def do_query(query, print_flag=False, *, n_result = 10):
try:
from googlesearch import search
except ImportError:
print("No module named 'google' found")
# to search
#query = "Geeksforgeeks"
for j in search(query, tld="com", num=n_result, stop=1, pause=2):
if print_flag:
print(j)
speak("According to Wikipedia")
speak(results)
except Exception as e:
print(e)
sys.stdout.flush()
speak(e)
elif 'search google' in query:
speak("What do you want me to search?")
print("Listening.....")
sys.stdout.flush()
gs = takeCommand().lower()
speak("Searching Google...")
arr = list(search(gs, tld='co.in', lang='en',
num=5, start=0, stop=5, pause=1.2))
clone_arr = list()
for i in range(len(arr)):
clone_arr.append(f"{i+1}. " + arr[i])
google_outs = ''
google_outs += "<br>".join(clone_arr)
print(google_outs+"<br>"*2 + "Listening....")
sys.stdout.flush()
# time.sleep(1.5)
speak("Do you want me to open any of these??")
def get_arxiv_urls(paper_titles, output_json_dir=None):
"""Get a list of arxiv urls from paper_titles
One way to do it is to install googler and use it.
```
for filename in files[:1]:
os.system('googler -n 1 "{}" arxiv.org filetype:pdf'.format(filename))
```
Note that google search has a query limit. Per instructions here:
https://github.com/abenassi/Google-Search-API/blob/master/google/modules/utils.py#L81
>> You may also wanna wait some time between queries, say, randint(50,65)
between each query, and randint(180,240) every 100 queries, which is
what I found useful.
Here we use python lib googlesearch for portability
TODO: try https://github.com/abenassi/Google-Search-API to avoid double query
"""
urls = []
for idx_query, paper_title in tqdm(list(enumerate(paper_titles[:]))):
success = False
num_trial = 0
sleep_in_seconds = 0
query_results = []
query = '{} arxiv.org'.format(paper_title)
print(query)
# try num_trial times with sleep_in_seconds intervals before moving on to next search
while not success and num_trial < 2:
time.sleep(sleep_in_seconds)
try:
# convert returned iterator to list to catch the error here
query_results = list(
googlesearch.search(query, stop=1, pause=2))
except:
sleep_in_seconds = random.randint(180, 240) * (num_trial + 1)
print('Warning: sleep and retry in {} seconds'.format(
sleep_in_seconds))
continue
num_trial += 1
success = True
for url in query_results:
if 'arxiv.org/pdf' in url:
# cannot scrape the title of a web page containing a pdf file
continue
# sometimes google gives a numeric IP as of arxiv.
url = 'https://arxiv.org/' + '/'.join(
url.replace('https://', '').split('/')[-2:])
try:
url_title = google_scrape(url)
except:
url_title = ''
print('url ', url)
print('url title ', url_title)
urls.append({
'url_title': url_title,
'url': url,
'query': paper_title,
})
if os.path.isdir(output_json_dir):
with open(os.path.join(output_json_dir, 'query_urls.json'),
'a') as f_out:
json.dump(urls, f_out, indent=4, sort_keys=True)
return urls
def searching(item):
searching = search(item, num_results=5)
for i in searching:
search_list.append(i)
return search_list
import webbrowser
from googlesearch import search
import pyqrcode
from pyqrcode import QRCode
f = open("glinks", 'w')
web = input("ENTER TOPIC TO SEARCH ON GOOGLE :")
url_list = []
x = 1
for i in search(web, tld="co.in", lang="eng", num=3, start=0, stop=3, pause=2):
url_list.append(i)
print(i)
url = pyqrcode.create(i)
webbrowser.open(i)
url.svg("qrcode" + str(x) + ".svg", scale=6)
x = x + 1
cursor = connection.cursor()
cursor.execute(sql_select_Query)
records = cursor.fetchall()
print("Number of games: ", cursor.rowcount)
print("\nFor each game now:")
# row[0] = id, row[1] = name
for row in records:
games[row[0]] = row[1]
# searching
for id in games:
query = "Buy " + games[id] + "digital copy"
links = []
domains = []
for url in search(query, tld="co.in", num=8, stop=8, pause=2):
domain = url.split("//")[-1].split("/")[0]
if domain not in domains:
domains.append(domain)
links.append(url)
if len(links) == 3:
break
for i in range(0, len(links)):
try:
sql_insert_Query = "insert into store_links (id_game, domain_name, link) values (%s, %s, %s)"
val = (id, domains[i], links[i])
cursor2 = connection.cursor()
cursor2.execute(sql_insert_Query, val)
print("a intrat ", games[id])
except Error as e:
def scrape_company(company,
max_depth=MAX_DEPTH,
max_entry_links=MAX_ENTRY_LINKS,
max_total_links=MAX_TOTAL_LINKS):
# Open up Selenium web browser
options = webdriver.ChromeOptions()
options.add_argument('headless')
options.add_argument('--incognito')
options.add_argument('user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64 '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/70.0.3538.77 Safari/537.36')
driver = webdriver.Chrome(options=options)
# Find company website, abbreviation
for url in search(company + ' careers website', stop=1):
company_website = urlparse(url).netloc
company_abbrev = company.lower().replace(' ', '').replace('.', '')
print('Company is {0}.'.format(company))
print('Company careers website is {0}.'.format(company_website))
# Intially, frontier is populated a Google search
# These links must originate at the company website found earlier
frontier = PriorityQueue()
visited = set()
search_term = company + ' internship apply'
for entry_link in search(search_term, stop=max_entry_links):
if urlparse(entry_link).netloc != company_website:
continue
entry_link = normalize_link(entry_link)
heuristic = score_link_heuristic(entry_link, company)
frontier.put((-heuristic, (entry_link, 1)))
visited.add(entry_link)
# This method allows us to vet & add child links to the frontier
def explore_child_links(links):
for link in links:
# Filter out obviously bad links
if not link or len(link) <= 2 or link[0] == '#' or \
'javascript:void' in link or link.startswith('mailto'):
continue
# Fix relative links, trim trailing slashes, etc
link = normalize_link(link,
parent=current,
parent_base=current_base)
# Links must either be tied to the company or
# an external job application website
domain = urlparse(link).netloc
if domain != company_website and \
company_abbrev not in domain and \
'taleo' not in domain and \
'workday' not in domain and \
'greenhouse' not in domain and \
'jobvite' not in domain and \
'icims' not in domain:
continue
# PDF or image links should not be followed
if link.endswith('.pdf') or link.endswith('.jpg') or \
link.endswith('.jpg'):
continue
# Skip links that have already been added to the frontier
if link in visited:
continue
heuristic = score_link_heuristic(link, company_abbrev)
frontier.put((-heuristic, (link, depth + 1)))
visited.add(link)
results = []
link_idx = 0
while frontier and link_idx < max_total_links:
