def search_abc_es(target):
target = target.replace(" ", "+")
target_split = target.split("+")
try:
url = f"https://abc.es/hemeroteca/resultos-busqueda-avanzada/todo?exa={target}"
HTML = requests.get(url).text
soup = BeautifulSoup(HTML, "html.parser")
results = soup.findAll("a",attrs={"class": "titulo"})
if results:
for r in results:
print ()
print ("|----[INFO][SPAINPRESS][ABC][>]")
print ("|--------[TITLE][>] " + er.remove_tags(str(r)))
print ("|--------[URL][>]" + r["href"])
else:
print ()
print("|----[INFO][SPAINPRESS[ABC][>] No record found...")
except Exception as e:
print ()
print (f"|----[WARNING][ABC ERROR][>] {e}")
def search_google_(target):
engine = Google()
results = engine.search("'" + target + "'")
for r in results:
print("|")
print("|----[INFO][GOOGLE][RESULTS][>] " + r["title"])
print("|----[INFO][GOOGLE][RESULTS][DESCRIPTION][>] " + r["text"])
print("|----[INFO][GOOGLE][RESULTS][LINK][>] " + r["link"])
try:
tsd, td, tsu = extract(r["link"])
domain = td + '.' + tsu
spain_newspaper = open("data/newspaper/spain-newspaper.txt", "r")
for news in spain_newspaper:
if domain == news.strip():
newspaper.news_parser(r["link"], target)
else:
if not domain in config.BL_parserPhone:
web = requests.get(r["link"], timeout=3)
if web.status_code >= 200 or web.status_code < 300:
TEXT = er.remove_tags(str(web.text))
parser.parserMAIN(TEXT)
print("|")
except Exception as e:
print("|----[ERROR][HTTP CONNECTION][>] " + str(e))
def parser_email(text):
r = re.compile(
r"[a-z0-9!#$%&'*+-/=?^_`{|}~]{1,64}@[a-zA-Z0-9]{1,255}\.[a-zA-Z0-9-]{1,24}"
)
results = r.findall(text)
if results:
for x in results:
x = er.replace_acentos(
er.remove_tags(er.replace_letras_raras(str(x))))
print("|--------[INFO][PARSER][EMAIL][>] " + x)
if len(x) < 20:
config.emailsData_list.append(x)
def parser_email(text):
r = re.compile(
r"(^[a-zA-Z0-9.!#$%&'*+/=?^_`{|}~-]+@[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(?:\.[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*$)"
)
results = r.findall(text)
if results:
for x in results:
x = er.replace_acentos(
er.remove_tags(er.replace_letras_raras(str(x))))
print("|--------[INFO][PARSER][EMAIL][>] " + x)
if len(x) < 20:
config.emailsData_list.append(x)
def searchPaginasAmarillas(nombre, a1, a2, loc):
url = "http://blancas.paginasamarillas.es/jsp/resultados.jsp?no=" + nombre + "&ap1=" + a1 + "&ap2=" + a2 + "&sec=41&pgpv=1&tbus=0&nomprov=" + loc + "&idioma=spa"
html = requests.get(url).text
soup = BeautifulSoup(html, "html.parser")
r = soup.find("div", attrs={'class': 'resul yellad yellad_ad0'})
r = er.remove_tags(str(r))
if not r == "None":
print("|----[INFO][PAGINAS AMARILLAS][>] ")
print(" - " + str(cleanPaginasAmarillas_result(r)))
else:
pass
def search_abc_es(target):
target = target.replace(" ", "+")
url = f"https://abc.es/hemeroteca/resultos-busqueda-avanzada/todo?exa={target}"
HTML = requests.get(url).text
soup = BeautifulSoup(HTML, "html.parser")
results = soup.findAll("a", attrs={"class": "titulo"})
for r in results:
print()
print("|----[INFO][SPAINPRESS][ABC][>]")
print("|--------[TITLE][>] " + er.remove_tags(str(r)))
print("|--------[URL][>]" + r["href"])
def search_google_(target):
engine = Google()
results = engine.search("'" + target + "'")
for r in results:
print ("|--[INFO][GOOGLE][RESULTS][>] " + r["title"] + " | " + r["text"] + " | " + r["link"])
try:
web = requests.get(r["link"], timeout=3)
print ("|----[INFO][WEB][HTTP CODE][>] " + str(web.status_code) + "\n")
if web.status_code >= 200 or web.status_code < 300:
TEXT = er.remove_tags(str(web.text))
parser.parserMAIN(TEXT)
except Exception as e:
print ("|----[ERROR][HTTP CONNECTION][>] " + str(e))
def check_facebook(email):
r = br.open('https://mbasic.facebook.com/')
br.select_form(nr=0)
br.form["email"] = email
br.form["pass"] = "******"
br.submit()
respuestaURL = br.response().geturl()
html = br.response().read()
soup = BeautifulSoup(html, "html.parser")
div = soup.find("div", {"id": "login_error"})
if "ninguna" in R.remove_tags(str(div)):
print("|--[INFO][FACEBOOK][CHECK][>] Account doesn't exist...")
