def run(self, keywords=[]):
if not keywords:
# Check if file exists
if not os.path.isfile(self.default_keyword_file):
return False
else:
keywords = []
fp = open(self.default_keyword_file, "r")
for line in fp.readlines():
keywords.append(line.strip())
fp.close()
self.keywords = keywords
print "Using Keywords:{0}".format(self.keywords)
try:
# Get the hits for the given keywords
bing = PyBingSearch(BING_API_KEY)
for keyword in self.keywords:
print "KEYWORD:{0}".format(keyword)
result_list, next_uri = bing.search(keyword,
limit=self.maxResuts,
format='json')
for result in result_list:
url = result.url
print "Found URL:{0}".format(url)
self.urls.append(url)
except:
print "Something went wrong querying Bing."
pass
return True
def bing_search(query):
bing = PyBingSearch('rLSasvRW9cvlU5fG9hoSGjJG2M1eIjR+Ld27nFC9Pj8=')
buildquery = query.replace(',', ' ')
result_list = bing.search_all(query, limit=10, format='json')
bingurls = []
for result in result_list:
bingurls.append(result.url)
return bingurls
def bingSearch(self, numresult=10):
bing = PyBingSearch(self.bing_api_key)
results, next_uri = bing.search(self.query,
limit=numresult,
format='json')
res = []
for i in range(numresult):
res += [results[i].url]
return res
def GetLinksForQueryBing(query):
bing = PyBingSearch('3Bybyj2qcK/w5FXbBqBUjI9MajN51efC2uYldmzvvnY')
try:
result_list = bing.search_all(query, limit=20, format='json')
except PyBingException:
return []
results = [result.url for result in result_list]
results = results[:min(20, len(results))]
return [r for r in results if r.find("youtube") == -1]
def bingSearch(link, limit=4):
#Sanitize input
try:
linkfile = link.replace("^", "|")
bing=PyBingSearch('MsYC/eW39AiaY9EYFIC8mlX8C7HPRRooagMKRwVZx7Q')
try: result_list, next_uri = bing.search(linkfile, limit, format='json')
except: result_list, next_uri = bing.search(linkfile.replace(" news", ""), limit, format='json')
returning=[]
for i in xrange(limit):
try: returning.append(result_list[i].url.encode('utf8'))
except: break
return returning
except: return [link.replace(" news", "")]
def getTopTen():
global query
global pagesToBeCrawled
global fb
bing = PyBingSearch('mMlCxUd5qmU5uDJ1w1VLbDkobVK905A9cZZhYkfqGHg=')
query = raw_input("Enter a search query ")
pagesToBeCrawled = input("Enter the number of pages you would like to be crawled? ")
fp.write('****************************The query searched for is:' + query + ", pages to be crawled: " + str(pagesToBeCrawled) + '\n')
urlList, next_uri = bing.search(query, limit=10, format='json') # get the results
for result in urlList:
#initialUrls.append(result); # Add the initial lists to the list
if (pages > pagesToBeCrawled):
print 'We have successfully crawled',pagesToBeCrawled,'pages'
break
checkUrl(result.url)
def bingSearch(linkfile):
print "\nCalling bingSearch with arguments linkfile: {}:".format(str(linkfile))
#Sanitize input
linkfile = linkfile.replace("^", "|")
bing=PyBingSearch('XXXXX')
#Get from bing:
result_list, next_uri = bing.search(linkfile, limit=5, format='json')
#result_list, next_uri = bing.search("Python Software Foundation", limit=50, format='json')
result_list[0].description #first bing result
file = open( 'bingResults.txt', 'w')
for res in result_list:
file.write('"' + res.url + '" ')
break
print "\nbingSearch complete"
return str(result_list[0].url)
def GetLinksForQueryBing(query):
#service = build("customsearch", "v1",
# developerKey="AIzaSyDBh9qkTpuXSWbsjCfnCTQJFuFGKOYCElM")
#res = service.cse().list(
# q=query,
# cx='000504779742960611072:dpmv5fihhu8',
# ).execute()
#return [item['link'] for item in res['items']][:20]
try:
bing = PyBingSearch('3Bybyj2qcK/w5FXbBqBUjI9MajN51efC2uYldmzvvnY')
result_list = bing.search_all(query, limit=20, format='json')
results = [result.url for result in result_list]
except:
return None
return results[:min(20, len(results))]
def get_improved_term(query):
bing = PyBingSearch('') # Add your bing-api key here
