forked from AlchemyAPI/alchemyapi_python
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathalchemyapi.py
More file actions
768 lines (597 loc) · 29.5 KB
/
alchemyapi.py
File metadata and controls
768 lines (597 loc) · 29.5 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
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
90
91
92
93
94
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
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
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
#!/usr/bin/env python
# Copyright 2013 AlchemyAPI
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import print_function
import requests
try:
from urllib.request import urlopen
from urllib.parse import urlparse
from urllib.parse import urlencode
except ImportError:
from urlparse import urlparse
from urllib2 import urlopen
from urllib import urlencode
try:
import json
except ImportError:
#Older versions of Python (i.e. 2.4) require simplejson instead of json
import simplejson as json
if __name__ == '__main__':
"""
Writes the API key to api_key.txt file. It will create the file if it doesn't exist.
This function is intended to be called from the Python command line using: python alchemyapi YOUR_API_KEY
If you don't have an API key yet, register for one at: http://www.alchemyapi.com/api/register.html
INPUT:
argv[1] -> Your API key from AlchemyAPI. Should be 40 hex characters
OUTPUT:
none
"""
import sys
if len(sys.argv) == 2 and sys.argv[1]:
if len(sys.argv[1]) == 40:
#write the key to the file
f = open('api_key.txt','w')
f.write(sys.argv[1])
f.close()
print('Key: ' + sys.argv[1] + ' was written to api_key.txt')
print('You are now ready to start using AlchemyAPI. For an example, run: python example.py')
else:
print('The key appears to invalid. Please make sure to use the 40 character key assigned by AlchemyAPI')
class AlchemyAPI:
#Setup the endpoints
ENDPOINTS = {}
ENDPOINTS['sentiment'] = {}
ENDPOINTS['sentiment']['url'] = '/url/URLGetTextSentiment'
ENDPOINTS['sentiment']['text'] = '/text/TextGetTextSentiment'
ENDPOINTS['sentiment']['html'] = '/html/HTMLGetTextSentiment'
ENDPOINTS['sentiment_targeted'] = {}
ENDPOINTS['sentiment_targeted']['url'] = '/url/URLGetTargetedSentiment'
ENDPOINTS['sentiment_targeted']['text'] = '/text/TextGetTargetedSentiment'
ENDPOINTS['sentiment_targeted']['html'] = '/html/HTMLGetTargetedSentiment'
ENDPOINTS['author'] = {}
ENDPOINTS['author']['url'] = '/url/URLGetAuthor'
ENDPOINTS['author']['html'] = '/html/HTMLGetAuthor'
ENDPOINTS['keywords'] = {}
ENDPOINTS['keywords']['url'] = '/url/URLGetRankedKeywords'
ENDPOINTS['keywords']['text'] = '/text/TextGetRankedKeywords'
ENDPOINTS['keywords']['html'] = '/html/HTMLGetRankedKeywords'
ENDPOINTS['concepts'] = {}
ENDPOINTS['concepts']['url'] = '/url/URLGetRankedConcepts'
ENDPOINTS['concepts']['text'] = '/text/TextGetRankedConcepts'
ENDPOINTS['concepts']['html'] = '/html/HTMLGetRankedConcepts'
ENDPOINTS['entities'] = {}
ENDPOINTS['entities']['url'] = '/url/URLGetRankedNamedEntities'
ENDPOINTS['entities']['text'] = '/text/TextGetRankedNamedEntities'
ENDPOINTS['entities']['html'] = '/html/HTMLGetRankedNamedEntities'
ENDPOINTS['category'] = {}
ENDPOINTS['category']['url'] = '/url/URLGetCategory'
ENDPOINTS['category']['text'] = '/text/TextGetCategory'
ENDPOINTS['category']['html'] = '/html/HTMLGetCategory'
ENDPOINTS['relations'] = {}
ENDPOINTS['relations']['url'] = '/url/URLGetRelations'
