1 | | - | import requests,json |
2 | | - | from bs4 import BeautifulSoup |
3 | 1 | | import argparse |
| 2 | + | import csv |
| 3 | + | import math |
| 4 | + | import re |
| 5 | + | import time |
| 6 | + | from datetime import datetime |
| 7 | + | from functools import reduce |
| 8 | + | from random import choice |
| 9 | + | |
| 10 | + | from multiprocessing import Pool, cpu_count, current_process, freeze_support |
4 | 11 | | from tqdm import tqdm |
5 | | - | parser = argparse.ArgumentParser() |
6 | | - | required = parser.add_argument_group('required arguments') |
| 12 | + | |
| 13 | + | import requests |
| 14 | + | import urllib.parse as urlparse |
| 15 | + | from urllib.parse import parse_qs |
| 16 | + | from urllib.parse import quote |
| 17 | + | from urllib.parse import unquote |
| 18 | + | from bs4 import BeautifulSoup |
| 19 | + | from urllib3.exceptions import ProtocolError |
| 20 | + | |
| 21 | + | import engines |
| 22 | + | |
| 23 | + | desktop_agents = [ |
| 24 | + | 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36', |
| 25 | + | 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36', |
| 26 | + | 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) ' |
| 27 | + | 'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36', |
| 28 | + | 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_1) ' |
| 29 | + | 'AppleWebKit/602.2.14 (KHTML, like Gecko) Version/10.0.1 Safari/602.2.14', |
| 30 | + | 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.71 Safari/537.36', |
| 31 | + | 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_1) ' |
| 32 | + | 'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36', |
| 33 | + | 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6) ' |
| 34 | + | 'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36', |
| 35 | + | 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.71 Safari/537.36', |
| 36 | + | 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36', |
| 37 | + | 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:50.0) Gecko/20100101 Firefox/50.0' |
| 38 | + | ] |
| 39 | + | |
| 40 | + | supported_engines = engines.ENGINES |
| 41 | + | |
| 42 | + | available_csv_fields = [ |
| 43 | + | "engine", |
| 44 | + | "name", |
| 45 | + | "link", |
| 46 | + | "domain" |
| 47 | + | ] |
| 48 | + | |
| 49 | + | |
| 50 | + | def print_epilog(): |
| 51 | + | epilog = "Available CSV fields: \n\t" |
| 52 | + | for f in available_csv_fields: |
| 53 | + | epilog += " {}".format(f) |
| 54 | + | epilog += "\n" |
| 55 | + | epilog += "Supported engines: \n\t" |
| 56 | + | for e in supported_engines.keys(): |
| 57 | + | epilog += " {}".format(e) |
| 58 | + | return epilog |
| 59 | + | |
| 60 | + | |
| 61 | + | parser = argparse.ArgumentParser(epilog=print_epilog(), formatter_class=argparse.RawTextHelpFormatter) |
7 | 62 | | 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)") |
| 63 | + | parser.add_argument("--output", default='output_$SEARCH_$DATE.txt', type=str, |
| 64 | + | help="Output File (default: output_$SEARCH_$DATE.txt), where $SEARCH is replaced by the first " |
| 65 | + | "chars of the search string and $DATE is replaced by the datetime") |
| 66 | + | parser.add_argument("--continuous_write", type=bool, default=False, |
| 67 | + | help="Write progressively to output file (default: False)") |
| 68 | + | parser.add_argument("search", type=str, help="The search string or phrase") |
| 69 | + | parser.add_argument("--limit", type=int, default=0, help="Set a max number of pages per engine to load") |
| 70 | + | parser.add_argument("--engines", type=str, action='append', help='Engines to request (default: full list)', nargs="*") |
| 71 | + | parser.add_argument("--exclude", type=str, action='append', help='Engines to exclude (default: none)', nargs="*") |
| 72 | + | parser.add_argument("--fields", type=str, action='append', |
| 73 | + | help='Fields to output to csv file (default: engine name link), available fields are shown below', |
| 74 | + | nargs="*") |
| 75 | + | parser.add_argument("--field_delimiter", type=str, default=",", help='Delimiter for the CSV fields') |
| 76 | + | parser.add_argument("--mp_units", type=int, default=(cpu_count() - 1), help="Number of processing units (default: " |
| 77 | + | "core number minus 1)") |
9 | 78 | | |
10 | | - | parser.add_argument("--search",type=str, help="search") |
11 | 79 | | args = parser.parse_args() |
12 | 80 | | proxies = {'http': 'socks5h://{}'.format(args.proxy), 'https': 'socks5h://{}'.format(args.proxy)} |
| 81 | + | filename = args.output |
| 82 | + | field_delim = "," |
| 83 | + | if args.field_delimiter and len(args.field_delimiter) == 1: |
| 84 | + | field_delim = args.field_delimiter |
| 85 | + | |
| 86 | + | |
| 87 | + | def random_headers(): |
| 88 | + | return {'User-Agent': choice(desktop_agents), |
| 89 | + | 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'} |
| 90 | + | |
13 | 91 | | |
14 | 92 | | def clear(toclear): |
15 | | - | return(toclear.replace("\n","").replace(" ","")) |
16 | | - | def clearn(toclear): |
17 | | - | return(toclear.replace("\n"," ")) |
| 93 | + | str = toclear.replace("\n", " ") |
| 94 | + | str = ' '.join(str.split()) |
| 95 | + | return str |
| 96 | + | |
| 97 | + | |
| 98 | + | def get_parameter(url, parameter_name): |
| 99 | + | parsed = urlparse.urlparse(url) |
| 100 | + | return parse_qs(parsed.query)[parameter_name][0] |
| 101 | + | |
| 102 | + | |
| 103 | + | def get_proc_pos(): |
| 104 | + | return (current_process()._identity[0]) - 1 |
| 105 | + | |
