extract phrasal verbs

epv.py

#!/usr/bin/env python
import pprint
import json
import corenlp

corenlp_dir = "/tmp/stanford-corenlp-full-2013-06-20"
parser = corenlp.StanfordCoreNLP(corenlp_path=corenlp_dir)

result_json = json.loads(parser.parse("hey shut down the station"))
pprint.pprint(result_json)

output

➜  /tmp  ./test.py
{u'sentences': [{u'dependencies': [[u'nsubj', u'shut', u'hey'],
                                   [u'root', u'ROOT', u'shut'],
                                   [u'prt', u'shut', u'down'],
                                   [u'det', u'station', u'the'],
                                   [u'dobj', u'shut', u'station']],
                 u'indexeddependencies': [[u'nsubj', u'shut-2', u'hey-1'],
                                          [u'root', u'ROOT-0', u'shut-2'],
                                          [u'prt', u'shut-2', u'down-3'],
                                          [u'det', u'station-5', u'the-4'],
                                          [u'dobj',
                                           u'shut-2',
                                           u'station-5']],
                 u'parsetree': u'(ROOT (S (NP (NN hey)) (VP (VBD shut) (PRT (RP down)) (NP (DT the) (NN station)))))',
                 u'text': u'hey shut down the station',
                 u'words': [[u'hey',
                             {u'CharacterOffsetBegin': u'0',
                              u'CharacterOffsetEnd': u'3',
                              u'Lemma': u'hey',
                              u'NamedEntityTag': u'O',
                              u'PartOfSpeech': u'NN'}],
                            [u'shut',
                             {u'CharacterOffsetBegin': u'4',
                              u'CharacterOffsetEnd': u'8',
                              u'Lemma': u'shut',
                              u'NamedEntityTag': u'O',
                              u'PartOfSpeech': u'VBD'}],
                            [u'down',
                             {u'CharacterOffsetBegin': u'9',
                              u'CharacterOffsetEnd': u'13',
                              u'Lemma': u'down',
                              u'NamedEntityTag': u'O',
                              u'PartOfSpeech': u'RP'}],
                            [u'the',
                             {u'CharacterOffsetBegin': u'14',
                              u'CharacterOffsetEnd': u'17',
                              u'Lemma': u'the',
                              u'NamedEntityTag': u'O',
                              u'PartOfSpeech': u'DT'}],
                            [u'station',
                             {u'CharacterOffsetBegin': u'18',
                              u'CharacterOffsetEnd': u'25',
                              u'Lemma': u'station',
                              u'NamedEntityTag': u'O',
                              u'PartOfSpeech': u'NN'}]]}]}