ENDPOINTS['relations']['text'] = '/text/TextGetRelations'
ENDPOINTS['relations']['html'] = '/html/HTMLGetRelations'
ENDPOINTS['language'] = {}
ENDPOINTS['language']['url'] = '/url/URLGetLanguage'
ENDPOINTS['language']['text'] = '/text/TextGetLanguage'
ENDPOINTS['language']['html'] = '/html/HTMLGetLanguage'
ENDPOINTS['text'] = {}
ENDPOINTS['text']['url'] = '/url/URLGetText'
ENDPOINTS['text']['html'] = '/html/HTMLGetText'
ENDPOINTS['text_raw'] = {}
ENDPOINTS['text_raw']['url'] = '/url/URLGetRawText'
ENDPOINTS['text_raw']['html'] = '/html/HTMLGetRawText'
ENDPOINTS['title'] = {}
ENDPOINTS['title']['url'] = '/url/URLGetTitle'
ENDPOINTS['title']['html'] = '/html/HTMLGetTitle'
ENDPOINTS['feeds'] = {}
ENDPOINTS['feeds']['url'] = '/url/URLGetFeedLinks'
ENDPOINTS['feeds']['html'] = '/html/HTMLGetFeedLinks'
ENDPOINTS['microformats'] = {}
ENDPOINTS['microformats']['url'] = '/url/URLGetMicroformatData'
ENDPOINTS['microformats']['html'] = '/html/HTMLGetMicroformatData'
ENDPOINTS['combined'] = {}
ENDPOINTS['combined']['url'] = '/url/URLGetCombinedData'
ENDPOINTS['combined']['text'] = '/text/TextGetCombinedData'
ENDPOINTS['image'] = {}
ENDPOINTS['image']['url'] = '/url/URLGetImage'
ENDPOINTS['imagetagging'] = {}
ENDPOINTS['imagetagging']['url'] = '/url/URLGetRankedImageKeywords'
ENDPOINTS['imagetagging']['image'] = '/image/ImageGetRankedImageKeywords'
ENDPOINTS['taxonomy'] = {}
ENDPOINTS['taxonomy']['url'] = '/url/URLGetRankedTaxonomy'
ENDPOINTS['taxonomy']['html'] = '/html/HTMLGetRankedTaxonomy'
ENDPOINTS['taxonomy']['text'] = '/text/TextGetRankedTaxonomy'
#The base URL for all endpoints
BASE_URL = 'http://access.alchemyapi.com/calls'
def __init__(self):
"""
Initializes the SDK so it can send requests to AlchemyAPI for analysis.
It loads the API key from api_key.txt and configures the endpoints.
"""
import sys
try:
# Open the key file and read the key
f = open("api_key.txt", "r")
key = f.read().strip()
if key == '':
#The key file should't be blank
print('The api_key.txt file appears to be blank, please run: python alchemyapi.py YOUR_KEY_HERE')
print('If you do not have an API Key from AlchemyAPI, please register for one at: http://www.alchemyapi.com/api/register.html')
sys.exit(0)
elif len(key) != 40:
#Keys should be exactly 40 characters long
print('It appears that the key in api_key.txt is invalid. Please make sure the file only includes the API key, and it is the correct one.')
sys.exit(0)
else:
#setup the key
self.apikey = key
# Close file
f.close()
except IOError:
#The file doesn't exist, so show the message and create the file.
print('API Key not found! Please run: python alchemyapi.py YOUR_KEY_HERE')
print('If you do not have an API Key from AlchemyAPI, please register for one at: http://www.alchemyapi.com/api/register.html')
#create a blank key file
open('api_key.txt', 'a').close()
sys.exit(0)
except Exception as e:
print(e)
def entities(self, flavor, data, options={}):
"""
Extracts the entities for text, a URL or HTML.
For an overview, please refer to: http://www.alchemyapi.com/products/features/entity-extraction/
For the docs, please refer to: http://www.alchemyapi.com/api/entity-extraction/
INPUT:
flavor -> which version of the call, i.e. text, url or html.
data -> the data to analyze, either the text, the url or html code.
options -> various parameters that can be used to adjust how the API works, see below for more info on the available options.