# Extract current link we are on and the link's root (excludes path)
neg_heuristic, (current, depth) = frontier.get()
current_parse = urlparse(current)
current_loc = current_parse.netloc
current_base = current_parse.scheme + '://' + current_loc
# TODO: Convert from printing to logging
print('Visiting ... {0} (depth={1}, lh={2})'.format(
current, depth, -neg_heuristic))
# Use Selenium to fetch our page, wait a bit for the page to load
driver.get(current)
time.sleep(2)
content = driver.page_source
# Determine whether a page is explorable without doing
# any HTML parsing by doing some primitive checks
lcontent = content.lower()
explorable = False
for keyword in ['job', 'career', 'intern']:
if keyword in lcontent:
explorable = True
break
if not explorable:
continue
link_idx += 1
# Parse HTML using BS4, discard links in header and footer
soup = BeautifulSoup(content, 'lxml')
if soup.header:
soup.header.decompose()
if soup.footer:
soup.footer.decompose()
# Assign score to page based off of BS4 parse
page_score = score_page(soup, company_abbrev)
iframes = driver.find_elements_by_tag_name('iframe')
for iframe in iframes:
driver.switch_to.frame(iframe)
isoup = BeautifulSoup(driver.page_source, 'lxml')
if isoup.header:
isoup.header.decompose()
if isoup.footer:
isoup.footer.decompose()
page_score = max(page_score, score_page(isoup, company_abbrev))
driver.switch_to.default_content()
if page_score > 0:
results.append((current, page_score))
# Child exploration cannot exceed the given maximum depth
if depth < max_depth:
# Collect links from anchor tags
explore_child_links(
[a.get('href') for a in soup.find_all('a', href=True)])
# Collect links from each iframe separately
for iframe in iframes:
driver.switch_to.frame(iframe)
isoup = BeautifulSoup(driver.page_source, 'lxml')
if isoup.header:
isoup.header.decompose()
if isoup.footer:
isoup.footer.decompose()
explore_child_links(
[a.get('href') for a in isoup.find_all('a', href=True)])
# Close the browser instance that Selenium opened
driver.close()
# Find all result links that have the maximum score
if results:
max_score = max([score for _, score in results])
max_links = [link for link, score in results if score == max_score]
return (max_links, max_score)
else:
return ([], 0)
selection = int(
input(
"\nPlease select a dork:\n[1] cat\n[2] id\n[3] article\n[4] page\n[5] bookid\n[6] Custom dork\n"
))
if selection == 6:
dork = input(
"\nPlease enter the dork (ex: for ?id= you would just enter id)\n")
else:
dork = dorkList[selection - 1]
finalDork = "inurl: ?" + dork + "="
searchAmount = int(input("\nPlease enter an amount of links to test:\n"))
print("\nSearching and testing...\n")
for x in search(finalDork,
tld='com',
lang='en',
num=searchAmount,
start=0,
stop=searchAmount,
pause=2.0):
url = x + "'"
res = requests.get(url)
html_page = res.content
soup = BeautifulSoup(html_page, 'html.parser')
text = soup.find_all(text=True)
for y in text:
if y.find("You have an error in your SQL") != -1:
foundUrls.append(x)
print("\nVulnerable site found:", x)
file = open("output.txt", "a")
for x in foundUrls:
file.write(x + "\n")
elif press == 5:
os.system("date +'%F %T'")
elif press == 6:
print("are you sure ? y/n")
access=input()
if access == "y":
os.system("reboot")
elif access == "n":
print("Process aborted")
else:
print("wrong keyword pressed")
elif press == 7:
name=input("Enter your search keyword : ")
os.system('firefox --search {}'.format(name))
elif press == 8:
#Install mpg123 packages.(yum install -y mpg123)
file = "/root/Downloads/hindi.mp3"
os.system("mpg123 " + file)
elif press == 9:
#Install 'pip3 install google'.
try:
from googlesearch import search
except ImportError:
print("No module named 'google' found")
keyword =input("Enter your keyword to search : ")
for name in search(keyword, tld="com", num=5, stop=5, pause=2):
print(name)
def runvisuals(self):
#Have to make user_id set in the sessions
#GOOGLE APIS
try:
from googlesearch import search
except ImportError:
print("We could not find it at all!")
query = "Instagram"
for i in search(query, tld="co.in", num=10, stop=10, pause=2):
print(i)
self.winfo_toplevel().title("Perseus 1.1.0")
#self.parent.geometry('2000x900')
self.parent.configure(background="grey")
#sideFrame = Frame(self.parent,height=1500,width=100, relief=SUNKEN)
#sideFrame.grid(row=0,column=0, sticky='w')
newFrame = Frame(self.parent, height=1500,width=150, relief=SUNKEN)
newFrame.grid(row=0,column=1, sticky='ne',padx=(0,10))
e = Entry(newFrame, width=150);
e.grid(row=0,column=0,padx=(0,10))
def Search():
try:
from googlesearch import search
except ImportError:
print("We could not find it at all!")
query = e.get()
r = 2
for i in search(e.get(), tld="co.in", num=10, stop=10, pause=2):
LabelResult = Label(newFrame, text=i)
LabelResult.grid(row=r, column=0, sticky='nw', padx=(0,10))
ButtonOptions = Button(newFrame, text="Save", command=lambda:SaveLink(e.get(),i, 1))
ButtonOptions.grid(row=r, column=2, sticky='nw', padx=(0,10))
r = r + 1
searchBtn = Button(newFrame,text="Search", command=Search)
searchBtn.grid(row=1,column=0, sticky='nw',padx=(0,10))
#newFrame.grid(row=2,column=0)
#yscrolbar.configure(command=newSpace.yview)
#xscrollbar.configure(command=newSpace.xview)
""" Making the Side window with File Tree
>>>>>>> 73be496... Finish
p = ttk.Panedwindow(sideFrame, orient=VERTICAL)
# first pane, which would get widgets gridded into it:
fp = ttk.Labelframe(p, text='File Management', width=200, height=720)
p.add(fp)
p.pack(fill=BOTH, expand=1)
#Tab view
n = ttk.Notebook(fp)
f1 = ttk.Frame(n, width=200, height=720) # first page, which would get widgets gridded into it
<<<<<<< HEAD
f2 = ttk.Frame(n, width=200, height=720)
# second page
n.add(f1, text='Local Files')
n.add(f2, text='Online Files')
n.pack(fill="both", expand=1)
#Toolbar view
#toolbar = Frame(frame, style='My.TFrame', height=720, width=25, relief=SUNKEN)
#canvasToolbar = Canvas(toolbar, bg='blue',height=720, width=20)
#toolbar.pack(side=RIGHT, fill=BOTH, expand=1)
#toolbar.place(relx=1,rely=0,anchor=NE)
#buttons on the toolbar
"""for i in range(15):
button = Button(toolbar, height=1)
button.pack(side=TOP, fill=BOTH, expand=1)
"""
"""Label"""
ttk.Label(f1, text="Hierachical Treeview").pack()
"""Treeview"""
treeview=ttk.Treeview(f1)
treeview.pack()
"""Treeview items"""
=======
# second page
n.add(f1, text='Saved Files')
n.pack(fill="both", expand=1)
#Toolbar view
toolbar = Frame(newFrame, style='My.TFrame', height=720, width=25, relief=SUNKEN)
canvasToolbar = Canvas(toolbar, bg='blue',height=720, width=20)
toolbar.pack(side=RIGHT, fill=BOTH, expand=1)
toolbar.place(relx=1,rely=0,anchor=NE)"
#buttons on the toolbar
#options = ["Search", "Save", "Delete"]
