| | 1 | + | import requests,json |
| | 2 | + | from bs4 import BeautifulSoup |
| | 3 | + | import argparse |
| | 4 | + | from tqdm import tqdm |
| | 5 | + | parser = argparse.ArgumentParser() |
| | 6 | + | required = parser.add_argument_group('required arguments') |
| | 7 | + | parser.add_argument("--proxy", default='localhost:9050', type=str, help="Set Tor proxy (default: 127.0.0.1:9050)") |
| | 8 | + | parser.add_argument("--output", default='output.txt', type=str, help="Output File (default: output.txt)") |
| | 9 | + | |
| | 10 | + | parser.add_argument("--search",type=str, help="search") |
| | 11 | + | args = parser.parse_args() |
| | 12 | + | proxies = {'http': 'socks5h://{}'.format(args.proxy), 'https': 'socks5h://{}'.format(args.proxy)} |
| | 13 | + | |
| | 14 | + | def clear(toclear): |
| | 15 | + | return(toclear.replace("\n","").replace(" ","")) |
| | 16 | + | def clearn(toclear): |
| | 17 | + | return(toclear.replace("\n"," ")) |
| | 18 | + | |
| | 19 | + | def scrape(): |
| | 20 | + | result = {} |
| | 21 | + | ahmia = "http://msydqstlz2kzerdg.onion/search/?q="+args.search |
| | 22 | + | response = requests.get(ahmia, proxies=proxies) |
| | 23 | + | #print(response) |
| | 24 | + | soup = BeautifulSoup(response.text, 'html.parser') |
| | 25 | + | result['ahmia'] = [] |
| | 26 | + | #pageNumber = clear(soup.find("span", id="pageResultEnd").get_text()) |
| | 27 | + | for i in tqdm(soup.findAll('li', attrs = {'class' : 'result'}),desc="Ahmia"): |
| | 28 | + | i = i.find('h4') |
| | 29 | + | result['ahmia'].append({"name":clear(i.get_text()),"link":i.find('a')['href'].replace("/search/search/redirect?search_term=search&redirect_url=","")}) |
| | 30 | + | |
| | 31 | + | urlTorchNumber = "http://xmh57jrzrnw6insl.onion/4a1f6b371c/search.cgi?cmd=Search!&np=1&q=" |
| | 32 | + | req = requests.get(urlTorchNumber+args.search,proxies=proxies) |
| | 33 | + | soup = BeautifulSoup(req.text, 'html.parser') |
| | 34 | + | result['urlTorch'] = [] |
| | 35 | + | pageNumber = "" |
| | 36 | + | for i in soup.find("table",attrs={"width":"100%"}).findAll("small"): |
| | 37 | + | if("of"in i.get_text()): |
| | 38 | + | pageNumber = i.get_text() |
| | 39 | + | pageNumber = round(float(clear(pageNumber.split("-")[1].split("of")[1]))/10) |
| | 40 | + | if(pageNumber>99): |
| | 41 | + | pageNumber=99 |
| | 42 | + | result['urlTorch'] = [] |
| | 43 | + | for n in tqdm(range(1,pageNumber+1),desc="Torch"): |
| | 44 | + | urlTorch = "http://xmh57jrzrnw6insl.onion/4a1f6b371c/search.cgi?cmd=Search!&np={}&q={}".format(n,args.search) |
| | 45 | + | #print(urlTorch) |
| | 46 | + | try: |
| | 47 | + | req = requests.get(urlTorchNumber+args.search,proxies=proxies) |
| | 48 | + | soup = BeautifulSoup(req.text, 'html.parser') |
| | 49 | + | for i in soup.findAll('dl'): |
| | 50 | + | result['urlTorch'].append({"name":clear(i.find('a').get_text()),"link":i.find('a')['href']}) |
| | 51 | + | except: |
| | 52 | + | pass |
| | 53 | + | |
| | 54 | + | darksearchnumber = "http://darksearch.io/api/search?query=" |
| | 55 | + | req = requests.get(darksearchnumber+args.search,proxies=proxies) |
| | 56 | + | cookies = req.cookies |
| | 57 | + | if(req.status_code==200): |
| | 58 | + | result['darksearch']=[] |
| | 59 | + | #print(req) |
| | 60 | + | req = req.json() |
| | 61 | + | if(req['last_page']>30): |
| | 62 | + | pageNumber=30 |
| | 63 | + | else: |
| | 64 | + | pageNumber=req['last_page'] |
| | 65 | + | #print(pageNumber) |
| | 66 | + | for i in tqdm(range(1,pageNumber+1),desc="Darksearch io"): |
| | 67 | + | #print(i) |
| | 68 | + | darksearch = "http://darksearch.io/api/search?query={}&page=".format(args.search) |
| | 69 | + | req = requests.get(darksearch+str(pageNumber),proxies=proxies,cookies=cookies) |
| | 70 | + | if(req.status_code==200): |
| | 71 | + | for r in req.json()['data']: |
| | 72 | + | result['darksearch'].append({"name":r["title"],"link":r["link"]}) |
| | 73 | + | |
| | 74 | + | else: |
| | 75 | + | print("Rate limit darksearch.io !") |
| | 76 | + | |
| | 77 | + | result['onionland'] = [] |
| | 78 | + | for n in tqdm(range(1,400),desc="OnionLand"): |
| | 79 | + | onionland = "http://3bbaaaccczcbdddz.onion/search?q={}&page={}".format(args.search,n) |
| | 80 | + | #print(urlTorch) |
| | 81 | + | req = requests.get(onionland,proxies=proxies) |
| | 82 | + | if(req.status_code==200): |
| | 83 | + | soup = BeautifulSoup(req.text, 'html.parser') |
| | 84 | + | for i in soup.findAll('div',attrs={"class":"result-block"}): |
| | 85 | + | if('''<span class="label-ad">Ad</span>''' not in i): |
| | 86 | + | #print({"name":i.find('div',attrs={'class':"title"}).get_text(),"link":clear(i.find('div',attrs={'class':"link"}).get_text())}) |
| | 87 | + | result['onionland'].append({"name":i.find('div',attrs={'class':"title"}).get_text(),"link":clear(i.find('div',attrs={'class':"link"}).get_text())}) |
| | 88 | + | else: |
| | 89 | + | break |
| | 90 | + | |
| | 91 | + | print("Ahmia : " + str(len(result['ahmia']))) |
| | 92 | + | print("Torch : "+str(len(result['urlTorch']))) |
| | 93 | + | print("Darksearch io : "+str(len(result['darksearch']))) |
| | 94 | + | print("Onionland : "+str(len(result['onionland']))) |
| | 95 | + | print("Total of {} links !\nExported to {}".format(str(len(result['ahmia'])+len(result['urlTorch'])+len(result['darksearch'])+len(result['onionland'])),args.output)) |
| | 96 | + | f= open(args.output,"w+") |
| | 97 | + | for i in result['urlTorch']: |
| | 98 | + | f.write("name : {} link: {}\n".format(clearn(i["name"]),i["link"])) |
| | 99 | + | for i in result['onionland']: |
| | 100 | + | f.write("name: {} link : {}\n".format(clearn(i["name"]),i["link"])) |
| | 101 | + | for i in result['ahmia']: |
| | 102 | + | f.write("name : {} link : {}\n".format(clearn(i["name"]),i["link"])) |
| | 103 | + | for i in result['darksearch']: |
| | 104 | + | f.write("name : {} link : {}\n".format(clearn(i["name"]),i["link"])) |
| | 105 | + | |
| | 106 | + | f.close() |
| | 107 | + | scrape() |
| | 108 | + | |
