def StockKeyWords(symbol):
url = "http://www.reuters.com/finance/stocks/companyProfile?symbol=" + symbol
toBeWritten = ''
toBeWritten += symbol + ","
c = -1
try:
a = Article(url)
a.download()
a.parse()
UnicodeArticle = a.text
StringArticle = UnicodeArticle.encode('ascii', 'ignore')
StrippedArticle = StringArticle.replace('\n', '')
KeyWords = articletext.getKeywords(StrippedArticle)
for i in KeyWords:
c += 1
toBeWritten += KeyWords[c] + ' '
toBeWritten += '\n'
except Exception as ex:
template = "An exception of type {0} occured. Arguments:\n{1!r}"
message = template.format(type(ex).__name__, ex.args)
print message, symbol
#write variable to file if there are keywords
if len(KeyWords) > 1:
lock.acquire()
try:
myfile.write(toBeWritten)
finally:
lock.release()
import gethtml
import articletext
import articletrans
import getarticle
import test1
from bs4 import BeautifulSoup
import paraphrase
import googlesearch
import articletext
urls = []
topics = []
visited = []
root_topic = "news"
for googl in googlesearch.getGoogleLinks(root_topic):
urls.append(googl)
for u in urls:
mytext = articletext.getArticle(u)
keywords = articletext.getKeywords(mytext)
for k in keywords:
if k not in topics:
topics.append(k)
print mytext
#print paraphrase.getTrans("http://sparkbrowser.com")
import gethtml import articletext url="www.nytimes.com/2016/02/15/sports/westminster-dog-show-judge-is-alone-on-center-stage.html" article = articletext.getArticle(url) print articletext.getKeywords(article)
import gethtml
import articletext
url = "http://english.jagran.com/uttar-pradesh-suspense-on-priyanka-gandhis-role-for-uttar-pradesh-assembly-polls-85069"
#web_text = gethtml.getHtmlText(url)
#print articletext.getArticleText(web_text)
article = articletext.getArticle(url)
for w in articletext.getKeywords(article):
print w