Available Options:
disambiguate -> disambiguate entities (i.e. Apple the company vs. apple the fruit). 0: disabled, 1: enabled (default)
linkedData -> include linked data on disambiguated entities. 0: disabled, 1: enabled (default)
coreference -> resolve coreferences (i.e. the pronouns that correspond to named entities). 0: disabled, 1: enabled (default)
quotations -> extract quotations by entities. 0: disabled (default), 1: enabled.
sentiment -> analyze sentiment for each entity. 0: disabled (default), 1: enabled. Requires 1 additional API transction if enabled.
showSourceText -> 0: disabled (default), 1: enabled
maxRetrieve -> the maximum number of entities to retrieve (default: 50)
OUTPUT:
The response, already converted from JSON to a Python object.
"""
#Make sure this request supports this flavor
if flavor not in AlchemyAPI.ENDPOINTS['entities']:
return { 'status':'ERROR', 'statusInfo':'entity extraction for ' + flavor + ' not available' }
#add the data to the options and analyze
options[flavor] = data
return self.__analyze(AlchemyAPI.ENDPOINTS['entities'][flavor], options)
def keywords(self, flavor, data, options={}):
"""
Extracts the keywords from text, a URL or HTML.
For an overview, please refer to: http://www.alchemyapi.com/products/features/keyword-extraction/
For the docs, please refer to: http://www.alchemyapi.com/api/keyword-extraction/
INPUT:
flavor -> which version of the call, i.e. text, url or html.
data -> the data to analyze, either the text, the url or html code.
options -> various parameters that can be used to adjust how the API works, see below for more info on the available options.
Available Options:
keywordExtractMode -> normal (default), strict
sentiment -> analyze sentiment for each keyword. 0: disabled (default), 1: enabled. Requires 1 additional API transaction if enabled.
showSourceText -> 0: disabled (default), 1: enabled.
maxRetrieve -> the max number of keywords returned (default: 50)
OUTPUT:
The response, already converted from JSON to a Python object.
"""
#Make sure this request supports this flavor
if flavor not in AlchemyAPI.ENDPOINTS['keywords']:
return { 'status':'ERROR', 'statusInfo':'keyword extraction for ' + flavor + ' not available' }
#add the data to the options and analyze
options[flavor] = data
return self.__analyze(AlchemyAPI.ENDPOINTS['keywords'][flavor], options)
def concepts(self, flavor, data, options={}):
"""
Tags the concepts for text, a URL or HTML.
For an overview, please refer to: http://www.alchemyapi.com/products/features/concept-tagging/
For the docs, please refer to: http://www.alchemyapi.com/api/concept-tagging/
Available Options:
maxRetrieve -> the maximum number of concepts to retrieve (default: 8)
linkedData -> include linked data, 0: disabled, 1: enabled (default)
showSourceText -> 0:disabled (default), 1: enabled
OUTPUT:
The response, already converted from JSON to a Python object.
"""
#Make sure this request supports this flavor
if flavor not in AlchemyAPI.ENDPOINTS['concepts']:
return { 'status':'ERROR', 'statusInfo':'concept tagging for ' + flavor + ' not available' }
#add the data to the options and analyze
options[flavor] = data
return self.__analyze(AlchemyAPI.ENDPOINTS['concepts'][flavor], options)
def sentiment(self, flavor, data, options={}):
"""
Calculates the sentiment for text, a URL or HTML.
For an overview, please refer to: http://www.alchemyapi.com/products/features/sentiment-analysis/
For the docs, please refer to: http://www.alchemyapi.com/api/sentiment-analysis/
INPUT:
flavor -> which version of the call, i.e. text, url or html.
data -> the data to analyze, either the text, the url or html code.
options -> various parameters that can be used to adjust how the API works, see below for more info on the available options.
Available Options:
showSourceText -> 0: disabled (default), 1: enabled
OUTPUT:
The response, already converted from JSON to a Python object.
"""
#Make sure this request supports this flavor
if flavor not in AlchemyAPI.ENDPOINTS['sentiment']:
return { 'status':'ERROR', 'statusInfo':'sentiment analysis for ' + flavor + ' not available' }
#add the data to the options and analyze
options[flavor] = data
return self.__analyze(AlchemyAPI.ENDPOINTS['sentiment'][flavor], options)
def sentiment_targeted(self, flavor, data, target, options={}):
"""
Calculates the targeted sentiment for text, a URL or HTML.