#for i in options:
# button = Button(toolbar, text=i)
# button.pack(side=TOP, fill=BOTH, expand=1)"""
"""#Label
ttk.Label(f1, text="Hierachical Treeview").pack()
#Treeview
treeview=ttk.Treeview(f1)
treeview.pack()
#Treeview items
>>>>>>> 73be496... Finish
treeview.insert('','0','item1',text='Parent tree')
treeview.insert('','1','item2',text='1st Child')
treeview.insert('','end','item3',text='2nd Child')
treeview.insert('item2','end','A',text='A')
treeview.insert('item2','end','B',text='B')
treeview.insert('item2','end','C',text='C')
treeview.insert('item3','end','D',text='D')
treeview.insert('item3','end','E',text='E')
treeview.insert('item3','end','F',text='F')
treeview.move('item2','item1','end')
<<<<<<< HEAD
treeview.move('item3','item1','end')
"""Making the compression Rate Label """
#compressionRateLabel = Label(frame, text="Compression Rate : ", height=1, width=1648, bd=1, bg="grey")
#compressionRateLabel.place(relx=0, rely= 1, anchor=S)
#TestShape = Shapes(frame)
#TestShape.circle()
""" Making the menu bar for the application"""
menubar = Menu(self.parent)
"""Making the file tree """
localFileTree = Treeview(f1)
=======
treeview.move('item3','item1','end')"""
"""Making the compression Rate Label """
#ompressionRateLabel = Label(Shapes.frame, text="Compression Rate : ", width=1648, bd=1, bg="grey")
#compressionRateLabel.place(relx=0, rely= 1, anchor=S)
#TestShape = Shapes(newFrame)
#TestShape.circle(10,10,100,100,"red",)
""" Making the menu bar for the application"""
menubar = Menu(self.parent)
"""Making the file tree """
#!/usr/bin/python
import webbrowser
from googlesearch import search
#to take input of search
web = input('Enter what to search')
url = []
#Now to search
for each_search in search(web, stop=5):
url.append(each_search)
print(each_search) #print each searched link
webbrowser.open_new_tab(each_search)
for each in search(each_search, stop=5): #to search again in above 5 links
print(each) #print each searched link
webbrowser.open_new_tab(each)
def get_urls(tag, n, language):
urls = [url for url in search(tag, stop=n, lang=language)][:n]
return urls
from googlesearch import search
import pyqrcode
from pyqrcode import QRCode
urlinput=input("enter text to search")
urllist=[]
for i in search(urlinput, tld='com', lang='en', num=10, start=0, stop=5, pause=2) :
urllist.append(i)
print(i)
url=pyqrcode.create(i)
for j in range(5) :
url.svg(str(j)+".svg",scale=8)
print(url.terminal())
# ****
def spinning_cursor():
while True:
for cursor in '|/-\\':
yield cursor
spinner = spinning_cursor()
for _ in range(100):
sys.stdout.write(next(spinner))
sys.stdout.flush()
time.sleep(0.1)
sys.stdout.write('\b')
#*****
for gamma in search(query, tld=beta, stop=50, num=10, pause=2):
print(colored('[+] Found > ', 'yellow') + (gamma))
print(colored('[+] 20% done ', 'green'))
B = """ inurl:dtm.html intitle:1747-L551 """
query = B
# ****
def spinning_cursor():
while True:
for cursor in '|/-\\':
yield cursor
spinner = spinning_cursor()
for _ in range(100):
def extractFraseGoogle(frase, cantRes):
print ("Searching emails... please wait")
print ("This operation may take several minutes")
try:
listUrl = []
count = 0
for url in search(frase, stop=cantRes):
listUrl.append(url)
for i in listUrl:
try:
req = urllib.request.Request(
i,
data=None,
headers={
'User-Agent': ua.random
})
try:
conn = urllib.request.urlopen(req)
except timeout:
print("Bad Url..")
time.sleep(2)
pass
except(HTTPError, URLError):
print("Bad Url..")
time.sleep(2)
pass
status = conn.getcode()
contentType = conn.info().get_content_type()
if(status != 200 or contentType == "audio/mpeg"):
print("Bad Url..")
time.sleep(2)
pass
html = conn.read()
soup = BeautifulSoup(html, "lxml")
links = soup.find_all('a')
print("They will be analyzed " + str(len(links) + 1) + " Urls..." )
time.sleep(2)
for tag in links:
link = tag.get('href', None)
if link is not None:
try:
print ("Searching in " + link)
if(link[0:4] == 'http'):
req = urllib.request.Request(
link,
data=None,
headers={
'User-Agent': ua.random
})
try:
f = urllib.request.urlopen(req)
except timeout:
print("Bad Url..")
time.sleep(2)
pass
except(HTTPError, URLError):
print("Bad Url..")
time.sleep(2)
pass
status = conn.getcode()
contentType = conn.info().get_content_type()
if(status != 200 or contentType == "audio/mpeg"):
print("Bad Url..")
time.sleep(2)
pass
s = f.read().decode('utf-8')
emails = re.findall(r"[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,4}", s)
for email in emails:
if (email not in listUrl and email[-3:] not in imageExt):
count += 1
print(str(count) + " - " + email)
listUrl.append(email)
if (searchEmail("Emails.db", email, frase) == 0):
insertEmail("Emails.db", email, frase, link)
# Sigue si existe algun error
except Exception:
pass
print(str(count) + " emails were found")
except urllib.error.URLError as e:
print("Problems with the url:" + i)
print(e)
pass
except KeyboardInterrupt:
input("Press return to continue")
menu()
except Exception as e:
print(e)
input("Press enter to continue")
menu()
print("Enter Your Choice : ")
ch=int(input("1)TEXT\t2)VOICE"))
if ch==2:
r=sr.Recognizer()
with sr.Microphone() as source:
print("Listening....");
data=r.listen(source)
print("Searching...")
try:
query=r.recognize_google(data)
except:
pass;
elif ch==1:
query=input("Type the Query: ")
else :
print("Invalid")
exit
url=[]
for i in search(query,stop=10):
print(i)
url.append(i)
print(url)
def start():
time.sleep(2)
print("what is your name sir? ")
os.startfile("wiyn.mp3")
time.sleep(1.3)
with mic as source:
try:
print("---listening---")
r.adjust_for_ambient_noise(source)
audio=r.listen(source)
print("recognising...")
name=r.recognize_google(audio)
print(name)
except:
name=("Sir")
greet= gTTS(text=name,lang="hi")
greet.save("name.mp3")
os.startfile("hello.mp3")
os.startfile("hello.mp3")
time.sleep(1.1)
os.startfile("name.mp3")
time.sleep(2.0)
text=("I am Mouli. your virtual assistant, say ' hey molly ', if you need any help ")
intro=gTTS(text=text,lang="en")
intro.save("text.mp3")
os.startfile("text.mp3")
time.sleep(4.3)
while True:
bkchd=-5
with mic as source:
try:
print("listening")
r.adjust_for_ambient_noise(source)
audio=r.listen(source)
print("recognising")
openw=r.recognize_google(audio)
if (openw=="Hemali" or openw=="hey only" or openw=="hey money" or openw=="hey Molly"):
os.startfile("beep.mp3")
print("verified")
bkchd=5
except:
a=("hye")
if (bkchd>0):
hcihy=gTTS(text="how can i help you?",lang="en")
hcihy.save("hcihy.mp3")
os.startfile("hcihy.mp3")
time.sleep(2)
with mic as source:
try:
print("---listening---")
r.adjust_for_ambient_noise(source)
audio=r.listen(source)
print("recognising...")