| 106 | + | |
| 107 | + | def get_tqdm_desc(e_name, pos): |
| 108 | + | return "%20s (#%d)" % (e_name, pos) |
| 109 | + | |
| 110 | + | |
| 111 | + | def ahmia(searchstr): |
| 112 | + | results = [] |
| 113 | + | ahmia_url = supported_engines['ahmia'] + "/search/?q={}" |
| 114 | + | |
| 115 | + | pos = get_proc_pos() |
| 116 | + | with tqdm(total=1, initial=0, desc=get_tqdm_desc("Ahmia", pos), position=pos) as progress_bar: |
| 117 | + | response = requests.get(ahmia_url.format(quote(searchstr)), proxies=proxies, headers=random_headers()) |
| 118 | + | soup = BeautifulSoup(response.text, 'html5lib') |
| 119 | + | results = link_finder("ahmia", soup) |
| 120 | + | progress_bar.update() |
| 121 | + | |
| 122 | + | return results |
| 123 | + | |
| 124 | + | |
| 125 | + | def torch(searchstr): |
| 126 | + | results = [] |
| 127 | + | torch_url = supported_engines['torch'] + "/4a1f6b371c/search.cgi?cmd=Search!&np={}&q={}" |
| 128 | + | results_per_page = 10 |
| 129 | + | max_nb_page = 100 |
| 130 | + | if args.limit != 0: |
| 131 | + | max_nb_page = args.limit |
| 132 | + | |
| 133 | + | with requests.Session() as s: |
| 134 | + | s.proxies = proxies |
| 135 | + | s.headers = random_headers() |
| 136 | + | |
| 137 | + | req = s.get(torch_url.format(0, quote(searchstr))) |
| 138 | + | soup = BeautifulSoup(req.text, 'html5lib') |
| 139 | + | |
| 140 | + | page_number = 1 |
| 141 | + | for i in soup.find("table", attrs={"width": "100%"}).find_all("small"): |
| 142 | + | if i.get_text() is not None and "of" in i.get_text(): |
| 143 | + | page_number = math.ceil(float(clear(i.get_text().split("-")[1].split("of")[1])) / results_per_page) |
| 144 | + | if page_number > max_nb_page: |
| 145 | + | page_number = max_nb_page |
| 146 | + | |
| 147 | + | pos = get_proc_pos() |
| 148 | + | with tqdm(total=page_number, initial=0, desc=get_tqdm_desc("TORCH", pos), position=pos) as progress_bar: |
| 149 | + | |
| 150 | + | results = link_finder("torch", soup) |
| 151 | + | progress_bar.update() |
| 152 | + | |
| 153 | + | # Usually range is 2 to n+1, but TORCH behaves differently |
| 154 | + | for n in range(1, page_number): |
| 155 | + | req = s.get(torch_url.format(n, quote(searchstr))) |
| 156 | + | soup = BeautifulSoup(req.text, 'html5lib') |
| 157 | + | results = results + link_finder("torch", soup) |
| 158 | + | progress_bar.update() |
| 159 | + | |
| 160 | + | return results |
| 161 | + | |
| 162 | + | |
| 163 | + | def torch1(searchstr): |
| 164 | + | results = [] |
| 165 | + | torch1_url = supported_engines['torch1'] + "/search?q={}&cmd=Search!" |
| 166 | + | |
| 167 | + | pos = get_proc_pos() |
| 168 | + | with tqdm(total=1, initial=0, desc=get_tqdm_desc("TORCH 1", pos), position=pos) as progress_bar: |
| 169 | + | response = requests.get(torch1_url.format(quote(searchstr)), proxies=proxies, headers=random_headers()) |
| 170 | + | soup = BeautifulSoup(response.text, 'html5lib') |
| 171 | + | results = link_finder("torch1", soup) |
| 172 | + | progress_bar.update() |
18 | 173 | | |
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=","")}) |
| 174 | + | return results |
30 | 175 | | |
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 |
| 176 | + | |
| 177 | + | def darksearchio(searchstr): |
| 178 | + | results = [] |
| 179 | + | darksearchio_url = supported_engines['darksearchio'] + "/api/search?query={}&page={}" |
| 180 | + | max_nb_page = 30 |
| 181 | + | if args.limit != 0: |
| 182 | + | max_nb_page = args.limit |
| 183 | + | |
| 184 | + | with requests.Session() as s: |
| 185 | + | s.proxies = proxies |
| 186 | + | s.headers = random_headers() |
| 187 | + | resp = s.get(darksearchio_url.format(quote(searchstr), 1)) |
53 | 188 | | |
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 |
| 189 | + | page_number = 1 |
| 190 | + | if resp.status_code == 200: |
| 191 | + | resp = resp.json() |
| 192 | + | if 'last_page' in resp: |
| 193 | + | page_number = resp['last_page'] |
| 194 | + | if page_number > max_nb_page: |
| 195 | + | page_number = max_nb_page |
63 | 196 | | 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"]}) |
| 197 | + | return |
| 198 | + | |
| 199 | + | pos = get_proc_pos() |
| 200 | + | with tqdm(total=page_number, initial=0, desc=get_tqdm_desc("DarkSearch (.io)", pos), position=pos) \ |
| 201 | + | as progress_bar: |
| 202 | + | |
| 203 | + | results = link_finder("darksearchio", resp['data']) |
| 204 | + | progress_bar.update() |
| 205 | + | |
| 206 | + | for n in range(2, page_number + 1): |
| 207 | + | resp = s.get(darksearchio_url.format(quote(searchstr), n)) |
| 208 | + | if resp.status_code == 200: |
| 209 | + | resp = resp.json() |
| 210 | + | results = results + link_finder("darksearchio", resp['data']) |
| 211 | + | progress_bar.update() |
| 212 | + | else: |
| 213 | + | # Current page results will be lost but we will try to continue after a short sleep |
| 214 | + | time.sleep(1) |
| 215 | + | |
| 216 | + | return results |
| 217 | + | |
| 218 | + | |
| 219 | + | def onionland(searchstr): |
| 220 | + | results = [] |
| 221 | + | onionlandv3_url = supported_engines['onionland'] + "/search?q={}&page={}" |
| 222 | + | max_nb_page = 100 |
| 223 | + | if args.limit != 0: |
| 224 | + | max_nb_page = args.limit |
| 225 | + | |
| 226 | + | with requests.Session() as s: |
| 227 | + | s.proxies = proxies |
| 228 | + | s.headers = random_headers() |
| 229 | + | |
| 230 | + | resp = s.get(onionlandv3_url.format(quote(searchstr), 1)) |
| 231 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 232 | + | |