else:
print("|--[INFO][FACEBOOK][CHECK][>] The account exist...")
def searchInfojobs(nombre, a1, a2, loc):
headers = {'User-Agent': "DG Minimal Version"}
url_array = ("https://www.infojobs.net/" + nombre.replace(" ", "-") + "-" + a1.replace(" ", "-") + "-" + a2.replace(" ", "-") + ".prf", "https://www.infojobs.net/" + nombre.replace(" ", "-") + "-" + a1.replace(" ", "-") + ".prf", "https://www.infojobs.net/" + nombre.replace(" ", "-") + "-" + a1.replace(" ", "-") + "-1.prf")
for url in url_array:
html = requests.get(url, headers=headers).text
soup = BeautifulSoup(html, "html.parser")
h1s = soup.findAll("h1")
for h1 in h1s:
if "humano" in er.remove_tags(str(h1)):
print ()
print("|----[INFO][INFOJOBS][>] Captcha detectado...")
break
else:
print()
print("|----[INFO][INFOJOBS][>] " + str(h1))
def check_facebook(phone):
r = br.open('https://mbasic.facebook.com/')
br.select_form(nr=0)
br.form["email"] = phone
br.form["pass"] = "******"
br.submit()
respuestaURL = br.response().geturl()
html = br.response().read()
soup = BeautifulSoup(html, "html.parser")
a = soup.find("a",{"class":"bb"})
if "olvidado" in R.remove_tags(str(a)):
print("|--[INFO][FACEBOOK][CHECK][>] The account exist... \n")
else:
print("|--[INFO][FACEBOOK][CHECK][>] Account doesn't exist... \n")
def search_DDG_DORKS(TITLE, TEXT_0):
engine = Duckduckgo()
for FC_domain in config.FC_list:
results = engine.search(f"site:{FC_domain} {TITLE}")
for r in results:
print("|--[INFO][GOOGLE][RESULTS][>] " + r["title"] + " | " +
r["text"] + " | " + r["link"])
try:
tsd, td, tsu = extract(r["link"])
domain = td + '.' + tsu
web = requests.get(r["link"], timeout=3)
print("|----[INFO][WEB][HTTP CODE][>] " +
str(web.status_code) + "\n")
if web.status_code >= 200 or web.status_code < 300:
if ".pdf" in r["link"]:
pass
else:
if not domain in config.BL_parserPhone:
TEXT = er.remove_tags(str(web.text))
compareTEXT(TEXT, TEXT_0)
parser.FC_words_in_text(TEXT)
parser.parserMAIN(TEXT)
ratio = compareTEXT(TEXT_0, TEXT)
print(
f"|----[INFO][COMPARE TEXTS][>] Ratio: {ratio}"
)
#Guardamos la info en un log
data = f"{r['title']} ||| {r['link']} ||| {r['text']}, ||| {ratio} \n"
generateLOG(data, target)
else:
pass
print("")
time.sleep(2)
except Exception as e:
print("|----[ERROR][HTTP CONNECTION][>] " + str(e))
def check_netflix(email):
try:
r = br.open('https://www.netflix.com/es/login')
br.select_form(nr=0)
br.form["userLoginId"] = email
br.form["password"] = "******"
br.submit()
respuestaURL = br.response().geturl()
html = br.response().read()
soup = BeautifulSoup(html, "html.parser")
div = soup.find("div", {"class": "ui-message-contents"})
if "ninguna" in R.remove_tags(str(div)):
print("|--[INFO][NETFLIX][ES][CHECK][>] Account doesn't exist...")