task=r.recognize_google(audio)
print(task)
except:
print("could not recognise")
task=("hi Molly")
bkchd=-5
j = search(task,num=1,tld="com",lang="en",stop=2,pause=1,start=1)
for i in j:
website=i
w1=task.find("remind")
w2=task.find("play")
w3=task.find("open")
w4=task.find("music")
w5=task.find("stop listening")
w6=task.find("shutdown")
w7=task.find("joke")
w8=task.find("please molly")
w9=task.find("hi Molly")
if (w2>=0):
os.startfile("suresir.mp3")
time.sleep(3.5)
ntask=(task)
n1=ntask.replace("on YouTube","")
n1=n1.replace("on gaana","")
n2=n1.replace("play","")
n3=n2.replace("video","")
n0=n3.replace("song","")
n5=n0.replace("1","")
n5=n5.replace("2","")
n5=n5.replace("3","")
n5=n5.replace("4","")
n5=n5.replace("5","")
n5=n5.replace("6","")
n5=n5.replace("7","")
n5=n5.replace("8","")
n5=n5.replace("9","")
n5=n5.replace("0","")
n4=n5.replace("and stop listining for","")
n4=n4.replace("minute","")
n4=n4.replace("minutes","")
n4=n4.replace("second","")
n4=n4.replace("seconds","")
w10=task.find("movie")
w11=task.find("song")
if (w11>=0):
w13=task.find("gaana")
if (w13>=0):
webbrowser.open("www.gaana.com")
time.sleep(4)
keyboard.press(Key.space)
keyboard.release(Key.space)
bkchd=-5
else:
y=1
webbrowser.open("www.youtube.com")
time.sleep(5)
keyboard.press(Key.tab)
keyboard.release(Key.tab)
keyboard.press(Key.tab)
keyboard.release(Key.tab)
keyboard.press(Key.tab)
keyboard.release(Key.tab)
keyboard.type(n4)
keyboard.press(Key.enter)
keyboard.release(Key.enter)
time.sleep(2)
for y in range (1,11):
keyboard.press(Key.tab)
keyboard.release(Key.tab)
y=y+1
time.sleep(0.5)
keyboard.press(Key.enter)
keyboard.release(Key.enter)
bkchd=-5
elif(w10>=0):
webbrowser.open("www.khatrimaza.link")
bkchd=-5
else:
y=1
webbrowser.open("www.youtube.com")
time.sleep(5)
keyboard.press(Key.tab)
keyboard.release(Key.tab)
keyboard.press(Key.tab)
keyboard.release(Key.tab)
keyboard.press(Key.tab)
keyboard.release(Key.tab)
keyboard.type(n4)
keyboard.press(Key.enter)
keyboard.release(Key.enter)
time.sleep(2)
for y in range (1,11):
keyboard.press(Key.tab)
keyboard.release(Key.tab)
y=y+1
time.sleep(0.5)
keyboard.press(Key.enter)
keyboard.release(Key.enter)
bkchd=-5
if(w7>=0):
os.startfile("suresir.mp3")
time.sleep(1)
i=random.randint(0,1)
if (i==0):
joke1()
elif (i==1):
joke2()
bkchd=-5
if(w6>=0):
os.startfile("suresir.mp3")
print("Bye...")
time.sleep(2)
subprocess.call(["shutdown", "-f", "-s", "-t", "60"])
bkchd=-5
if(w3>=0):
os.startfile("suresir.mp3")
time.sleep(2)
fname1=task.replace("open","")
fname2=fname1.replace("game","")
fname3=fname2.replace("folder","")
fname4=fname3.replace("file","")
fname41=fname4.replace("calculator","calc")
fname5=fname41.replace("app","")
keyboard.press(Key.cmd)
keyboard.release(Key.cmd)
time.sleep(0.05)
keyboard.type(fname5)
time.sleep(0.15)
keyboard.press(Key.enter)
keyboard.release(Key.enter)
bkchd=-5
if(w1<0 and w2<0 and w3<0 and w4<0 and w5<0 and w6<0 and w7<0 and w8<0 and w9<0):
os.startfile("suresir.mp3")
a=0
i=0
ntask=(task)
n1=ntask.replace("on YouTube","")
n1=n1.replace("on gaana","")
n2=n1.replace("play","")
n3=n2.replace("video","")
n0=n3.replace("song","")
n5=n0.replace("1","")
n5=n0.replace("2","")
n5=n0.replace("3","")
n5=n0.replace("4","")
n5=n0.replace("5","")
n5=n0.replace("6","")
n5=n0.replace("7","")
n5=n0.replace("8","")
n5=n0.replace("9","")
n5=n0.replace("0","")
n4=n5.replace("and stop listining for","")
n4=n4.replace("minute","")
n4=n4.replace("minutes","")
n4=n4.replace("second","")
n4=n4.replace("seconds","")
for i in range(0,6):
prob=task.find(question[i])+1
a=a+prob
i=i+1
if(a==0):
try:
detail= (wikipedia.summary(task,sentences=2))
tts= gTTS(text=detail,lang="en")
tts.save("a.mp3")
os.startfile("a.mp3")
print(detail)
time.sleep(15)
bkchd=-5
except:
print ("I can search it for you")
time.sleep(1)
webbrowser.open(website)
bkchd=-5
else:
print ("I can search it for you")
time.sleep(1)
webbrowser.open(website)
bkchd=-5
if(w5>=0):
f1=task.find("minute")
f2=task.find("minutes")
a1=task.replace("a","")
a2=a1.replace("b","")
a3=a2.replace("c","")
a4=a3.replace("d","")
a5=a4.replace("e","")
a6=a5.replace("f","")
a7=a6.replace("g","")
a8=a7.replace("h","")
a9=a8.replace("i","")
a10=a9.replace("j","")
a11=a10.replace("k","")
a12=a11.replace("l","")
a13=a12.replace("m","")
a14=a13.replace("n","")
a15=a14.replace("o","")
a16=a15.replace("p","")
a17=a16.replace("q","")
a18=a17.replace("r","")
a19=a18.replace("s","")
a20=a19.replace("t","")
a21=a20.replace("u","")
a22=a21.replace("v","")
a23=a22.replace("w","")
a24=a23.replace("x","")
a25=a24.replace("y","")
a26=a25.replace("z","")
task=a26
a1=task.replace("A","")
a2=a1.replace("B","")
a3=a2.replace("C","")
a4=a3.replace("D","")
a5=a4.replace("E","")
a6=a5.replace("F","")
a7=a6.replace("G","")
a8=a7.replace("H","")
a9=a8.replace("I","")
a10=a9.replace("J","")
a11=a10.replace("K","")
a12=a11.replace("L","")
a13=a12.replace("M","")
a14=a13.replace("N","")
a15=a14.replace("O","")
a16=a15.replace("P","")
a17=a16.replace("Q","")
a18=a17.replace("R","")
a19=a18.replace("S","")
a20=a19.replace("T","")
a21=a20.replace("U","")
a22=a21.replace("V","")
a23=a22.replace("W","")
a24=a23.replace("X","")
a25=a24.replace("Y","")
a26=a25.replace("Z","")
a27=a26.replace(" ","")
print(a27)
if(f1>=0 or f2>=0):
a0=int(a27)
a4=a0*60
else:
a4=int(a27)
os.startfile("suresir.mp3")
time.sleep(a4)
bck=gTTS(text="Back again. sir",lang="en")
bck.save("backagain.mp3")
os.startfile("backagain.mp3")
time.sleep(1.5)
try:
from googlesearch import search
except ImportError:
print("No module named 'google' found")
# to search
query = "Geeksforgeeks"
for j in search(
query,
tld="co.in",
num=10,
stop=10,
pause=2,
user_agent=
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36"
):
print(j)
# import urllib.request
# import json
# x = urllib.request.urlopen('http://testpy.pickandpaid.com/test/')
# data = x.read()
# JSON_object = json.loads(data.decode('utf-8'))
# # print(JSON_object)
# for data in JSON_object:
# print(JSON_object[data])
def digital_assistant(data):
try:
if "how are you" in data:
respond("I am well")
return
elif "time" in data:
respond(ctime())
return
elif "who are you" in data or "what can you do" in data or "define yourself" in data:
respond("I am viswanadh's personal assistant, I am programmed to do minor tasks like system monitoring, profiling,"
"predict time, take a photo, predict weather,"
" opening applications like youtube, google chrome ,gmail etcetre, show the top headline news and you can ask me computational or geographical questions too!")