| 233 | + | page_number = 1 |
| 234 | + | for i in soup.find_all('div', attrs={"class": "search-status"}): |
| 235 | + | approx_re = re.match(r"About ([,0-9]+) result(.*)", |
| 236 | + | clear(i.find('div', attrs={'class': "col-sm-12"}).get_text())) |
| 237 | + | if approx_re is not None: |
| 238 | + | nb_res = int((approx_re.group(1)).replace(",", "")) |
| 239 | + | results_per_page = 19 |
| 240 | + | page_number = math.ceil(nb_res / results_per_page) |
| 241 | + | if page_number > max_nb_page: |
| 242 | + | page_number = max_nb_page |
| 243 | + | |
| 244 | + | pos = get_proc_pos() |
| 245 | + | with tqdm(total=max_nb_page, initial=0, desc=get_tqdm_desc("OnionLand", pos), position=pos) as progress_bar: |
| 246 | + | |
| 247 | + | results = link_finder("onionland", soup) |
| 248 | + | progress_bar.update() |
| 249 | + | |
| 250 | + | for n in range(2, page_number + 1): |
| 251 | + | resp = s.get(onionlandv3_url.format(quote(searchstr), n)) |
| 252 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 253 | + | ret = link_finder("onionland", soup) |
| 254 | + | if len(ret) == 0: |
| 255 | + | break |
| 256 | + | results = results + ret |
| 257 | + | progress_bar.update() |
| 258 | + | |
| 259 | + | return results |
| 260 | + | |
| 261 | + | |
| 262 | + | def notevil(searchstr): |
| 263 | + | results = [] |
| 264 | + | notevil_url1 = supported_engines['notevil'] + "/index.php?q={}" |
| 265 | + | notevil_url2 = supported_engines['notevil'] + "/index.php?q={}&hostLimit=20&start={}&numRows={}&template=0" |
| 266 | + | max_nb_page = 20 |
| 267 | + | if args.limit != 0: |
| 268 | + | max_nb_page = args.limit |
| 269 | + | |
| 270 | + | # Do not use requests.Session() here (by experience less results would be got) |
| 271 | + | req = requests.get(notevil_url1.format(quote(searchstr)), proxies=proxies, headers=random_headers()) |
| 272 | + | soup = BeautifulSoup(req.text, 'html5lib') |
| 273 | + | |
| 274 | + | page_number = 1 |
| 275 | + | last_div = soup.find("div", attrs={"style": "text-align:center"}).find("div", attrs={"style": "text-align:center"}) |
| 276 | + | if last_div is not None: |
| 277 | + | for i in last_div.find_all("a"): |
| 278 | + | page_number = int(i.get_text()) |
| 279 | + | if page_number > max_nb_page: |
| 280 | + | page_number = max_nb_page |
| 281 | + | |
| 282 | + | pos = get_proc_pos() |
| 283 | + | with tqdm(total=page_number, initial=0, desc=get_tqdm_desc("not Evil", pos), position=pos) as progress_bar: |
| 284 | + | num_rows = 20 |
| 285 | + | results = link_finder("notevil", soup) |
| 286 | + | progress_bar.update() |
| 287 | + | |
| 288 | + | for n in range(2, page_number + 1): |
| 289 | + | start = (int(n - 1) * num_rows) |
| 290 | + | req = requests.get(notevil_url2.format(quote(searchstr), start, num_rows), |
| 291 | + | proxies=proxies, |
| 292 | + | headers=random_headers()) |
| 293 | + | soup = BeautifulSoup(req.text, 'html5lib') |
| 294 | + | results = results + link_finder("notevil", soup) |
| 295 | + | progress_bar.update() |
| 296 | + | time.sleep(1) |
| 297 | + | |
| 298 | + | return results |
| 299 | + | |
| 300 | + | |
| 301 | + | def visitor(searchstr): |
| 302 | + | results = [] |
| 303 | + | visitor_url = supported_engines['visitor'] + "/search/?q={}&page={}" |
| 304 | + | max_nb_page = 30 |
| 305 | + | if args.limit != 0: |
| 306 | + | max_nb_page = args.limit |
| 307 | + | |
| 308 | + | pos = get_proc_pos() |
| 309 | + | with tqdm(total=max_nb_page, initial=0, desc=get_tqdm_desc("VisiTOR", pos), position=pos) as progress_bar: |
| 310 | + | continue_processing = True |
| 311 | + | page_to_request = 1 |
| 312 | + | |
| 313 | + | with requests.Session() as s: |
| 314 | + | s.proxies = proxies |
| 315 | + | s.headers = random_headers() |
| 316 | + | |
| 317 | + | while continue_processing: |
| 318 | + | resp = s.get(visitor_url.format(quote(searchstr), page_to_request)) |
| 319 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 320 | + | results = results + link_finder("visitor", soup) |
| 321 | + | progress_bar.update() |
| 322 | + | |
| 323 | + | next_page = soup.find('a', text="Next »") |
| 324 | + | if next_page is None or page_to_request >= max_nb_page: |
| 325 | + | continue_processing = False |
| 326 | + | |
| 327 | + | page_to_request += 1 |
| 328 | + | |
| 329 | + | return results |
| 330 | + | |
| 331 | + | |
| 332 | + | def darksearchenginer(searchstr): |
| 333 | + | results = [] |
| 334 | + | darksearchenginer_url = supported_engines['darksearchenginer'] |
| 335 | + | max_nb_page = 20 |
| 336 | + | if args.limit != 0: |
| 337 | + | max_nb_page = args.limit |
| 338 | + | page_number = 1 |
| 339 | + | |
| 340 | + | with requests.Session() as s: |
| 341 | + | s.proxies = proxies |
| 342 | + | s.headers = random_headers() |
| 343 | + | |
| 344 | + | # Note that this search engine is very likely to timeout |
| 345 | + | resp = s.post(darksearchenginer_url, data={"search[keyword]": searchstr, "page": page_number}) |
| 346 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 347 | + | |
| 348 | + | pages_input = soup.find_all("input", attrs={"name": "page"}) |
| 349 | + | for i in pages_input: |
| 350 | + | page_number = int(i['value']) |
| 351 | + | if page_number > max_nb_page: |
| 352 | + | page_number = max_nb_page |
| 353 | + | |
| 354 | + | pos = get_proc_pos() |
| 355 | + | with tqdm(total=page_number, initial=0, desc=get_tqdm_desc("Dark Search Enginer", pos), position=pos) \ |
| 356 | + | as progress_bar: |
| 357 | + | |