For an overview, please refer to: http://www.alchemyapi.com/products/features/sentiment-analysis/
For the docs, please refer to: http://www.alchemyapi.com/api/sentiment-analysis/
INPUT:
flavor -> which version of the call, i.e. text, url or html.
data -> the data to analyze, either the text, the url or html code.
target -> the word or phrase to run sentiment analysis on.
options -> various parameters that can be used to adjust how the API works, see below for more info on the available options.
Available Options:
showSourceText -> 0: disabled, 1: enabled
OUTPUT:
The response, already converted from JSON to a Python object.
"""
#Make sure the target is valid
if target is None or target == '':
return { 'status':'ERROR', 'statusInfo':'targeted sentiment requires a non-null target' }
#Make sure this request supports this flavor
if flavor not in AlchemyAPI.ENDPOINTS['sentiment_targeted']:
return { 'status':'ERROR', 'statusInfo':'targeted sentiment analysis for ' + flavor + ' not available' }
#add the URL encoded data and target to the options and analyze
options[flavor] = data
options['target'] = target
return self.__analyze(AlchemyAPI.ENDPOINTS['sentiment_targeted'][flavor], options)
def text(self, flavor, data, options={}):
"""
Extracts the cleaned text (removes ads, navigation, etc.) for text, a URL or HTML.
For an overview, please refer to: http://www.alchemyapi.com/products/features/text-extraction/
For the docs, please refer to: http://www.alchemyapi.com/api/text-extraction/
INPUT:
flavor -> which version of the call, i.e. text, url or html.
data -> the data to analyze, either the text, the url or html code.
options -> various parameters that can be used to adjust how the API works, see below for more info on the available options.
Available Options:
useMetadata -> utilize meta description data, 0: disabled, 1: enabled (default)
extractLinks -> include links, 0: disabled (default), 1: enabled.
OUTPUT:
The response, already converted from JSON to a Python object.
"""
#Make sure this request supports this flavor
if flavor not in AlchemyAPI.ENDPOINTS['text']:
return { 'status':'ERROR', 'statusInfo':'clean text extraction for ' + flavor + ' not available' }
#add the data to the options and analyze
options[flavor] = data
return self.__analyze(AlchemyAPI.ENDPOINTS['text'][flavor], options)
def text_raw(self, flavor, data, options={}):
"""
Extracts the raw text (includes ads, navigation, etc.) for a URL or HTML.
For an overview, please refer to: http://www.alchemyapi.com/products/features/text-extraction/
For the docs, please refer to: http://www.alchemyapi.com/api/text-extraction/
INPUT:
flavor -> which version of the call, i.e. text, url or html.
data -> the data to analyze, either the text, the url or html code.
options -> various parameters that can be used to adjust how the API works, see below for more info on the available options.
Available Options:
none
OUTPUT:
The response, already converted from JSON to a Python object.
"""
#Make sure this request supports this flavor
if flavor not in AlchemyAPI.ENDPOINTS['text_raw']:
return { 'status':'ERROR', 'statusInfo':'raw text extraction for ' + flavor + ' not available' }
#add the data to the options and analyze
options[flavor] = data
return self.__analyze(AlchemyAPI.ENDPOINTS['text_raw'][flavor], options)
def author(self, flavor, data, options={}):
"""
Extracts the author from a URL or HTML.
For an overview, please refer to: http://www.alchemyapi.com/products/features/author-extraction/
For the docs, please refer to: http://www.alchemyapi.com/api/author-extraction/
INPUT:
flavor -> which version of the call, i.e. text, url or html.
data -> the data to analyze, either the text, the url or html code.
options -> various parameters that can be used to adjust how the API works, see below for more info on the available options.
Availble Options:
none
OUTPUT:
The response, already converted from JSON to a Python object.
