrapers/imgur_spec.rb
155
+ - spec/scrapers/nasa_apod_spec.rb
156
+ - spec/scrapers_spec.rb
157
+ - spec/spec_helper.rb
158
+ - vcr_cassettes/allrecipes_morning-glory-muffins-i.yml
159
+ - vcr_cassettes/disconews_history-of-space.yml
160
+ - vcr_cassettes/download_cassette.yml
161
+ - vcr_cassettes/exampleatspecscrapersnasaapodspecrb16_cassette.yml
162
+ - vcr_cassettes/exampleatspecscrapersnasaapodspecrb21_cassette.yml
163
+ - vcr_cassettes/exampleatspecscrapersnasaapodspecrb22_cassette.yml
164
+ - vcr_cassettes/gocomics_nonsequitur.yml
165
+ - vcr_cassettes/shouldincludecontentencoded_cassette.yml
166
+ - vcr_cassettes/shouldincludedescription_cassette.yml
167
+ - vcr_cassettes/shouldincludeguid_cassette.yml
168
+ - vcr_cassettes/shouldincludelink_cassette.yml
169
+ - vcr_cassettes/shouldincludepubDate_cassette.yml
170
+ - vcr_cassettes/shouldincludetitle_cassette.yml
171
+ homepage: http://github.com/tamouse/scrapers
172
+ licenses:
173
+ - MIT
174
+ metadata: {}
175
+ post_install_message:
176
+ rdoc_options: []
177
+ require_paths:
178
+ - lib
179
+ required_ruby_version: !ruby/object:Gem::Requirement
180
+ requirements:
181
+ - - '>='
182
+ - !ruby/object:Gem::Version
183
+ version: '0'
184
+ required_rubygems_version: !ruby/object:Gem::Requirement
185
+ requirements:
186
+ - - '>='
187
+ - !ruby/object:Gem::Version
188
+ version: '0'
189
+ requirements: []
190
+ rubyforge_project:
191
+ rubygems_version: 2.0.3
192
+ signing_key:
193
+ specification_version: 4
194
+ summary: Web site scrapers
195
+ test_files:
196
+ - spec/scrapers/allrecipes_spec.rb
197
+ - spec/scrapers/discoverynews_spec.rb
198
+ - spec/scrapers/download_spec.rb
199
+ - spec/scrapers/gocomics_spec.rb
200
+ - spec/scrapers/imgur_spec.rb
201
+ - spec/scrapers/nasa_apod_spec.rb
202
+ - spec/scrapers_spec.rb
203
+ - spec/spec_helper.rb