| 358 | + | results = link_finder("darksearchenginer", soup) |
| 359 | + | progress_bar.update() |
| 360 | + | |
| 361 | + | for n in range(2, page_number + 1): |
| 362 | + | resp = s.post(darksearchenginer_url, data={"search[keyword]": searchstr, "page": str(n)}) |
| 363 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 364 | + | results = results + link_finder("darksearchenginer", soup) |
| 365 | + | progress_bar.update() |
| 366 | + | |
| 367 | + | return results |
| 368 | + | |
| 369 | + | |
| 370 | + | def phobos(searchstr): |
| 371 | + | results = [] |
| 372 | + | phobos_url = supported_engines['phobos'] + "/search?query={}&p={}" |
| 373 | + | max_nb_page = 100 |
| 374 | + | if args.limit != 0: |
| 375 | + | max_nb_page = args.limit |
| 376 | + | |
| 377 | + | with requests.Session() as s: |
| 378 | + | s.proxies = proxies |
| 379 | + | s.headers = random_headers() |
| 380 | + | |
| 381 | + | resp = s.get(phobos_url.format(quote(searchstr), 1), proxies=proxies, headers=random_headers()) |
| 382 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 383 | + | |
| 384 | + | page_number = 1 |
| 385 | + | pages = soup.find("div", attrs={"class": "pages"}).find_all('a') |
| 386 | + | if pages is not None: |
| 387 | + | for i in pages: |
| 388 | + | page_number = int(i.get_text()) |
| 389 | + | if page_number > max_nb_page: |
| 390 | + | page_number = max_nb_page |
| 391 | + | |
| 392 | + | pos = get_proc_pos() |
| 393 | + | with tqdm(total=page_number, initial=0, desc=get_tqdm_desc("Phobos", pos), position=pos) as progress_bar: |
| 394 | + | results = link_finder("phobos", soup) |
| 395 | + | progress_bar.update() |
| 396 | + | |
| 397 | + | for n in range(2, page_number + 1): |
| 398 | + | resp = s.get(phobos_url.format(quote(searchstr), n), proxies=proxies, headers=random_headers()) |
| 399 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 400 | + | results = results + link_finder("phobos", soup) |
| 401 | + | progress_bar.update() |
| 402 | + | |
| 403 | + | return results |
| 404 | + | |
| 405 | + | |
| 406 | + | def onionsearchserver(searchstr): |
| 407 | + | results = [] |
| 408 | + | onionsearchserver_url1 = supported_engines['onionsearchserver'] + "/oss/" |
| 409 | + | onionsearchserver_url2 = None |
| 410 | + | results_per_page = 10 |
| 411 | + | max_nb_page = 100 |
| 412 | + | if args.limit != 0: |
| 413 | + | max_nb_page = args.limit |
| 414 | + | |
| 415 | + | with requests.Session() as s: |
| 416 | + | s.proxies = proxies |
| 417 | + | s.headers = random_headers() |
| 418 | + | |
| 419 | + | resp = s.get(onionsearchserver_url1) |
| 420 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 421 | + | for i in soup.find_all('iframe', attrs={"style": "display:none;"}): |
| 422 | + | onionsearchserver_url2 = i['src'] + "{}&page={}" |
| 423 | + | |
| 424 | + | if onionsearchserver_url2 is None: |
| 425 | + | return results |
| 426 | + | |
| 427 | + | resp = s.get(onionsearchserver_url2.format(quote(searchstr), 1)) |
| 428 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 429 | + | |
| 430 | + | page_number = 1 |
| 431 | + | pages = soup.find_all("div", attrs={"class": "osscmnrdr ossnumfound"}) |
| 432 | + | if pages is not None and not str(pages[0].get_text()).startswith("No"): |
| 433 | + | total_results = float(str.split(clear(pages[0].get_text()))[0]) |
| 434 | + | page_number = math.ceil(total_results / results_per_page) |
| 435 | + | if page_number > max_nb_page: |
| 436 | + | page_number = max_nb_page |
| 437 | + | |
| 438 | + | pos = get_proc_pos() |
| 439 | + | with tqdm(total=page_number, initial=0, desc=get_tqdm_desc("Onion Search Server", pos), position=pos) \ |
| 440 | + | as progress_bar: |
| 441 | + | |
| 442 | + | results = link_finder("onionsearchserver", soup) |
| 443 | + | progress_bar.update() |
| 444 | + | |
| 445 | + | for n in range(2, page_number + 1): |
| 446 | + | resp = s.get(onionsearchserver_url2.format(quote(searchstr), n)) |
| 447 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 448 | + | results = results + link_finder("onionsearchserver", soup) |
| 449 | + | progress_bar.update() |
| 450 | + | |
| 451 | + | return results |
| 452 | + | |
| 453 | + | |
| 454 | + | def grams(searchstr): |
| 455 | + | results = [] |
| 456 | + | # No multi pages handling as it is very hard to get many results on this engine |
| 457 | + | grams_url1 = supported_engines['grams'] |
| 458 | + | grams_url2 = supported_engines['grams'] + "/results" |
| 459 | + | |
| 460 | + | with requests.Session() as s: |
| 461 | + | s.proxies = proxies |
| 462 | + | s.headers = random_headers() |
| 463 | + | |
| 464 | + | resp = s.get(grams_url1) |
| 465 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 466 | + | token = soup.find('input', attrs={'name': '_token'})['value'] |
| 467 | + | |
| 468 | + | pos = get_proc_pos() |
| 469 | + | with tqdm(total=1, initial=0, desc=get_tqdm_desc("Grams", pos), position=pos) as progress_bar: |
| 470 | + | resp = s.post(grams_url2, data={"req": searchstr, "_token": token}) |
| 471 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 472 | + | results = link_finder("grams", soup) |
| 473 | + | progress_bar.update() |
| 474 | + | |
| 475 | + | return results |
| 476 | + | |
| 477 | + | |
| 478 | + | def candle(searchstr): |
| 479 | + | results = [] |
| 480 | + | candle_url = supported_engines['candle'] + "/?q={}" |
| 481 | + | |
| 482 | + | pos = get_proc_pos() |
| 483 | + | with tqdm(total=1, initial=0, desc=get_tqdm_desc("Candle", pos), position=pos) as progress_bar: |