"""
#Make sure this request supports this flavor
if flavor not in AlchemyAPI.ENDPOINTS['author']:
return { 'status':'ERROR', 'statusInfo':'author extraction for ' + flavor + ' not available' }
#add the data to the options and analyze
options[flavor] = data
return self.__analyze(AlchemyAPI.ENDPOINTS['author'][flavor], options)
def language(self, flavor, data, options={}):
"""
Detects the language for text, a URL or HTML.
For an overview, please refer to: http://www.alchemyapi.com/api/language-detection/
For the docs, please refer to: http://www.alchemyapi.com/products/features/language-detection/
INPUT:
flavor -> which version of the call, i.e. text, url or html.
data -> the data to analyze, either the text, the url or html code.
options -> various parameters that can be used to adjust how the API works, see below for more info on the available options.
Available Options:
none
OUTPUT:
The response, already converted from JSON to a Python object.
"""
#Make sure this request supports this flavor
if flavor not in AlchemyAPI.ENDPOINTS['language']:
return { 'status':'ERROR', 'statusInfo':'language detection for ' + flavor + ' not available' }
#add the data to the options and analyze
options[flavor] = data
return self.__analyze(AlchemyAPI.ENDPOINTS['language'][flavor], options)
def title(self, flavor, data, options={}):
"""
Extracts the title for a URL or HTML.
For an overview, please refer to: http://www.alchemyapi.com/products/features/text-extraction/
For the docs, please refer to: http://www.alchemyapi.com/api/text-extraction/
INPUT:
flavor -> which version of the call, i.e. text, url or html.
data -> the data to analyze, either the text, the url or html code.
options -> various parameters that can be used to adjust how the API works, see below for more info on the available options.
Available Options:
useMetadata -> utilize title info embedded in meta data, 0: disabled, 1: enabled (default)
OUTPUT:
The response, already converted from JSON to a Python object.
"""
#Make sure this request supports this flavor
if flavor not in AlchemyAPI.ENDPOINTS['title']:
return { 'status':'ERROR', 'statusInfo':'title extraction for ' + flavor + ' not available' }
#add the data to the options and analyze
options[flavor] = data
return self.__analyze(AlchemyAPI.ENDPOINTS['title'][flavor], options)
def relations(self, flavor, data, options={}):
"""
Extracts the relations for text, a URL or HTML.
For an overview, please refer to: http://www.alchemyapi.com/products/features/relation-extraction/
For the docs, please refer to: http://www.alchemyapi.com/api/relation-extraction/
INPUT:
flavor -> which version of the call, i.e. text, url or html.
data -> the data to analyze, either the text, the url or html code.
options -> various parameters that can be used to adjust how the API works, see below for more info on the available options.
Available Options:
sentiment -> 0: disabled (default), 1: enabled. Requires one additional API transaction if enabled.
keywords -> extract keywords from the subject and object. 0: disabled (default), 1: enabled. Requires one additional API transaction if enabled.
entities -> extract entities from the subject and object. 0: disabled (default), 1: enabled. Requires one additional API transaction if enabled.
requireEntities -> only extract relations that have entities. 0: disabled (default), 1: enabled.
sentimentExcludeEntities -> exclude full entity name in sentiment analysis. 0: disabled, 1: enabled (default)
disambiguate -> disambiguate entities (i.e. Apple the company vs. apple the fruit). 0: disabled, 1: enabled (default)
linkedData -> include linked data with disambiguated entities. 0: disabled, 1: enabled (default).
coreference -> resolve entity coreferences. 0: disabled, 1: enabled (default)
showSourceText -> 0: disabled (default), 1: enabled.
maxRetrieve -> the maximum number of relations to extract (default: 50, max: 100)
OUTPUT:
The response, already converted from JSON to a Python object.
"""
#Make sure this request supports this flavor
if flavor not in AlchemyAPI.ENDPOINTS['relations']:
return { 'status':'ERROR', 'statusInfo':'relation extraction for ' + flavor + ' not available' }
#add the data to the options and analyze
options[flavor] = data
return self.__analyze(AlchemyAPI.ENDPOINTS['relations'][flavor], options)
def category(self, flavor, data, options={}):
"""
Categorizes the text for text, a URL or HTML.
