def queryYahoo(self, query):
from yahoo.search.web import WebSearch
srch = WebSearch(config.yahoo_appid, query=query, results=self.count)
dom = srch.get_results()
results = srch.parse_results(dom)
for res in results:
url = res.Url
yield url
def queryYahoo(self, query):
from yahoo.search.web import WebSearch
srch = WebSearch(config.yahoo_appid, query=query, results=self.count)
dom = srch.get_results()
results = srch.parse_results(dom)
for res in results:
url = res.Url
yield url
class WebCorpus(object):
'''
Builds a corpus from Yahoo snippets given several
keywords.
'''
def __init__(self):
'''
Constructor
'''
self.s = WebSearch(YAHOO_API)
self.total_counts = 0
def search(self):
dom = self.s.get_results()
self.total_counts = self.total_counts + 1
return self.s.parse_results(dom)
def get_results(self, query, start=START, pages=PAGES):
self.s.query = query
self.s.start = start
self.s.results = pages
return self.search()
def get_count(self, results):
return results.total_results_available
def get_snippets(self, results):
snippets = [(res['MimeType'], res.Url, res['Summary']) for res in results]
return snippets
def get_summaries(self, query, start=START, pages=PAGES):
results = self.get_results(query, start=start, pages=pages)
snippets = get_snippets(results)
summaries = [snippets[2] for snippet in snippets]
return summaries
return n
def printSortedDict(adict):
keys = adict.keys()
keys.sort()
for k in keys:
print k
print adict[k]['Title']
print adict[k]['Url']
print adict[k]['Summary']
print " "
app_id = "NCD-Probe-Demo"
srch = WebSearch(app_id, language='en')
srch.query = "Radisson"
srch.results = 50
dom = srch.get_results()
results = srch.parse_results(dom)
ranked = {}
for res in results:
# strip out search word from summary
summary = str(res['Summary'])
stripped_summary = summary.replace('Radisson', '')
distance = ncd_probe(xbytes, cx, stripped_summary)
dstr = 'NCD: ' + str(distance)
ranked[dstr] = res
printSortedDict(ranked)
def printSortedDict(adict):
keys = adict.keys()
keys.sort()
for k in keys:
print k
print adict[k]['Title']
print adict[k]['Url']
print adict[k]['Summary']
print " "
app_id = "NCD-Probe-Demo"
srch = WebSearch(app_id, language='en')
srch.query = "Radisson"
srch.results = 50
dom = srch.get_results()
results = srch.parse_results(dom)
ranked = {}
for res in results:
# strip out search word from summary
summary = str(res['Summary'])
stripped_summary = summary.replace('Radisson', '')
distance = ncd_probe(xbytes, cx, stripped_summary)
dstr = 'NCD: ' + str(distance)
ranked[dstr] = res
printSortedDict(ranked)