return
elif "who made you" in data or "who created you" in data:
respond("I was built by viswa")
return
elif "shutdown" in data:
respond("Are you sure! you want to shutdown your computer")
data = listen()
if data == "yes":
respond("system is going to shutdown...")
os.system("taskkill /f /im Rainmeter.exe")
os.system("shutdown /s /t 1")
return
elif "restart" in data:
respond("want to restart your computer")
data=listen()
if data=="yes":
os.system("shutdown /r /t 1")
return
elif "battery" in data:
battery=psutil.sensors_battery()
respond("Your system is at " + str(battery.percent) + " percent")
return
elif "cpu" in data:
respond("CPU is at "+ str(psutil.cpu_percent()))
return
elif "music" in data:
respond("Here you go with music")
music_dir = "C:\\Users\\VISWANADH\\Music"
song = random.choice(os.listdir(music_dir))
os.startfile(os.path.join(music_dir,song))
time.sleep(5)
return
elif "movie" in data:
os.system("D:\\movies\\Ala_Vaikunthapurramloo.mkv")
time.sleep(5)
return
elif "notepad" in data:
os.system("notepad")
return
elif "open" in data:
data = data.split(" ")
query = data[1]
for j in search(query, tld='com', lang='en', num=1, start=0, stop=1, pause=2.0):
url=j
webbrowser.get('chrome').open_new(url)
respond(data[1] + " is open now")
time.sleep(7)
return
elif "news" in data:
query = "news"
url="https://timesofindia.indiatimes.com/home/headlines"
webbrowser.get('chrome').open_new(url)
respond("Here are some headlines from the Times of India,Happy reading")
time.sleep(5)
return
elif "weather" in data:
data=data.split(" ")
#create key: https://home.openweathermap.org/users/sign_in
api_key = ####################
base_url = "https://api.openweathermap.org/data/2.5/weather?"
if "in" not in data:
city_name = "kurupam"
else:
city_name = data[-1]
complete_url = base_url + "appid=" + api_key + "&q=" + city_name
response = requests.get(complete_url)
x = response.json()
if x["cod"] != "404":
y = x["main"]
current_temperature = y["temp"]
current_humidiy = y["humidity"]
z = x["weather"]
weather_description = z[0]["description"]
respond(" Temperature in kelvin unit at " + city_name + " is " +
str(current_temperature) +
"\n humidity in percentage is " +
str(current_humidiy) +
"\n description " +
str(weather_description))
return
else:
respond(city_name + " weather details not found")
return
elif "something" in data:
respond("Searching...")
data=data[22:]
data = "According to wikipedia " + wikipedia.summary(data, sentences=4)
respond(data)
return
elif "capture the photo" in data or "take a photo" in data:
ec.capture(0,False,"img.jpg")
respond("photo captured successfully")
return
elif "video" in data or "capture the video" in data:
ec.auto_vidcapture(0,False,"video.mkv",10)
respond("video recorded successfully")
return
elif "access" in data:
access()
return
elif "where is" in data:
data = data.split(" ")
name = data[-1]
url = "https://www.google.com/maps/place/"+name
webbrowser.get('chrome').open_new(url)
time.sleep(5)
return
elif "write a note" in data:
respond("What should i write, sir!")
data = listen()
file = open('note.txt', 'w')
file.write(data)
respond("noted successfully")
return
elif "execute" in data:
execute_commands()
return
elif "upcoming events" in data or "scheduled events" in data or "events" in data:
events = calendar_events()
return
elif "game" in data or "play" in data:
try:
tic_tac_toe()
return
except:
return
elif "create event" in data:
create_event()
return
elif "speed test" in data:
try:
respond("sure! wait a second to measure")
st = speedtest.Speedtest()
server_names = []
st.get_servers(server_names)
ping = st.results.ping
downlink_Mbps = round(st.download() / 1000000, 2)
uplink_Mbps = round(st.upload() / 1000000, 2)
respond('ping {} ms'.format(ping))
respond("The uplink is {} Mbps".format(uplink_Mbps))
respond("The downlink is {}Mbps".format(downlink_Mbps))
return
except:
respond ("I couldn't run a speedtest")
return
elif "memory" in data:
process_id = os.getpid()
py = psutil.Process(process_id)
memory_use = round(py.memory_info()[0]/2. **30, 2)
respond("I use {} Gb of memory".format(memory_use))
return
elif "internet connection" in data or "internet" in data:
if internet_availability():
respond("Internet Connection is okay!")
return
elif 'email to' in data:
try:
respond("Sir, give me your message")
print('Give message.......')
content = takeCommand()
to = "receiver email address"
sendEmail(to, content)
print('Sending mail........')
respond("Email has been sent!")