| 484 | + | response = requests.get(candle_url.format(quote(searchstr)), proxies=proxies, headers=random_headers()) |
| 485 | + | soup = BeautifulSoup(response.text, 'html5lib') |
| 486 | + | results = link_finder("candle", soup) |
| 487 | + | progress_bar.update() |
| 488 | + | |
| 489 | + | return results |
| 490 | + | |
| 491 | + | |
| 492 | + | def torsearchengine(searchstr): |
| 493 | + | results = [] |
| 494 | + | torsearchengine_url = supported_engines['torsearchengine'] + "/search/move/?q={}&pn={}&num=10&sdh=&" |
| 495 | + | max_nb_page = 100 |
| 496 | + | if args.limit != 0: |
| 497 | + | max_nb_page = args.limit |
| 498 | + | |
| 499 | + | with requests.Session() as s: |
| 500 | + | s.proxies = proxies |
| 501 | + | s.headers = random_headers() |
| 502 | + | |
| 503 | + | resp = s.get(torsearchengine_url.format(quote(searchstr), 1)) |
| 504 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 505 | + | |
| 506 | + | page_number = 1 |
| 507 | + | for i in soup.find_all('div', attrs={"id": "subheader"}): |
| 508 | + | if i.get_text() is not None and "of" in i.get_text(): |
| 509 | + | total_results = int(i.find('p').find_all('b')[2].get_text().replace(",", "")) |
| 510 | + | results_per_page = 10 |
| 511 | + | page_number = math.ceil(total_results / results_per_page) |
| 512 | + | if page_number > max_nb_page: |
| 513 | + | page_number = max_nb_page |
| 514 | + | |
| 515 | + | pos = get_proc_pos() |
| 516 | + | with tqdm(total=page_number, initial=0, desc=get_tqdm_desc("Tor Search Engine", pos), position=pos) \ |
| 517 | + | as progress_bar: |
| 518 | + | |
| 519 | + | results = link_finder("torsearchengine", soup) |
| 520 | + | progress_bar.update() |
| 521 | + | |
| 522 | + | for n in range(2, page_number + 1): |
| 523 | + | resp = s.get(torsearchengine_url.format(quote(searchstr), n)) |
| 524 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 525 | + | results = results + link_finder("torsearchengine", soup) |
| 526 | + | progress_bar.update() |
| 527 | + | |
| 528 | + | return results |
| 529 | + | |
| 530 | + | |
| 531 | + | def torgle(searchstr): |
| 532 | + | results = [] |
| 533 | + | torgle_url = supported_engines['torgle'] + "/search.php?term={}" |
| 534 | + | |
| 535 | + | pos = get_proc_pos() |
| 536 | + | with tqdm(total=1, initial=0, desc=get_tqdm_desc("Torgle", pos), position=pos) as progress_bar: |
| 537 | + | response = requests.get(torgle_url.format(quote(searchstr)), proxies=proxies, headers=random_headers()) |
| 538 | + | soup = BeautifulSoup(response.text, 'html5lib') |
| 539 | + | results = link_finder("torgle", soup) |
| 540 | + | progress_bar.update() |
| 541 | + | |
| 542 | + | return results |
| 543 | + | |
| 544 | + | |
| 545 | + | def onionsearchengine(searchstr): |
| 546 | + | results = [] |
| 547 | + | onionsearchengine_url = supported_engines['onionsearchengine'] + "/search.php?search={}&submit=Search&page={}" |
| 548 | + | # same as onionsearchengine_url = "http://5u56fjmxu63xcmbk.onion/search.php?search={}&submit=Search&page={}" |
| 549 | + | max_nb_page = 100 |
| 550 | + | if args.limit != 0: |
| 551 | + | max_nb_page = args.limit |
| 552 | + | |
| 553 | + | with requests.Session() as s: |
| 554 | + | s.proxies = proxies |
| 555 | + | s.headers = random_headers() |
| 556 | + | |
| 557 | + | resp = s.get(onionsearchengine_url.format(quote(searchstr), 1)) |
| 558 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 559 | + | |
| 560 | + | page_number = 1 |
| 561 | + | approx_re = re.search(r"\s([0-9]+)\sresult[s]?\sfound\s!.*", clear(soup.find('body').get_text())) |
| 562 | + | if approx_re is not None: |
| 563 | + | nb_res = int(approx_re.group(1)) |
| 564 | + | results_per_page = 9 |
| 565 | + | page_number = math.ceil(float(nb_res / results_per_page)) |
| 566 | + | if page_number > max_nb_page: |
| 567 | + | page_number = max_nb_page |
| 568 | + | |
| 569 | + | pos = get_proc_pos() |
| 570 | + | with tqdm(total=page_number, initial=0, desc=get_tqdm_desc("Onion Search Engine", pos), position=pos) \ |
| 571 | + | as progress_bar: |
| 572 | + | |
| 573 | + | results = link_finder("onionsearchengine", soup) |
| 574 | + | progress_bar.update() |
| 575 | + | |
| 576 | + | for n in range(2, page_number + 1): |
| 577 | + | resp = s.get(onionsearchengine_url.format(quote(searchstr), n)) |
| 578 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 579 | + | results = results + link_finder("onionsearchengine", soup) |
| 580 | + | progress_bar.update() |
| 581 | + | |
| 582 | + | return results |
| 583 | + | |
| 584 | + | |
| 585 | + | def tordex(searchstr): |
| 586 | + | results = [] |
| 587 | + | tordex_url = supported_engines['tordex'] + "/search?query={}&page={}" |
| 588 | + | max_nb_page = 100 |
| 589 | + | if args.limit != 0: |
| 590 | + | max_nb_page = args.limit |
| 591 | + | |
| 592 | + | with requests.Session() as s: |
| 593 | + | s.proxies = proxies |
| 594 | + | s.headers = random_headers() |
| 595 | + | |
| 596 | + | resp = s.get(tordex_url.format(quote(searchstr), 1)) |
| 597 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 598 | + | |
| 599 | + | page_number = 1 |
| 600 | + | pages = soup.find_all("li", attrs={"class": "page-item"}) |
| 601 | + | if pages is not None: |
| 602 | + | for i in pages: |
| 603 | + | if i.get_text() != "...": |
| 604 | + | page_number = int(i.get_text()) |
| 605 | + | if page_number > max_nb_page: |
| 606 | + | page_number = max_nb_page |
73 | 607 | | |
| 608 | + | pos = get_proc_pos() |
| 609 | + | with tqdm(total=page_number, initial=0, desc=get_tqdm_desc("Tordex", pos), position=pos) as progress_bar: |