else:
print("|--[INFO][NETFLIX][ES][CHECK][>] The account exist...")
except:
print(C.colores.green +
"|--[ERROR][Check_Netflix][>] Netflix error..." +
C.colores.normal)
def check_wordpress(email):
try:
r = br.open('http://wordpress.com/wp-login.php')
br.select_form("loginform")
br.form["log"] = email
br.form["pwd"] = "123456"
br.submit()
respuestaWP = br.response().geturl()
html = br.response().read()
soup = BeautifulSoup(html, "html.parser")
divError = soup.findAll("div", {"id": "login_error"})
div = R.remove_tags(str(divError))
if "incorrect" in div:
print("|--[INFO][WordPress][CHECK][>] The account exist...")
if "Invalid" in div:
print("|--[INFO][WordPress][CHECK][>] Account doesn't exist...")
except:
print(C.colores.alert + "|--[WARNING][LinkedIn][>] Error..." +
C.colores.normal)
def check_AccountTwitter(email):
username = get_usernameEmail(email)
url = "https://twitter.com/" + username
try:
html = requests.get(url).text
soup = BeautifulSoup(html, "html.parser")
for text in soup.findAll("h1"):
text = R.remove_tags(str(text))
if "Sorry" in text or "Lo sentimos," in text:
print("|--[INFO][Twitter][" + C.colores.blue + username +
C.colores.normal + "][>] Account doesn't exist...")
else:
print(C.colores.green + "|--[INFO][Twitter][" +
C.colores.blue + username + C.colores.green +
"][>] The account exist." + C.colores.normal)
except urllib.error.HTTPError:
print(
C.colores.alert +
"|--[404 HTTP RESPONSE][Check_AccountTwitter][>] 404 HTTP Twitter error..."
+ C.colores.normal)
def check_Facebook(email):
url = 'https://mbasic.facebook.com/'
br.open(url)
br.select_form(nr=0)
response = br.submit()
#print (response.geturl())
br.select_form(nr=0) #This is login-password form -> nr = number = 0
br.form['email'] = email
br.form['pass'] = "******"
response = br.submit()
#print (response.geturl())
html = br.response().read()
soup = BeautifulSoup(html, "html.parser")
divError = soup.findAll("div", {"id": "login_error"})
div = R.remove_tags(str(divError))
if "no coincide" in div or "do not match" in div:
print("|--[INFO][Facebook][CHECK][>] Account doesn't exist...")