except Exception as e:
print(e)
respond("Sorry master . I am not able to send this email")
#from extract import extract_news_from_page, get_full_html_from_news, get_title, content_sportv, extract_text_from_news_link
from googlesearch import search
query = "globoesporte.globo.com/futebol/ /noticia/2016"
result = search(query,
tld='com',
lang='pt-br',
num=10,
start=0,
stop=50,
pause=2.0)
news_links = []
for r in result:
if "/2016/" in r:
news_links.append(r)
print(news_links)
wordcount = {}
for word in a.lower().split():
word = word.replace(".", "")
word = word.replace(",", "")
word = word.replace(":", "")
word = word.replace("\"", "")
word = word.replace("!", "")
word = word.replace("?", "")
if word not in stopwords:
if word not in wordcount:
wordcount[word] = 1
else:
wordcount[word] += 1
# Print most common word
n_print = int(input("How many key words to google?: "))
word_counter = collections.Counter(wordcount)
googleString = ""
for word, count in word_counter.most_common(n_print):
googleString = googleString + " " + word
try:
from googlesearch import search
except ImportError:
print("No module named 'google' found")
for j in search(googleString, tld="co.in", num=10, stop=5, pause=2):
print(j)
file.close()
def main():
running = True
while running:
#query = "U.S. president after Lincoln, almost impeached by the Radical Republicans quizlet"
query = input("Whats the question? (Type 'q' to quit)\n\n")
if query == "q":
running = False
break
# Get all the urls
urls = []
#os.environ['HTTP_PROXY'] = 'http://172.16.0.3:8888'
for j in search(query,
tld="co.in",
num=numSites,
stop=numSites,
pause=2):
if ("quizlet" in j):
n = findnth(j, "/", 3)
jfinal = j[0:n + 1]
urls.append(jfinal)
#print(jfinal)
# Check data from quizlets to see if theres relevant stuff
pp = pprint.PrettyPrinter(indent=4)
found = False
for url in urls:
data = get_data_from(url) # Just doing the first one for now
for pair in data:
t = pair["term"]
d = pair["definition"]
keyword_prune = prune(query.lower())
matchedT = re.findall(keyword_prune, t)
matchedD = re.findall(keyword_prune, d)
if len(matchedT) != 0 or len(matchedD) != 0:
found = True
print(
"\n\n -------------------------Found! (with prune)-------------------------\n\n"
)
pp.pprint(pair)
print(
"\n\n ---------------------------------------------------------------------\n\n"
)
# Now do the exact same thing with lnsw method
if not found:
for pair in data:
t = pair["term"]
d = pair["definition"]
keyword_lnsw = LNSW(query)
if keyword_lnsw == None:
print("None keyword_lnsw")
exit
matchedT = re.findall(keyword_lnsw, t)
matchedD = re.findall(keyword_lnsw, d)
if len(matchedT) != 0 or len(matchedD) != 0:
found = True
print(
"\n\n -------------------------Found! (with LNSW:",
keyword_lnsw, ")-------------------------\n\n")
pp.pprint(pair)
print(
"\n\n -------------------------------------------------------------\n\n"
)
#print(matches)
#pp.pprint(data)
if not found: print("\nNothing found.\n")
import speech_recognition as sr
import time
import webbrowser
from googlesearch import search
f=open('url.txt','w')
print("press 1 for keyboard and Press 2 for voice search")
choice=input()
if choice== '1':
web=input("Please enter here : ")
print(web)
webbrowser.open_new_tab("https://www.google.com/search?q="+web)
url=[]
for i in search(web,stop=10):
print(i)
time.sleep(3)
f.write(i+'\n')
url.append(i)
print(url)
f.close()
elif choice=='2':
def recognize_speech_from_mic(recognizer,microphone):
with microphone as source:
audio=recognizer.listen(source)
response={
"success": True,
"error": None,
"transcription": None,
}
try:
reponse["transcription"]=recognizer.recognize_google(audio)
except sr.RequestError:
def google_query(query):
link = []
for j in search(query, tld="ca", num=10, stop=10, pause=2):
link.append(j)
return link
elif latest < requested:
print("That comic doesn't exist yet silly!")
else:
url = (f'{url}{comicNumber}')
webbrowser.open_new(url)
except:
print("An error occured. Perhaps you didn't enter an integer, or you don't have a recognized web browser, or dark magic interfered. The world may never know.")
webbrowser.open_new("https://xkcd.com/2200/")
elif searchType == "phrase":
pattern = r"^https?://xkcd.com/\d+/$" # Matches url for an xkcd, with or without https
referencePhrase = input("What is the relevant phrase?")
num_results = input("How many xkcds would you like to search for?")
query = ("site:xkcd.com " + str(referencePhrase))
try:
i = int(num_results)
for result in search(query, num=20):
if i <= 0:
break
if re.match(pattern, result) is not None: # Result matches pattern
i -= 1
webbrowser.open_new(result)
except:
print("An error occured. Perhaps you didn't enter an integer for the number of searches, or you don't have google, or maybe its all my fault and I really am a disappointment like my parents said.")
webbrowser.open_new("https://xkcd.com/2200/")
elif searchType == "random":
newest_comic = asyncio.run(latest_comic_num())
comic_num = random.randint(1, newest_comic)
random_url = (f"{url}{comic_num}")
webbrowser.open_new(random_url)
else:
webbrowser.open_new("https://www.youtube.com/watch?v=dQw4w9WgXcQ")
from googlesearch import search
file = open('search.txt', 'r')
count = 0
while True:
count += 1
line = file.readline()
if not line:
break
linee = line.strip()
print(linee)
for url in search(
linee, tld="co.in", num=10, pause=10
): #you can change The Domain You Want By Change The Tld Vaule In This Case co.in
print(url)
pass
pass
# cannot scrape the title of a web page containing a pdf file
continue
# sometimes google gives a numeric IP as of arxiv.
url = 'https://arxiv.org/' + '/'.join(
url.replace('https://', '').split('/')[-2:])
try:
url_title = google_scrape(url)
except:
url_title = ''
print('url ', url)
print('url title ', url_title)
urls.append({
'url_title': url_title,
'url': url,
'query': paper_title,
})
if os.path.isdir(output_json_dir):
with open(os.path.join(output_json_dir, 'query_urls.json'),
'a') as f_out:
json.dump(urls, f_out, indent=4, sort_keys=True)
return urls
if __name__ == '__main__':
query = 'Response object above tell'
for url in search(query, stop=3):
a = google_scrape(url)
print("url", url)
print("Title: " + a)
print(" ")
import webbrowser
import googlesearch
from googlesearch import search
try:
from googlesearch import search
except ImportError:
print("No module named 'google' found")
# to search
query = "whatsapp"
for j in search(query, tld="co.in", num=10, stop=1, pause=2):
webbrowser.open(j)
def extractFraseGoogle(frase, cantRes):
print("Procurando emails...Aguarde")
print("Esta operacao pode demorar varios minutos")
try:
listUrl = []
listEmails = []
for url in search(frase, stop=cantRes):
listUrl.append(url)
for i in listUrl:
try:
req = urllib.request.Request(i,
data=None,
headers={'User-Agent': ua.random})
try:
conn = urllib.request.urlopen(req)
except timeout:
print("Bad Url..")
time.sleep(2)
pass
except (HTTPError, URLError):
print("Bad Url..")
time.sleep(2)
pass
status = conn.getcode()
contentType = conn.info().get_content_type()
if (status != 200 or contentType == "audio/mpeg"):
print("Bad Url..")
time.sleep(2)
pass
html = conn.read()
soup = BeautifulSoup(html, "lxml")
links = soup.find_all('a')
print("Serao analizados " + str(len(links) + 1) + " Urls...")