| 610 | + | |
| 611 | + | results = link_finder("tordex", soup) |
| 612 | + | progress_bar.update() |
| 613 | + | |
| 614 | + | for n in range(2, page_number + 1): |
| 615 | + | resp = s.get(tordex_url.format(quote(searchstr), n)) |
| 616 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 617 | + | results = results + link_finder("tordex", soup) |
| 618 | + | progress_bar.update() |
| 619 | + | |
| 620 | + | return results |
| 621 | + | |
| 622 | + | |
| 623 | + | def tor66(searchstr): |
| 624 | + | results = [] |
| 625 | + | tor66_url = supported_engines['tor66'] + "/search?q={}&sorttype=rel&page={}" |
| 626 | + | max_nb_page = 30 |
| 627 | + | if args.limit != 0: |
| 628 | + | max_nb_page = args.limit |
| 629 | + | |
| 630 | + | with requests.Session() as s: |
| 631 | + | s.proxies = proxies |
| 632 | + | s.headers = random_headers() |
| 633 | + | |
| 634 | + | resp = s.get(tor66_url.format(quote(searchstr), 1)) |
| 635 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 636 | + | |
| 637 | + | page_number = 1 |
| 638 | + | approx_re = re.search(r"\.Onion\ssites\sfound\s:\s([0-9]+)", resp.text) |
| 639 | + | if approx_re is not None: |
| 640 | + | nb_res = int(approx_re.group(1)) |
| 641 | + | results_per_page = 20 |
| 642 | + | page_number = math.ceil(float(nb_res / results_per_page)) |
| 643 | + | if page_number > max_nb_page: |
| 644 | + | page_number = max_nb_page |
| 645 | + | |
| 646 | + | pos = get_proc_pos() |
| 647 | + | with tqdm(total=page_number, initial=0, desc=get_tqdm_desc("Tor66", pos), position=pos) as progress_bar: |
| 648 | + | |
| 649 | + | results = link_finder("tor66", soup) |
| 650 | + | progress_bar.update() |
| 651 | + | |
| 652 | + | for n in range(2, page_number + 1): |
| 653 | + | resp = s.get(tor66_url.format(quote(searchstr), n)) |
| 654 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 655 | + | results = results + link_finder("tor66", soup) |
| 656 | + | progress_bar.update() |
| 657 | + | |
| 658 | + | return results |
| 659 | + | |
| 660 | + | |
| 661 | + | def tormax(searchstr): |
| 662 | + | results = [] |
| 663 | + | tormax_url = supported_engines['tormax'] + "/tormax/search?q={}" |
| 664 | + | |
| 665 | + | pos = get_proc_pos() |
| 666 | + | with tqdm(total=1, initial=0, desc=get_tqdm_desc("Tormax", pos), position=pos) as progress_bar: |
| 667 | + | response = requests.get(tormax_url.format(quote(searchstr)), proxies=proxies, headers=random_headers()) |
| 668 | + | soup = BeautifulSoup(response.text, 'html5lib') |
| 669 | + | results = link_finder("tormax", soup) |
| 670 | + | progress_bar.update() |
| 671 | + | |
| 672 | + | return results |
| 673 | + | |
| 674 | + | |
| 675 | + | def haystack(searchstr): |
| 676 | + | results = [] |
| 677 | + | haystack_url = supported_engines['haystack'] + "/?q={}&offset={}" |
| 678 | + | # At the 52nd page, it timeouts 100% of the time |
| 679 | + | max_nb_page = 50 |
| 680 | + | if args.limit != 0: |
| 681 | + | max_nb_page = args.limit |
| 682 | + | offset_coeff = 20 |
| 683 | + | |
| 684 | + | with requests.Session() as s: |
| 685 | + | s.proxies = proxies |
| 686 | + | s.headers = random_headers() |
| 687 | + | |
| 688 | + | req = s.get(haystack_url.format(quote(searchstr), 0)) |
| 689 | + | soup = BeautifulSoup(req.text, 'html5lib') |
| 690 | + | |
| 691 | + | pos = get_proc_pos() |
| 692 | + | with tqdm(total=max_nb_page, initial=0, desc=get_tqdm_desc("Haystack", pos), position=pos) as progress_bar: |
| 693 | + | continue_processing = True |
| 694 | + | ret = link_finder("haystack", soup) |
| 695 | + | results = results + ret |
| 696 | + | progress_bar.update() |
| 697 | + | if len(ret) == 0: |
| 698 | + | continue_processing = False |
| 699 | + | |
| 700 | + | it = 1 |
| 701 | + | while continue_processing: |
| 702 | + | offset = int(it * offset_coeff) |
| 703 | + | req = s.get(haystack_url.format(quote(searchstr), offset)) |
| 704 | + | soup = BeautifulSoup(req.text, 'html5lib') |
| 705 | + | ret = link_finder("haystack", soup) |
| 706 | + | results = results + ret |
| 707 | + | progress_bar.update() |
| 708 | + | it += 1 |
| 709 | + | if it >= max_nb_page or len(ret) == 0: |
| 710 | + | continue_processing = False |
| 711 | + | |
| 712 | + | return results |
| 713 | + | |
| 714 | + | |
| 715 | + | def multivac(searchstr): |
| 716 | + | results = [] |
| 717 | + | multivac_url = supported_engines['multivac'] + "/?q={}&page={}" |
| 718 | + | max_nb_page = 10 |
| 719 | + | if args.limit != 0: |
| 720 | + | max_nb_page = args.limit |
| 721 | + | |
| 722 | + | with requests.Session() as s: |
| 723 | + | s.proxies = proxies |
| 724 | + | s.headers = random_headers() |
| 725 | + | |
| 726 | + | page_to_request = 1 |
| 727 | + | req = s.get(multivac_url.format(quote(searchstr), page_to_request)) |
| 728 | + | soup = BeautifulSoup(req.text, 'html5lib') |
| 729 | + | |
| 730 | + | pos = get_proc_pos() |
| 731 | + | with tqdm(total=max_nb_page, initial=0, desc=get_tqdm_desc("Multivac", pos), position=pos) as progress_bar: |
| 732 | + | continue_processing = True |
| 733 | + | ret = link_finder("multivac", soup) |
| 734 | + | results = results + ret |
| 735 | + | progress_bar.update() |
| 736 | + | if len(ret) == 0 or page_to_request >= max_nb_page: |
| 737 | + | continue_processing = False |
| 738 | + | |
| 739 | + | while continue_processing: |
| 740 | + | page_to_request += 1 |
| 741 | + | req = s.get(multivac_url.format(quote(searchstr), page_to_request)) |
