cyberandy

# Expected use >> python read-GNews.py -q [query] -l [language] -p [country] 
# The following command will search for the latest news written in German from Austria about "Redbull" 
# python read-GNews.py -q Redbull -l de -p AT
#
# Queries can be provided as strings using quotation marks >> python read-GNews.py -q "Redbull Media House" -l de
# Multiple queries can be executed at once >> python read-GNews.py -q "Redbull Media House" -q Redbull -l de -p at -p de
# The script will save a CSV file containing Title, Link, pubDate, Description, Source and Alexa Traffic Rank. 

import feedparser
import time

cyberandy

import requests
from bs4 import BeautifulSoup
import time

USER_AGENT = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36'}


def fetch_results(search_term, number_results, language_code):
    assert isinstance(search_term, str), 'Search term must be a string'
    assert isinstance(number_results, int), 'Number of results must be an integer'

cyberandy

cyberandy

import csv
import os
import requests, sys
import pandas as pd
from sumy.parsers.html import HtmlParser
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lsa import LsaSummarizer as Lsa
from sumy.summarizers.luhn import LuhnSummarizer as Luhn
from sumy.summarizers.text_rank import TextRankSummarizer as TxtRank

cyberandy

{
  "@context": "https://www.w3.org/ns/activitystreams",
  "id": "https://wordlift.io/blog/en/#website",
  "type": "http://schema.org/WebSite",
  "http://schema.org/alternateName": "SEO made simple",
  "http://schema.org/name": "WordLift Blog",
  "http://schema.org/potentialAction": {
    "type": "http://schema.org/SearchAction",
    "http://schema.org/query-input": "required name=search_term_string",
    "http://schema.org/target": "https://wordlift.io/blog/en/?s={search_term_string}"

cyberandy

[
    {
        "@context": "http://schema.org",
        "@id": "http://data.wordlift.io/[entity-name]",
        "@type": ["LodgingBusiness"],
        "description": "Here goes the description",
        "mainEntityOfPage": "https://www.happywordliftclient.com",
        "image": [
            { "@type": "ImageObject", "url": "https://www.happywordliftclient.com/wp-content/uploads/2011/07/img-19az-1200x675.jpg", "width": 1200, "height": 675 },
            { "@type": "ImageObject", "url": "https://www.happywordliftclient.com/wp-content/uploads/2011/07/img-19az-1200x900.jpg", "width": 1200, "height": 900 },

cyberandy

0-100 porsche macan
0-60 porsche macan
1 porsche cayenne
1. porsche 911
1950s porsche
1950s porsche speedster
1955 porsche 356
1956 porsche 356
1956 porsche speedster
1959 porsche

cyberandy

{
  "embeddings": [
    {
      "tensorName": "My tensor",
      "tensorShape": [
        1000,
        50
      ],
      "tensorPath": "https://gist.githubusercontent.com/cyberandy/d85af5a612c9763928542708c0ac0bf6/raw/b0c02e2f4324657ec7632e6a1e3cffc138e4a845/embeddings_vectors_porsche.tsv",
      "metadataPath": "https://gist.githubusercontent.com/cyberandy/9a629edef01df3255d1e33b9875eadc9/raw/aab52346e227428ee1cf5d85dd4f7fbf2e227918/embeddings_meta_porsche.tsv"

cyberandy

-0.5113864	0.9224017	0.8275403	0.011984834	0.76330054	0.33919206	0.28311774	0.14538139	0.7499551	-0.03052776	0.10189354	0.99692094	-1.2256945	-0.02824433	0.162615	-0.051211037	-0.41829008	0.7155175	0.14836389	0.008838273	0.8170797	0.25933984	-0.16603503	0.44063374	0.08697651	-0.24981156	0.16387565	0.09536284	-0.37290013	0.050002567	0.2126679	0.35391727	0.2208684	0.14932127	-0.13903382	-0.30882716	-0.58008456	0.067993	0.26419926	0.028330343	0.06412557	0.14603412	-0.5382476	-1.1023028	0.92313683	0.5652307	-0.5976789	-0.08452714	-0.6236737	0.13708875	-0.045952026	0.32799286	0.12108048	-1.1154692	-0.09747529	0.20141003	-0.14496945	-1.254203	-0.3187798	1.0494366	0.06164006	-0.21705215	0.14927948	-0.097200364	0.3465199	-0.42689615	0.09920918	0.19603547	-0.5898324	-0.34810644	0.72347945	-0.60483193	0.7405867	0.65496427	0.36481908	0.13829523	-1.104363	0.23256357	0.46551976	0.01618421	0.32897347	-0.45708355	-0.34825176	0.96820194	0.6563605	-0.2686824	1.2559417	-0.80211407	0.28347582	-0.053863037	0.34286124	-0.4816527	

cyberandy

wl0216/entity/artificial_intelligence
wl0216/entity/gennaro_cuofano
wl0216/entity/google
wl0216/entity/google_analytics
wl0216/entity/how_to_optimize_your_website_for_voice_search
wl0216/entity/json-ld
wl0216/entity/knowledge_graph
wl0216/entity/metadata
wl0216/entity/microdata_html
wl0216/entity/natural_language_processing