result_list, next_url = bing.search("%s wikipedia" % query,
limit=3,
format='json')
for result in result_list:
wiki_url = result.url
wiki_desc = result.description
if "en.wikipedia" in wiki_url:
if ("may refer to" not in wiki_desc) or ("may also refer to"
not in wiki_desc):
wiki_corr_term = (wiki_url).split("/")[-1]
try:
wiki_corr_term_dec = str(
urllib.unquote(wiki_corr_term).decode('utf-8'))
return wiki_corr_term_dec
except:
pass
return query
soup = BeautifulSoup(r)
body = soup.find('body').text
body = unicodedata.normalize('NFKD', body).encode('ascii', 'ignore')
body = body.splitlines()
body = [i for i in body if i != '']
body = [x for x in body if len(x) > 70]
body = map(cut, body)
if len(body) < 5:
indexes = range(0, len(body))
else:
indexes = [randint(0, len(body) - 1) for i in range(0, 5)]
return ['"' + body[i] + '"' for i in indexes]
#Now the request
bing = PyBingSearch('1lQ7z/Ye5Qo/vuWoEuznwGUDQX841pfEkLC77SBTNCs')
#Function
def request_urls(url):
statements = rand_statements(url)
list_duplicates = []
for statement in statements:
result_list, next_uri = bing.search(statement, limit=50, format='json')
results = [
unicodedata.normalize('NFKD', result_list[i].url).encode(
'ascii', 'ignore') for i in range(0, len(result_list))
]
list_duplicates = list_duplicates + results
#Get the frequencies of each url we get
return Counter(list_duplicates).most_common()
def bingWikiSearch(self):
query = self.query.split(" ")[0] + " :wiki"
bing = PyBingSearch(self.bing_api_key)
results, next_uri = bing.search(query, limit=1, format='json')
return results[0].url
from py_bing_search import PyBingSearch
import urllib
import urllib2
import json
import os
import socket
socket.setdefaulttimeout(5)
key = '4axpjG94pE8x9yUZqveY2LObcgNLVfX5oTW6+s5JbR0'
bing = PyBingSearch('4axpjG94pE8x9yUZqveY2LObcgNLVfX5oTW6+s5JbR0')
credentialBing = 'Basic ' + (':%s' % key).encode(
'base64')[:-1] # the "-1" is to remove the trailing "\n" which encode adds
photo_directory = 'bingBad'
if not os.path.exists(photo_directory):
os.makedirs(photo_directory)
for offset in range(0, 50000, 50):
bing_search_url = "https://api.datamarket.azure.com/Bing/Search/v1/Image?Query=%27bad%20photography%27&$format=json&$top=200&$skip=" + str(
offset)
request = urllib2.Request(bing_search_url)
request.add_header('Authorization', credentialBing)
requestOpener = urllib2.build_opener()
response = requestOpener.open(request)
results = json.load(response)
for i, image in enumerate(results['d']['results']):
def GetLinksForQueryBing(query):
bing = PyBingSearch('3Bybyj2qcK/w5FXbBqBUjI9MajN51efC2uYldmzvvnY')
result_list = bing.search_all(query, limit=20, format='json')
return [result.url for result in result_list][:20]
import json
import os
import requests
import time
from collections import defaultdict
from functools import reduce
from py_bing_search import PyBingSearch
import sys
apikey = 'wtprucmwrgk6bd92rq7tun97'
edmund_url = 'http://api.edmunds.com/api/vehicle/v2/'
end_url = '?fmt=json&view=full&api_key=' + apikey
bing = PyBingSearch('Np5rmrL6fIPP3jpDqVi+Li/rJ1Joih4Q6wP69HrjQro=')
model_id = 1
make_id = 1
engine_id = 1
models_list = []
makes_list = []
engines_list = []
make_ids = {}
makes_models_dict = defaultdict(list)
makes_json = requests.get(edmund_url + 'makes' + end_url).json()
def add_engines(engine, model_id):
global engine_id
global engines_list
global models_list
from py_bing_search import PyBingSearch
bing = PyBingSearch('3Bybyj2qcK/w5FXbBqBUjI9MajN51efC2uYldmzvvnY')
result_list = bing.search_all(
"(yawn) AND (other OR early) AND (people) AND (contagious OR catching) AND (room)",
limit=50,
format='json')
print[result.url for result in result_list][:10]
# -*- coding: utf-8 -*-
__author__ = 'lufo'
from py_bing_search import PyBingSearch
bing = PyBingSearch('QkcWAM6VJ/S0LJI9wvVGN4UNQUwikMb4zY/kUVe/hAw')
result_list, next_uri = bing.search("Python Software Foundation",
limit=50,
format='json')
for result in result_list:
print result.url
