def get_keywords(documents, text_accessor=lambda x: x):
alchemy_api = AlchemyAPI()
keywords = []
for document in documents:
response = alchemy_api.keywords('text', text_accessor(document), {'sentiment': 1})
if response['status'] == 'OK':
keywords.append(set(map(lambda x: x['text'], response['keywords'])))
else:
keywords.append(set())
print('Error in keyword extraction call')
return keywords
def main():
from alchemyapi.alchemyapi import AlchemyAPI
# Extract text from a webpage for analysis
url = 'http://www.bloombergview.com/articles/2014-09-26/the-secret-goldman-sachs-tapes'
article = Webpage(url)
text = article.get_text()
# Extract keywords
alchemyapi = AlchemyAPI()
output = alchemyapi.keywords('text', text)
keywords = parse_keyword_output(output)
keywords.sort(reverse=True)
# Print to console
print('\nThe URL used for this assignment is:\n\n%s\n' % url)
print_keywords(keywords[:10])
class AlchemyApiService(object):
def __init__(self):
self.alchemy_api = AlchemyAPI()
def get_keywords(self, text):
# TODO(simplyfaisal): Refine error handling logic.
try:
response = self.alchemy_api.keywords('text', text, {'sentiment': 1})
if response['status'] == 'OK':
return response['keywords']
else:
print ('Error in keyword extraction')
print response
except Exception as e:
print e
return []
print(str(divText.div.strong.prettify) + " AUTHOR NAME TEST")
print(str(divText.div.blockquote.prettify) + " QUOTE TEXT TEST")
def build_quotes(TextSoup):
divText = TextSoup.find("div", {"id": "main_body"} , {"class": "right"})
Allauthors = []
Allquotes = []
for tag in divText:
author = tag.find('strong')
if author not in (-1, None):
Allauthors.append(author.contents)
quotes = tag.find('blockquote')
if quotes not in (-1, None):
quote = quotes.findAll('p', text = True)
Allquotes.append(quote)
print(str(Allauthors[0]) + str(Allquotes[0]) + "FIRST QUOTE - RESULTS TEST")
return(Allquotes)
Allquotes = build_quotes(soup)
alchemyapi = AlchemyAPI()
response = alchemyapi.keywords('text', Allquotes)
keywords = response.values()
keywords = keywords[2]
print(str(keywords[0]) + " KEYWORD SLICE CHECK")
df = pd.DataFrame(keywords)
df.index = df.index + 1
print df[0:10]
from alchemyapi.alchemyapi import AlchemyAPI
from json import load, dump
import time
songs = load(open('lyrics.json'))
alchemyapi = AlchemyAPI()
keywords = {}
for song in songs:
response = alchemyapi.keywords('text', songs[song])
for k in [ c['text'] for c in response['keywords'] ]:
if k not in keywords:
keywords[k] = []
keywords[k].append(song)
dump(keywords, open('keywords.json', 'w'))
alchemyapi = AlchemyAPI()
songs = Counter()
print ' Analysing: %s ' % (d['feed']['subtitle'])
count = len(d['entries'])
i = 0.0
stdout.write(' Working: 0%')
for t in d['entries']:
i += 1
title = t['title']
url = t['link']
if 'VIDEO:' not in title and 'AUDIO:' not in title:
response = alchemyapi.keywords('url', url)
if response['status'] == 'OK':
for w in response['keywords']:
w = w['text']
if w in keywords and w != 'page':
for s in keywords[w]:
songs[s] += 1
else:
print "\n%s: %s" % (response['status'], response['statusInfo'])
exit(1)
stdout.write('\b'*4 + '%3d%%' % ((i / count) * 100))
stdout.flush()
