Python googlesearch.search方法代码示例

# 需要导入模块: import googlesearch [as 别名]
# 或者: from googlesearch import search [as 别名]
def getposts(web):
    web0 = web
    if "@" in web0:
        web0 = web0.split("@")[1]
    site = str(web0)
    def clear_cookie():
        fo = open(".google-cookie", "w")
        fo.close()


    def google_it (dork):
        clear_cookie()
        for title in search(dork, stop=30):
            print(B+' [!] Post Found :> '+C+title)
            time.sleep(0.5)

    try:
        print(C+" [*] Finding Pastebin posts ...\n")
        google_it("site:pastebin.com intext:"+site+"")

    except urllib.error.HTTPError as err:
        if err.code == 503:
            print(R+' [-] Captcha appeared...\n')
            pass 

# 需要导入模块: import googlesearch [as 别名]
# 或者: from googlesearch import search [as 别名]
def googleSearch():

    try:
        time.sleep(0.4)
        #print(R+'\n   ===========================')
        print(R+'\n    G O O G L E   S E A R C H')
        print(R+'   ––·‹›·––·‹›·––·‹›·––·‹›·––·\n')
                    
        lol = input(O+ " [§] QUERY :> " + color.END)
        time.sleep(0.8)
        m = input(C+' [§] Search limit (not recommended above 30) :> ')
        print(C+ " [!] Below are the list of websites with info on '" +lol+ "'")
        x = search(lol, tld='com', lang='es', stop=int(m))
        for url in x:
            print(O+"   [!] Site Found :>"+C+color.TR3+C+G + url+C+color.TR2+C)
            q = open('.google-cookie','w')
            q.close()
    except urllib.error.HTTPError:
        print(R+' [-] You have used google many times.')
        print(R+' [-] Service temporarily unavailable.') 

# 需要导入模块: import googlesearch [as 别名]
# 或者: from googlesearch import search [as 别名]
def d0rkit (site,dork,filename):
	clear_cookie()
	out=open(filename,"a")
	for title in search(
		dork, 
		tld = 'com',  # The top level domain
        lang = 'en',  # The language
        num = 10,     # Number of results per page
        start = 0,    # First result to retrieve
        stop = 50,  # Last result to retrieve
        pause = 2.0,  # This is required to bypass google's limiting unfortunately
		):
            	print(title)
            	out.write(title)
            	out.write("\n")
	out.close() 

# 需要导入模块: import googlesearch [as 别名]
# 或者: from googlesearch import search [as 别名]
def statistical_report(url, hostname):
    try:
        ip_address = socket.gethostbyname(hostname)
    except:
        return -1
    url_match = re.search(
        r'at\.ua|usa\.cc|baltazarpresentes\.com\.br|pe\.hu|esy\.es|hol\.es|sweddy\.com|myjino\.ru|96\.lt|ow\.ly', url)
    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:
        return -1
    elif ip_match:
        return -1
    else:
        return 1 

# 需要导入模块: import googlesearch [as 别名]
# 或者: from googlesearch import search [as 别名]
def cli(google,wiki):
	browser = mechanize.Browser()
	browser.set_handle_robots(False)	#Allows everything to be written
	cookies = mechanize.CookieJar()
	browser.set_cookiejar(cookies)
	browser.addheaders = [('User-agent', 'Mozilla/5.0 (X11; U; Linux i686; en-US) AppleWebKit/534.7 (KHTML, like Gecko) Chrome/7.0.517.41 Safari/534.7')]
	browser.set_handle_refresh(False)	#Sometimes hangs without this
	if(google):
		query = raw_input("Enter the topic you want to search about: ")
		for link in search(query, tld="co.in", num=10, stop=1, pause=2):
			print link
	if(wiki):
		wiki_topic = raw_input('Enter the topic you want to read about: ')
		result = wikipedia.page(title=wiki_topic,auto_suggest=True,redirect=True, preload=False)
		wiki_content = result.content
		print wiki_content 