time.sleep(2)
for tag in links:
link = tag.get('href', None)
if link is not None:
# Fix TimeOut
searchSpecificLink(link, listEmails, frase)
except urllib.error.URLError as e:
print("Problems with the url:" + i)
print(e)
pass
except (http.client.IncompleteRead) as e:
print(e)
pass
except Exception as e:
print(e)
pass
print("")
print("*******")
print("Finish")
print("*******")
input("Aperte return para continuar")
menu()
except KeyboardInterrupt:
input("Aperte return para continuar")
menu()
except Exception as e:
print(e)
input("Aperte enter para continuar")
menu()
speak("Here you go to Google")
print("* J: Here you go to Google \n")
webbrowser.open("google.com")
elif 'open stackoverflow' in query:
speak("Here you go to Stack Over flow.Happy coding")
print("* J: Here you go to stackoverflow ")
webbrowser.open("stackoverflow.com")
elif "wikipedia" in query:
print("* J: Here you go to wikipedia")
webbrowser.open("wikipedia.com")
elif 'search for' in query:
x=re.search('search for',query)
speak("Finding results")
print("J: Finding results\n")
query=query[x.start()+10:]
for j in search(query,tld="co.in",num=1, stop=1):
print(j)
webbrowser.open(j)
elif 'news' in query:
speak('here are some top news from the times of india')
print('J: Here are some top news from the times of india')
webbrowser.open("https://timesofindia.indiatimes.com/india")
# STORY
elif 'tell me a story' in query:
speak("Reading a story book")
content=takeCommand()
speakstory()
# PLAY MOVIE
elif 'play movie' in query:
speak("Playing your playlist sir")
i+=1
return i
def vuln_test(url):
try:
response =urllib2.urlopen(url)
soup = BeautifulSoup( response.read(), 'html.parser' )
url2=url+"'"
response2=urllib2.urlopen(url2)
soup2 = BeautifulSoup(response2.read(),'html.parser')
if soup!=soup2 :
if word_err(soup2) > -1 :
print "\n[%s*%s]Possible SQL vulnerability => %s "% (green,norm,url2)
except urllib2.HTTPError :
pass
except urllib2.URLError:
pass
credit()
dork =raw_input("Inserire una dork (es: 'inurl:index.php?id=') => ")
try:
url_list=search(dork)
for url in url_list:
vuln_test(url)
except urllib2.HTTPError:
print "%sGoogle ban your IP%s (restart connection) " %(red,norm)
def generate_data_set(url):
data_set = []
# Converts the given URL into standard format
if not re.match(r"^https?", url):
url = "http://" + url
# Stores the response of the given URL
try:
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
except:
response = ""
soup = -999
# Extracts domain from the given URL
domain = re.findall(r"://([^/]+)/?", url)[0]
if re.match(r"^www.", domain):
domain = domain.replace("www.", "")
# Requests all the information about the domain
whois_response = whois.whois(domain)
rank_checker_response = requests.post(
"https://www.checkpagerank.net/index.php", {"name": domain})
# Extracts global rank of the website
try:
global_rank = int(
re.findall(r"Global Rank: ([0-9]+)",
rank_checker_response.text)[0])
except:
global_rank = -1
# 1.having_IP_Address
try:
ipaddress.ip_address(url)
data_set.append(-1)
except:
data_set.append(1)
# 2.URL_Length
if len(url) < 54:
data_set.append(1)
elif len(url) >= 54 and len(url) <= 75:
data_set.append(0)
else:
data_set.append(-1)
# 3.Shortining_Service
match = re.search(
'bit\.ly|goo\.gl|shorte\.st|go2l\.ink|x\.co|ow\.ly|t\.co|tinyurl|tr\.im|is\.gd|cli\.gs|'
'yfrog\.com|migre\.me|ff\.im|tiny\.cc|url4\.eu|twit\.ac|su\.pr|twurl\.nl|snipurl\.com|'
'short\.to|BudURL\.com|ping\.fm|post\.ly|Just\.as|bkite\.com|snipr\.com|fic\.kr|loopt\.us|'
'doiop\.com|short\.ie|kl\.am|wp\.me|rubyurl\.com|om\.ly|to\.ly|bit\.do|t\.co|lnkd\.in|'
'db\.tt|qr\.ae|adf\.ly|goo\.gl|bitly\.com|cur\.lv|tinyurl\.com|ow\.ly|bit\.ly|ity\.im|'
'q\.gs|is\.gd|po\.st|bc\.vc|twitthis\.com|u\.to|j\.mp|buzurl\.com|cutt\.us|u\.bb|yourls\.org|'
'x\.co|prettylinkpro\.com|scrnch\.me|filoops\.info|vzturl\.com|qr\.net|1url\.com|tweez\.me|v\.gd|tr\.im|link\.zip\.net',
url)
if match:
data_set.append(-1)
else:
data_set.append(1)
# 4.having_At_Symbol
if re.findall("@", url):
data_set.append(-1)
else:
data_set.append(1)
# 5.double_slash_redirecting
list = [x.start(0) for x in re.finditer('//', url)]
if list[len(list) - 1] > 6:
data_set.append(-1)
else:
data_set.append(1)
# 6.Prefix_Suffix
if re.findall(r"https?://[^\-]+-[^\-]+/", url):
data_set.append(-1)
else:
data_set.append(1)
# 7.having_Sub_Domain
if len(re.findall("\.", url)) == 1:
data_set.append(1)
elif len(re.findall("\.", url)) == 2:
data_set.append(0)
else:
data_set.append(-1)
# 8.SSLfinal_State
try:
if response.text:
data_set.append(1)
except:
data_set.append(-1)
# 9.Domain_registeration_length
expiration_date = whois_response.expiration_date
registration_length = 0
try:
expiration_date = min(expiration_date)
today = time.strftime('%Y-%m-%d')
today = datetime.strptime(today, '%Y-%m-%d')
registration_length = abs((expiration_date - today).days)
if registration_length / 365 <= 1:
data_set.append(-1)
else:
data_set.append(1)
except:
data_set.append(-1)
# 10.Favicon
if soup == -999:
data_set.append(-1)
else:
try:
for head in soup.find_all('head'):
for head.link in soup.find_all('link', href=True):
dots = [
x.start(0)
for x in re.finditer('\.', head.link['href'])
]
if url in head.link['href'] or len(
dots) == 1 or domain in head.link['href']:
data_set.append(1)
raise StopIteration
else:
data_set.append(-1)
raise StopIteration
except StopIteration:
pass
#11. port
try:
port = domain.split(":")[1]
if port:
data_set.append(-1)
else:
data_set.append(1)
except:
data_set.append(1)
#12. HTTPS_token
if re.findall(r"^https://", url):
data_set.append(1)
else:
data_set.append(-1)
#13. Request_URL
i = 0
success = 0
if soup == -999:
data_set.append(-1)
else:
for img in soup.find_all('img', src=True):
dots = [x.start(0) for x in re.finditer('\.', img['src'])]
if url in img['src'] or domain in img['src'] or len(dots) == 1:
success = success + 1
i = i + 1
for audio in soup.find_all('audio', src=True):
dots = [x.start(0) for x in re.finditer('\.', audio['src'])]
if url in audio['src'] or domain in audio['src'] or len(dots) == 1:
success = success + 1
i = i + 1
for embed in soup.find_all('embed', src=True):
dots = [x.start(0) for x in re.finditer('\.', embed['src'])]
if url in embed['src'] or domain in embed['src'] or len(dots) == 1:
success = success + 1
i = i + 1
for iframe in soup.find_all('iframe', src=True):
dots = [x.start(0) for x in re.finditer('\.', iframe['src'])]
if url in iframe['src'] or domain in iframe['src'] or len(
dots) == 1:
success = success + 1
i = i + 1
try:
percentage = success / float(i) * 100
if percentage < 22.0:
dataset.append(1)
elif ((percentage >= 22.0) and (percentage < 61.0)):
data_set.append(0)
else:
data_set.append(-1)
except:
data_set.append(1)
