def googleSearch(self):
#Query can be site specific-> site:link word
google = GoogleSearch(self.query)
ct = GoogleSearch(self.query).count()
print "No. Of Google Results: %d" % (ct)
results = google.top_urls()
return results
def Search(paper):
gs = GoogleSearch(paper + " ieeexplore.ieee.org")
url = gs.top_urls()[0]
artNumber = [word for word in url.split("=")][-1]
return artNumber
def Search(paper):
gs = GoogleSearch(paper + " ieeexplore.ieee.org")
url = gs.top_urls()[0]
artNumber = [word for word in url.split("=")][-1]
return artNumber
from openpyxl import Workbook, load_workbook
from googlesearch import GoogleSearch
wb = load_workbook('Attendees.xlsx')
for sheet in wb:
ws = wb[sheet.title]
for i in range(1, 290):
nameCell = ws.cell(row=i, column=1)
jobCell = ws.cell(row=i, column=3)
search = str(nameCell.value) + " " + str(jobCell.value) + " email"
gs = GoogleSearch(search)
print search
print gs.top_urls()[0]
print("\n")
def url_search(query, lucky=True):
gs = GoogleSearch(query)
try:
return [gs.top_url()] if lucky else gs.top_urls()
except ProxyError:
raise ValueError
from openpyxl import Workbook, load_workbook
from googlesearch import GoogleSearch
wb = load_workbook('Attendees.xlsx')
for sheet in wb:
ws = wb[sheet.title]
for i in range(1, 290):
nameCell = ws.cell(row=i, column=1)
jobCell = ws.cell(row=i, column=3)
search = str(nameCell.value) + " " + str(jobCell.value) + " email"
gs = GoogleSearch(search)
print search
print gs.top_urls()[0]
print("\n")
def get_url_by_name(name,elem):
gs = GoogleSearch('site:goodreads.com/{0}/show {1}'.format(elem,name))
for url in gs.top_urls():
if 'goodreads.com/{0}/show'.format(elem) in url:
return str(url)
return int(0)
from googlesearch import GoogleSearch
from readability.readability import Document
from bs4 import BeautifulSoup
import re
import sys
import requests
import urllib
def remove_non_ascii(text):
return ''.join(i for i in text if ord(i)<128)
if __name__ == "__main__":
if len(sys.argv) < 2:
print 'no urls found'
sys.exit(0)
query = ''
for i in range (1,len(sys.argv)):
query += sys.argv[i] + ' '
gs = GoogleSearch(query)
if len(gs.top_urls()) < 1:
print 'no urls found'
sys.exit(0)
urls = gs.top_urls()
# for url in urls:
# print url
html = urllib.urlopen(urls[0]).read()
soup = BeautifulSoup(Document(html).summary(), "lxml")
print remove_non_ascii(soup.get_text()[0:1000])