| 742 | + | soup = BeautifulSoup(req.text, 'html5lib') |
| 743 | + | ret = link_finder("multivac", soup) |
| 744 | + | results = results + ret |
| 745 | + | progress_bar.update() |
| 746 | + | if len(ret) == 0 or page_to_request >= max_nb_page: |
| 747 | + | continue_processing = False |
| 748 | + | |
| 749 | + | return results |
| 750 | + | |
| 751 | + | |
| 752 | + | def evosearch(searchstr): |
| 753 | + | results = [] |
| 754 | + | evosearch_url = supported_engines['evosearch'] + "/evo/search.php?" \ |
| 755 | + | "query={}&" \ |
| 756 | + | "start={}&" \ |
| 757 | + | "search=1&type=and&mark=bold+text&" \ |
| 758 | + | "results={}" |
| 759 | + | results_per_page = 50 |
| 760 | + | max_nb_page = 30 |
| 761 | + | if args.limit != 0: |
| 762 | + | max_nb_page = args.limit |
| 763 | + | |
| 764 | + | with requests.Session() as s: |
| 765 | + | s.proxies = proxies |
| 766 | + | s.headers = random_headers() |
| 767 | + | |
| 768 | + | req = s.get(evosearch_url.format(quote(searchstr), 1, results_per_page)) |
| 769 | + | soup = BeautifulSoup(req.text, 'html5lib') |
| 770 | + | |
| 771 | + | page_number = 1 |
| 772 | + | i = soup.find("p", attrs={"class": "cntr"}) |
| 773 | + | if i is not None: |
| 774 | + | if i.get_text() is not None and "of" in i.get_text(): |
| 775 | + | nb_res = float(clear(str.split(i.get_text().split("-")[1].split("of")[1])[0])) |
| 776 | + | page_number = math.ceil(nb_res / results_per_page) |
| 777 | + | if page_number > max_nb_page: |
| 778 | + | page_number = max_nb_page |
| 779 | + | |
| 780 | + | pos = get_proc_pos() |
| 781 | + | with tqdm(total=page_number, initial=0, desc=get_tqdm_desc("Evo Search", pos), position=pos) as progress_bar: |
| 782 | + | results = link_finder("evosearch", soup) |
| 783 | + | progress_bar.update() |
| 784 | + | |
| 785 | + | for n in range(2, page_number + 1): |
| 786 | + | resp = s.get(evosearch_url.format(quote(searchstr), n, results_per_page)) |
| 787 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 788 | + | results = results + link_finder("evosearch", soup) |
| 789 | + | progress_bar.update() |
| 790 | + | |
| 791 | + | return results |
| 792 | + | |
| 793 | + | |
| 794 | + | def oneirun(searchstr): |
| 795 | + | results = [] |
| 796 | + | oneirun_url = supported_engines['oneirun'] + "/Home/IndexEn" |
| 797 | + | |
| 798 | + | with requests.Session() as s: |
| 799 | + | s.proxies = proxies |
| 800 | + | s.headers = random_headers() |
| 801 | + | |
| 802 | + | resp = s.get(oneirun_url) |
| 803 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 804 | + | token = soup.find('input', attrs={"name": "__RequestVerificationToken"})['value'] |
| 805 | + | |
| 806 | + | pos = get_proc_pos() |
| 807 | + | with tqdm(total=1, initial=0, desc=get_tqdm_desc("Oneirun", pos), position=pos) as progress_bar: |
| 808 | + | response = s.post(oneirun_url.format(quote(searchstr)), data={ |
| 809 | + | "searchString": searchstr, |
| 810 | + | "__RequestVerificationToken": token |
| 811 | + | }) |
| 812 | + | soup = BeautifulSoup(response.text, 'html5lib') |
| 813 | + | results = link_finder("oneirun", soup) |
| 814 | + | progress_bar.update() |
| 815 | + | |
| 816 | + | return results |
| 817 | + | |
| 818 | + | |
| 819 | + | def deeplink(searchstr): |
| 820 | + | results = [] |
| 821 | + | deeplink_url1 = supported_engines['deeplink'] + "/index.php" |
| 822 | + | deeplink_url2 = supported_engines['deeplink'] + "/?search={}&type=verified" |
| 823 | + | |
| 824 | + | with requests.Session() as s: |
| 825 | + | s.proxies = proxies |
| 826 | + | s.headers = random_headers() |
| 827 | + | s.get(deeplink_url1) |
| 828 | + | |
| 829 | + | pos = get_proc_pos() |
| 830 | + | with tqdm(total=1, initial=0, desc=get_tqdm_desc("DeepLink", pos), position=pos) as progress_bar: |
| 831 | + | response = s.get(deeplink_url2.format(quote(searchstr))) |
| 832 | + | soup = BeautifulSoup(response.text, 'html5lib') |
| 833 | + | results = link_finder("deeplink", soup) |
| 834 | + | progress_bar.update() |
| 835 | + | |
| 836 | + | return results |
| 837 | + | |
| 838 | + | |
| 839 | + | def torsearchengine1(searchstr): |
| 840 | + | results = [] |
| 841 | + | torsearchengine1_url1 = supported_engines['torsearchengine1'] |
| 842 | + | torsearchengine1_url2 = supported_engines['torsearchengine1'] + "/index.php" |
| 843 | + | |
| 844 | + | with requests.Session() as s: |
| 845 | + | s.proxies = proxies |
| 846 | + | s.headers = random_headers() |
| 847 | + | s.get(torsearchengine1_url1) |
| 848 | + | |
| 849 | + | pos = get_proc_pos() |
| 850 | + | with tqdm(total=1, initial=0, desc=get_tqdm_desc("TOR Search Engine 1", pos), position=pos) as progress_bar: |
| 851 | + | response = s.post(torsearchengine1_url2, {'search': searchstr, 'search2': ''}) |
| 852 | + | soup = BeautifulSoup(response.text, 'html5lib') |
| 853 | + | results = link_finder("torsearchengine1", soup) |
| 854 | + | progress_bar.update() |
| 855 | + | |
| 856 | + | return results |
| 857 | + | |
| 858 | + | |
| 859 | + | def torgle1(searchstr): |
| 860 | + | results = [] |
| 861 | + | torgle1_url = supported_engines['torgle1'] + "/torgle/index-frame.php?query={}&search=1&engine-ver=2&isframe=0{}" |
| 862 | + | results_per_page = 10 |
| 863 | + | max_nb_page = 30 |
| 864 | + | if args.limit != 0: |
| 865 | + | max_nb_page = args.limit |
| 866 | + | |
| 867 | + | with requests.Session() as s: |
| 868 | + | s.proxies = proxies |
| 869 | + | s.headers = random_headers() |
| 870 | + | |
| 871 | + | resp = s.get(torgle1_url.format(quote(searchstr), "")) |