# 需要导入模块: import googlesearch [as 别名]
# 或者: from googlesearch import search [as 别名]
def main():

    if args.domain == None:
        # Use sys.argv[0] here so we never have to update this line if we change the script name
        print("Please enter the domain you wish to target: "+ sys.argv[0] +" -d target.com")
        # -1 exit code error
        exit(-1)
    else:
        site = args.domain
    
    # This is where the results will be stored
    results_list = []

    # A keyed list of dorks
    dorks = {
        'site' : 'site:"'+site+'" inurl:"wp-" OR inurl:"plugin" OR inurl:"upload" OR inurl:"download"',
        'php' : 'inurl:"?id=" AND filetype:"php"',
        'loginPage': "loginpage.txt"
    }

    # Loop over the dict of dorks
    for dork in dorks:

        # Verbose output
        if args.verbose :
            print("Currently Running : " + dorks[dork])

        # Perform the google search
        search_results = search(dorks[dork], tld='com', lang='en', num=10, start=0, stop=None, pause=2.0)
        
        # Loop over the search results and add them to the results_list variable
        for i in search_results:
            results_list.append(i)
    # Print the results_list
    print(results_list) 

# 需要导入模块: import googlesearch [as 别名]
# 或者: from googlesearch import search [as 别名]
def having_ip_address(url):
    ip_address_pattern = ipv4_pattern + "|" + ipv6_pattern
    match = re.search(ip_address_pattern, url)
    return -1 if match else 1 

# 需要导入模块: import googlesearch [as 别名]
# 或者: from googlesearch import search [as 别名]
def shortening_service(url):
    match = re.search(shortening_services, url)
    return -1 if match else 1 

# 需要导入模块: import googlesearch [as 别名]
# 或者: from googlesearch import search [as 别名]
def having_at_symbol(url):
    match = re.search('@', url)
    return -1 if match else 1 

# 需要导入模块: import googlesearch [as 别名]
# 或者: from googlesearch import search [as 别名]
def double_slash_redirecting(url):
    # since the position starts from 0, we have given 6 and not 7 which is according to the document.
    # It is convenient and easier to just use string search here to search the last occurrence instead of re.
    last_double_slash = url.rfind('//')
    return -1 if last_double_slash > 6 else 1 

# 需要导入模块: import googlesearch [as 别名]
# 或者: from googlesearch import search [as 别名]
def prefix_suffix(domain):
    match = re.search('-', domain)
    return -1 if match else 1 

# 需要导入模块: import googlesearch [as 别名]
# 或者: from googlesearch import search [as 别名]
def https_token(url):
    match = re.search(http_https, url)
    if match and match.start() == 0:
        url = url[match.end():]
    match = re.search('http|https', url)
    return -1 if match else 1 

# 需要导入模块: import googlesearch [as 别名]
# 或者: from googlesearch import search [as 别名]
def abnormal_url(domain, url):
    hostname = domain.name
    match = re.search(hostname, url)
    return 1 if match else -1


# IFrame Redirection 

# 需要导入模块: import googlesearch [as 别名]
# 或者: from googlesearch import search [as 别名]
def google_index(url):
    site = search(url, 5)
    return 1 if site else -1 

# 需要导入模块: import googlesearch [as 别名]
# 或者: from googlesearch import search [as 别名]
def get_hostname_from_url(url):
    hostname = url
    # TODO: Put this pattern in patterns.py as something like - get_hostname_pattern.
    pattern = "https://|http://|www.|https://www.|http://www."
    pre_pattern_match = re.search(pattern, hostname)

    if pre_pattern_match:
        hostname = hostname[pre_pattern_match.end():]
        post_pattern_match = re.search("/", hostname)
        if post_pattern_match:
            hostname = hostname[:post_pattern_match.start()]

    return hostname

# TODO: Put the DNS and domain code into a function.