#14. URL_of_Anchor
percentage = 0
i = 0
unsafe = 0
if soup == -999:
data_set.append(-1)
else:
for a in soup.find_all('a', href=True):
# 2nd condition was 'JavaScript ::void(0)' but we put JavaScript because the space between javascript and :: might not be
# there in the actual a['href']
if "#" in a['href'] or "javascript" in a['href'].lower(
) or "mailto" in a['href'].lower() or not (url in a['href']
or domain in a['href']):
unsafe = unsafe + 1
i = i + 1
try:
percentage = unsafe / float(i) * 100
except:
data_set.append(1)
if percentage < 31.0:
data_set.append(1)
elif ((percentage >= 31.0) and (percentage < 67.0)):
data_set.append(0)
else:
data_set.append(-1)
#15. Links_in_tags
i = 0
success = 0
if soup == -999:
data_set.append(-1)
else:
for link in soup.find_all('link', href=True):
dots = [x.start(0) for x in re.finditer('\.', link['href'])]
if url in link['href'] or domain in link['href'] or len(dots) == 1:
success = success + 1
i = i + 1
for script in soup.find_all('script', src=True):
dots = [x.start(0) for x in re.finditer('\.', script['src'])]
if url in script['src'] or domain in script['src'] or len(
dots) == 1:
success = success + 1
i = i + 1
try:
percentage = success / float(i) * 100
except:
data_set.append(1)
if percentage < 17.0:
data_set.append(1)
elif ((percentage >= 17.0) and (percentage < 81.0)):
data_set.append(0)
else:
data_set.append(-1)
#16. SFH
for form in soup.find_all('form', action=True):
if form['action'] == "" or form['action'] == "about:blank":
data_set.append(-1)
break
elif url not in form['action'] and domain not in form['action']:
data_set.append(0)
break
else:
data_set.append(1)
break
#17. Submitting_to_email
if response == "":
data_set.append(-1)
else:
if re.findall(r"[mail\(\)|mailto:?]", response.text):
data_set.append(1)
else:
data_set.append(-1)
#18. Abnormal_URL
if response == "":
data_set.append(-1)
else:
if response.text == "":
data_set.append(1)
else:
data_set.append(-1)
#19. Redirect
if response == "":
data_set.append(-1)
else:
if len(response.history) <= 1:
data_set.append(-1)
elif len(response.history) <= 4:
data_set.append(0)
else:
data_set.append(1)
#20. on_mouseover
if response == "":
data_set.append(-1)
else:
if re.findall("<script>.+onmouseover.+</script>", response.text):
data_set.append(1)
else:
data_set.append(-1)
#21. RightClick
if response == "":
data_set.append(-1)
else:
if re.findall(r"event.button ?== ?2", response.text):
data_set.append(1)
else:
data_set.append(-1)
#22. popUpWidnow
if response == "":
data_set.append(-1)
else:
if re.findall(r"alert\(", response.text):
data_set.append(1)
else:
data_set.append(-1)
#23. Iframe
if response == "":
data_set.append(-1)
else:
if re.findall(r"[<iframe>|<frameBorder>]", response.text):
data_set.append(1)
else:
data_set.append(-1)
#24. age_of_domain
if response == "":
data_set.append(-1)
else:
try:
registration_date = re.findall(
r'Registration Date:</div><div class="df-value">([^<]+)</div>',
whois_response.text)[0]
if diff_month(date.today(), date_parse(registration_date)) >= 6:
data_set.append(-1)
else:
data_set.append(1)
except:
data_set.append(1)
#25. DNSRecord
dns = 1
try:
d = whois.whois(domain)
except:
dns = -1
if dns == -1:
data_set.append(-1)
else:
if registration_length / 365 <= 1:
data_set.append(-1)
else:
data_set.append(1)
#26. web_traffic
try:
rank = BeautifulSoup(
urllib.request.urlopen(
"http://data.alexa.com/data?cli=10&dat=s&url=" + url).read(),
"xml").find("REACH")['RANK']
rank = int(rank)
if (rank < 100000):
data_set.append(1)
else:
data_set.append(0)
except TypeError:
data_set.append(-1)
#27. Page_Rank
try:
if global_rank > 0 and global_rank < 100000:
data_set.append(-1)
else:
data_set.append(1)
except:
data_set.append(1)
#28. Google_Index
site = search(url, 5)
if site:
data_set.append(1)
else:
data_set.append(-1)
#29. Links_pointing_to_page
if response == "":
data_set.append(-1)
else:
number_of_links = len(re.findall(r"<a href=", response.text))
if number_of_links == 0:
data_set.append(1)
elif number_of_links <= 2:
data_set.append(0)
else:
data_set.append(-1)
#30. Statistical_report
url_match = re.search(
'at\.ua|usa\.cc|baltazarpresentes\.com\.br|pe\.hu|esy\.es|hol\.es|sweddy\.com|myjino\.ru|96\.lt|ow\.ly',
url)
try:
ip_address = socket.gethostbyname(domain)
ip_match = re.search(
'146\.112\.61\.108|213\.174\.157\.151|121\.50\.168\.88|192\.185\.217\.116|78\.46\.211\.158|181\.174\.165\.13|46\.242\.145\.103|121\.50\.168\.40|83\.125\.22\.219|46\.242\.145\.98|'
'107\.151\.148\.44|107\.151\.148\.107|64\.70\.19\.203|199\.184\.144\.27|107\.151\.148\.108|107\.151\.148\.109|119\.28\.52\.61|54\.83\.43\.69|52\.69\.166\.231|216\.58\.192\.225|'
'118\.184\.25\.86|67\.208\.74\.71|23\.253\.126\.58|104\.239\.157\.210|175\.126\.123\.219|141\.8\.224\.221|10\.10\.10\.10|43\.229\.108\.32|103\.232\.215\.140|69\.172\.201\.153|'
'216\.218\.185\.162|54\.225\.104\.146|103\.243\.24\.98|199\.59\.243\.120|31\.170\.160\.61|213\.19\.128\.77|62\.113\.226\.131|208\.100\.26\.234|195\.16\.127\.102|195\.16\.127\.157|'
'34\.196\.13\.28|103\.224\.212\.222|172\.217\.4\.225|54\.72\.9\.51|192\.64\.147\.141|198\.200\.56\.183|23\.253\.164\.103|52\.48\.191\.26|52\.214\.197\.72|87\.98\.255\.18|209\.99\.17\.27|'
'216\.38\.62\.18|104\.130\.124\.96|47\.89\.58\.141|78\.46\.211\.158|54\.86\.225\.156|54\.82\.156\.19|37\.157\.192\.102|204\.11\.56\.48|110\.34\.231\.42',
ip_address)
if url_match:
data_set.append(-1)
elif ip_match:
data_set.append(-1)
else:
data_set.append(1)
except:
print('Connection problem. Please check your internet connection!')
print(data_set)
return data_set
#! /usr/bin/python3 import google import sys from googlesearch import search query=sys.argv[1] for i in search(query,tld="co.in",num=5,start=0,stop=5): print(i)
byewishing = [
'bye bye', 'Have a good day', 'I am happy to help you',
'see you again later', 'see you next time!farewell'
]
while True:
# query=takecommand().lower()
query = input()
checkgreet = query.split(" ")
if any(item in checkgreet for item in (grettings or wishes)):
greet = random.choice(tuple(grettings))
speak(greet)
elif 'search' in query:
query = query.replace("search", "")
if 'google' in query:
query = query.replace('google', '')
for link in search(query, num_results=5, lang="en-in"):
webbrowser.open_new_tab(link)
elif 'ganna' in query:
speak('Searching on gaana')
query = query.replace('bye', '')
query = query.replace('play', '')
query = query.replace('song', '')
query = query.replace('on', '')
query = query.replace('in', '')
query = query.replace('ganna', '')
play_audio(query)
elif 'youtube' in query or 'you tube' in query:
speak('searching on youtube')
query = query.replace("youtube", "")
query = query.replace('on', '')
query = query.replace('in', '')