For an overview, please refer to: http://www.alchemyapi.com/products/features/text-categorization/
For the docs, please refer to: http://www.alchemyapi.com/api/text-categorization/
INPUT:
flavor -> which version of the call, i.e. text, url or html.
data -> the data to analyze, either the text, the url or html code.
options -> various parameters that can be used to adjust how the API works, see below for more info on the available options.
Available Options:
showSourceText -> 0: disabled (default), 1: enabled
OUTPUT:
The response, already converted from JSON to a Python object.
"""
#Make sure this request supports this flavor
if flavor not in AlchemyAPI.ENDPOINTS['category']:
return { 'status':'ERROR', 'statusInfo':'text categorization for ' + flavor + ' not available' }
#add the data to the options and analyze
options[flavor] = data
return self.__analyze(AlchemyAPI.ENDPOINTS['category'][flavor], options)
def feeds(self, flavor, data, options={}):
"""
Detects the RSS/ATOM feeds for a URL or HTML.
For an overview, please refer to: http://www.alchemyapi.com/products/features/feed-detection/
For the docs, please refer to: http://www.alchemyapi.com/api/feed-detection/
INPUT:
flavor -> which version of the call, i.e. url or html.
data -> the data to analyze, either the the url or html code.
options -> various parameters that can be used to adjust how the API works, see below for more info on the available options.
Available Options:
none
OUTPUT:
The response, already converted from JSON to a Python object.
"""
#Make sure this request supports this flavor
if flavor not in AlchemyAPI.ENDPOINTS['feeds']:
return { 'status':'ERROR', 'statusInfo':'feed detection for ' + flavor + ' not available' }
#add the data to the options and analyze
options[flavor] = data
return self.__analyze(AlchemyAPI.ENDPOINTS['feeds'][flavor], options)
def microformats(self, flavor, data, options={}):
"""
Parses the microformats for a URL or HTML.
For an overview, please refer to: http://www.alchemyapi.com/products/features/microformats-parsing/
For the docs, please refer to: http://www.alchemyapi.com/api/microformats-parsing/
INPUT:
flavor -> which version of the call, i.e. url or html.
data -> the data to analyze, either the the url or html code.
options -> various parameters that can be used to adjust how the API works, see below for more info on the available options.
Available Options:
none
OUTPUT:
The response, already converted from JSON to a Python object.
"""
#Make sure this request supports this flavor
if flavor not in AlchemyAPI.ENDPOINTS['microformats']:
return { 'status':'ERROR', 'statusInfo':'microformat extraction for ' + flavor + ' not available' }
#add the data to the options and analyze
options[flavor] = data
return self.__analyze(AlchemyAPI.ENDPOINTS['microformats'][flavor], options)
def imageExtraction(self, flavor, data, options={}):
"""
Extracts main image from a URL
INPUT:
flavor -> which version of the call (url only currently).
data -> URL to analyze
options -> various parameters that can be used to adjust how the API works,
see below for more info on the available options.
Available Options:
extractMode ->
trust-metadata : (less CPU intensive, less accurate)
always-infer : (more CPU intensive, more accurate)
OUTPUT:
The response, already converted from JSON to a Python object.
"""
if flavor not in AlchemyAPI.ENDPOINTS['image']:
return { 'status':'ERROR', 'statusInfo':'image extraction for ' + flavor + ' not available' }
options[flavor] = data
return self.__analyze(AlchemyAPI.ENDPOINTS['image'][flavor], options)
def taxonomy(self, flavor, data, options={}):
"""
Taxonomy classification operations.
INPUT:
flavor -> which version of the call, i.e. url or html.
data -> the data to analyze, either the the url or html code.
options -> various parameters that can be used to adjust how the API works, see below for more info on the available options.
Available Options:
showSourceText ->
include the original 'source text' the taxonomy categories were extracted from within the API response
Possible values:
1 - enabled
0 - disabled (default)
sourceText ->
where to obtain the text that will be processed by this API call.
AlchemyAPI supports multiple modes of text extraction:
web page cleaning (removes ads, navigation links, etc.), raw text extraction
(processes all web page text, including ads / nav links), visual constraint queries, and XPath queries.