else:
print(C.colores.green +
"|--[INFO][Facebook][CHECK][>] The account exist..." +
C.colores.normal)
def main():
#Imprimimos el banner principal
print(config.banner)
#Insertamos la URL a buscar
url = input("Insert URL: ")
#Obtenemos el HTML
HTML = requests.get(url)
#Obtenemos el título
TITLE = footprintingWEB_TITLE(HTML)
#Obtenemos la descripción
DESC = er.remove_tags(str(footprintingWEB_DESC(HTML)))
print(f"|----[TARGET][>] {url}")
print(f"|--------[TARGET][TITLE][>] {TITLE}")
print(f"|--------[TARGET][DESCRIPTION][>] {DESC}")
time.sleep(2)
#Obtenemos el texto de la noticia
TEXT_0 = er.remove_tags(str(HTML.text))
#buscamos una fecha en la URL
DATE = parser.parser_EN_DATE(url)
#Parseamos y obtenemos diferentes tipos de datos
parser.parserMAIN(TEXT_0)
time.sleep(3)
#Buscamos en Google y DuckDuckGo
print("|----[INFO][>] Now let's look for other news: \n")
m = input("Do you want to search the original web? (Y/n): ")
if m == "y" or m == "Y":
search_google_(TITLE, TEXT_0)
search_DDG_(TITLE, TEXT_0)
else:
pass
#Buscamos en plataformas de verificación
m = input("Do you want to analyze in fact-checking platforms? (Y/n): ")
if m == "y" or m == "Y":
#Buscamos con dorks en DDG
search_DDG_DORKS(TITLE, TEXT_0)
else:
exit
#Buscamos en Twitter
m = input("Do you want to search in Twitter? (Y/n): ")
if m == "y" or m == "Y":
#Buscamos con dorks en DDG
Twint.search_Twitter(url)
else:
exit
def extract_personalData_wikipedia(html, url, target):
soup = BeautifulSoup(html.text, "html.parser")
tables = soup.findAll("tr")
for tr in tables:
tr_ = er.remove_tags(str(tr))
if "Nacimiento" in tr_:
print(f"|----[INFO][AGE][>] Age found on Wikipedia {tr_}")
#Obtenemos el horoscopo
signo = ("capricornio", "acuario", "piscis", "aries", "tauro",
"géminis", "cáncer", "leo", "virgo", "libra", "escorpio",
"sagitario")
meses = {
"enero": 1,
"febrero": 2,
"marzo": 3,
"abril": 4,
"mayo": 5,
"junio": 6,
"julio": 7,
"agosto": 8,
"septiembre": 9,
"octubre": 10,
"noviembre": 11,
"diciembre": 12
}
fechas = (20, 19, 20, 20, 21, 21, 22, 22, 22, 22, 22, 21)
dia = 0
mes = 0
words = tr_.replace("\n", " ").split(" ")
for w in words:
if w.isdigit() and len(w) <= 2:
dia = int(w)
else:
pass
if w.lower() in meses.keys():
mes = meses.get(w.lower())
else:
pass
mes = mes - 1
if dia > fechas[mes]:
mes = mes + 1
if mes == 12:
mes = 0
print("|----[INFO][HOROSCOPO][>] " + signo[mes])
#Save to DB
birth = tr_.replace("Age found on Wikipedia Nacimiento", "")
mongo.personalData_Wikipedia_insertMongoDB(target, birth, url, 1)
mongo.personalData_Wikipedia_insertMongoDB(target, signo[mes], url,
3)
data.Wiki_birth = birth
data.Wiki_url = url
data.WIki_horoscopo = signo[mes]
if "Fallecimiento" in tr_:
print(f"|----[INFO][DEATH][>] Death found on Wikipedia {tr_}")
#Save to DB
mongo.personalData_Wikipedia_insertMongoDB(target, tr_, url, 2)
data.Wiki_death = tr_
if "Partido político" in tr_:
print(f"|----[INFO][POLITICAL PARTY][>] {tr_}")
#Save to DB
mongo.personalData_Wikipedia_insertMongoDB(target, tr_, url, 7)
data.Wiki_politicalParty = tr_
if "Ocupación" in tr_:
print(f"|----[INFO][EMPLOYMENT][>] {tr_}")
#Save to DB
mongo.personalData_Wikipedia_insertMongoDB(target, tr_, url, 4)
data.Wiki_employment = tr_.replace("Ocupación", "")
if "Religión" in tr_:
print(f"|----[INFO][RELIGION][>] {tr_}")
#Save to DB
mongo.personalData_Wikipedia_insertMongoDB(target, tr_, url, 5)
data.Wiki_religion = tr_
if "Hijos" in tr_:
print(f"|----[INFO][SONS][>] {tr_}")
#Save to DB
mongo.personalData_Wikipedia_insertMongoDB(target, tr_, url, 6)
data.Wiki_sons = tr_