Possible values:
cleaned_or_raw : cleaning enabled, fallback to raw when cleaning produces no text (default)
cleaned : operate on 'cleaned' web page text (web page cleaning enabled)
raw : operate on raw web page text (web page cleaning disabled)
cquery : operate on the results of a visual constraints query
Note: The 'cquery' http argument must also be set to a valid visual constraints query.
xpath : operate on the results of an XPath query
Note: The 'xpath' http argument must also be set to a valid XPath query.
cquery ->
a visual constraints query to apply to the web page.
xpath ->
an XPath query to apply to the web page.
baseUrl ->
rel-tag output base http url (must be uri-argument encoded)
OUTPUT:
The response, already converted from JSON to a Python object.
"""
if flavor not in AlchemyAPI.ENDPOINTS['taxonomy']:
return { 'status':'ERROR', 'statusInfo':'taxonomy for ' + flavor + ' not available' }
options[flavor] = data
return self.__analyze(AlchemyAPI.ENDPOINTS['taxonomy'][flavor], options)
def combined(self, flavor, data, options={}):
"""
Combined call for page-image, entity, keyword, title, author, taxonomy, concept.
INPUT:
flavor -> which version of the call, i.e. url or html.
data -> the data to analyze, either the the url or html code.
options -> various parameters that can be used to adjust how the API works, see below for more info on the available options.
Available Options:
extract ->
Possible values: page-image, entity, keyword, title, author, taxonomy, concept
default : entity, keyword, taxonomy, concept
disambiguate ->
disambiguate detected entities
Possible values:
1 : enabled (default)
0 : disabled
linkedData ->
include Linked Data content links with disambiguated entities
Possible values :
1 : enabled (default)
0 : disabled
coreference ->
resolve he/she/etc coreferences into detected entities
Possible values:
1 : enabled (default)
0 : disabled
quotations ->
enable quotations extraction
Possible values:
1 : enabled
0 : disabled (default)
sentiment ->
enable entity-level sentiment analysis
Possible values:
1 : enabled
0 : disabled (default)
showSourceText ->
include the original 'source text' the entities were extracted from within the API response
Possible values:
1 : enabled
0 : disabled (default)
maxRetrieve ->
maximum number of named entities to extract
default : 50
baseUrl ->
rel-tag output base http url
OUTPUT:
The response, already converted from JSON to a Python object.
"""
if flavor not in AlchemyAPI.ENDPOINTS['combined']:
return { 'status':'ERROR', 'statusInfo':'combined for ' + flavor + ' not available' }
options[flavor] = data
return self.__analyze(AlchemyAPI.ENDPOINTS['combined'][flavor], options)
def imageTagging(self, flavor, data, options={}):
"""
INPUT:
flavor -> which version of the call only url or image.
data -> the data to analyze, either the the url or path to image.
options -> various parameters that can be used to adjust how the API works, see below for more info on the available options.
"""
if flavor not in AlchemyAPI.ENDPOINTS['imagetagging']:
return { 'status':'ERROR', 'statusInfo':'imagetagging for ' + flavor + ' not available' }
elif 'image' == flavor:
image = open(data, 'rb').read()
options['imagePostMode'] = 'raw'
return self.__analyze(AlchemyAPI.ENDPOINTS['imagetagging'][flavor], options, image)
options[flavor] = data
return self.__analyze(AlchemyAPI.ENDPOINTS['imagetagging'][flavor], options)
def __analyze(self, endpoint, params, post_data=bytearray()):
"""
HTTP Request wrapper that is called by the endpoint functions. This function is not intended to be called through an external interface.
It makes the call, then converts the returned JSON string into a Python object.
INPUT:
url -> the full URI encoded url
OUTPUT:
The response, already converted from JSON to a Python object.
"""
#Add the API Key and set the output mode to JSON
params['apikey'] = self.apikey;
params['outputMode'] = 'json';
#Insert the base url
post_url = AlchemyAPI.BASE_URL + endpoint + '?' + urlencode(params).encode('utf-8');
try:
return requests.post(url=post_url, data=post_data).json()
except Exception as e:
print(e)
return { 'status':'ERROR', 'statusInfo':'network-error' }