| 872 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 873 | + | |
| 874 | + | page_number = 1 |
| 875 | + | i = soup.find('div', attrs={"id": "result_report"}) |
| 876 | + | if i is not None: |
| 877 | + | if i.get_text() is not None and "of" in i.get_text(): |
| 878 | + | res_re = re.match(r".*of\s([0-9]+)\s.*", clear(i.get_text())) |
| 879 | + | total_results = int(res_re.group(1)) |
| 880 | + | page_number = math.ceil(total_results / results_per_page) |
| 881 | + | if page_number > max_nb_page: |
| 882 | + | page_number = max_nb_page |
| 883 | + | |
| 884 | + | pos = get_proc_pos() |
| 885 | + | with tqdm(total=page_number, initial=0, desc=get_tqdm_desc("Torgle 1", pos), position=pos) as progress_bar: |
| 886 | + | results = link_finder("torgle1", soup) |
| 887 | + | progress_bar.update() |
| 888 | + | |
| 889 | + | for n in range(2, page_number + 1): |
| 890 | + | start_page_param = "&start={}".format(n) |
| 891 | + | resp = s.get(torgle1_url.format(quote(searchstr), start_page_param)) |
| 892 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 893 | + | results = results + link_finder("torgle1", soup) |
| 894 | + | progress_bar.update() |
| 895 | + | |
| 896 | + | return results |
| 897 | + | |
| 898 | + | |
| 899 | + | def grams1(searchstr): |
| 900 | + | results = [] |
| 901 | + | grams1_url = supported_engines['grams1'] + "/results/index.php?page={}&searchstr={}" |
| 902 | + | results_per_page = 25 |
| 903 | + | max_nb_page = 30 |
| 904 | + | if args.limit != 0: |
| 905 | + | max_nb_page = args.limit |
| 906 | + | |
| 907 | + | with requests.Session() as s: |
| 908 | + | s.proxies = proxies |
| 909 | + | s.headers = random_headers() |
| 910 | + | |
| 911 | + | resp = s.get(grams1_url.format(1, quote(searchstr))) |
| 912 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 913 | + | |
| 914 | + | page_number = 1 |
| 915 | + | pages = soup.find_all('div', attrs={"class": "result-text"}) |
| 916 | + | if pages is not None: |
| 917 | + | res_re = re.match(r"About ([0-9]+) result(.*)", clear(pages[0].get_text())) |
| 918 | + | total_results = int(res_re.group(1)) |
| 919 | + | page_number = math.ceil(total_results / results_per_page) |
| 920 | + | if page_number > max_nb_page: |
| 921 | + | page_number = max_nb_page |
| 922 | + | |
| 923 | + | pos = get_proc_pos() |
| 924 | + | with tqdm(total=page_number, initial=0, desc=get_tqdm_desc("Grams 1", pos), position=pos) as progress_bar: |
| 925 | + | results = link_finder("grams1", soup) |
| 926 | + | progress_bar.update() |
| 927 | + | |
| 928 | + | for n in range(2, page_number + 1): |
| 929 | + | resp = s.get(grams1_url.format(n, quote(searchstr))) |
| 930 | + | soup = BeautifulSoup(resp.text, 'html5lib') |
| 931 | + | results = results + link_finder("grams1", soup) |
| 932 | + | progress_bar.update() |
| 933 | + | |
| 934 | + | return results |
| 935 | + | |
| 936 | + | |
| 937 | + | def get_domain_from_url(link): |
| 938 | + | fqdn_re = r"^[a-z][a-z0-9+\-.]*://([a-z0-9\-._~%!$&'()*+,;=]+@)?([a-z0-9\-._~%]+|\[[a-z0-9\-._~%!$&'()*+,;=:]+\])" |
| 939 | + | domain_re = re.match(fqdn_re, link) |
| 940 | + | if domain_re is not None: |
| 941 | + | if domain_re.lastindex == 2: |
| 942 | + | return domain_re.group(2) |
| 943 | + | return None |
| 944 | + | |
| 945 | + | |
| 946 | + | def write_to_csv(csv_writer, fields): |
| 947 | + | line_to_write = [] |
| 948 | + | if args.fields and len(args.fields) > 0: |
| 949 | + | for f in args.fields[0]: |
| 950 | + | if f in fields: |
| 951 | + | line_to_write.append(fields[f]) |
| 952 | + | if f == "domain": |
| 953 | + | domain = get_domain_from_url(fields['link']) |
| 954 | + | line_to_write.append(domain) |
| 955 | + | csv_writer.writerow(line_to_write) |
74 | 956 | | else: |
75 | | - | print("Rate limit darksearch.io !") |
| 957 | + | # Default output mode |
| 958 | + | line_to_write.append(fields['engine']) |
| 959 | + | line_to_write.append(fields['name']) |
| 960 | + | line_to_write.append(fields['link']) |
| 961 | + | csv_writer.writerow(line_to_write) |
| 962 | + | |
| 963 | + | |
| 964 | + | def link_finder(engine_str, data_obj): |
| 965 | + | global filename |
| 966 | + | name = "" |
| 967 | + | link = "" |
| 968 | + | csv_file = None |
| 969 | + | found_links = [] |
| 970 | + | |
| 971 | + | if args.continuous_write: |
| 972 | + | csv_file = open(filename, 'a', newline='') |
| 973 | + | |
| 974 | + | def add_link(): |
| 975 | + | found_links.append({"engine": engine_str, "name": name, "link": link}) |
| 976 | + | |
| 977 | + | if args.continuous_write and csv_file.writable(): |
| 978 | + | csv_writer = csv.writer(csv_file, delimiter=field_delim, quoting=csv.QUOTE_ALL) |
| 979 | + | fields = {"engine": engine_str, "name": name, "link": link} |
| 980 | + | write_to_csv(csv_writer, fields) |
| 981 | + | |
| 982 | + | if engine_str == "ahmia": |
| 983 | + | for r in data_obj.select('li.result h4'): |
| 984 | + | name = clear(r.get_text()) |
| 985 | + | link = r.find('a')['href'].split('redirect_url=')[1] |
| 986 | + | add_link() |
| 987 | + | |
| 988 | + | if engine_str == "candle": |
| 989 | + | for r in data_obj.select("body h2 a"): |
| 990 | + | if str(r['href']).startswith("http"): |
| 991 | + | name = clear(r.get_text()) |
| 992 | + | link = clear(r['href']) |
| 993 | + | add_link() |
| 994 | + | |
| 995 | + | if engine_str == "darksearchenginer": |
| 996 | + | for r in data_obj.select('.table-responsive a'): |
| 997 | + | name = clear(r.get_text()) |
| 998 | + | link = clear(r['href']) |
| 999 | + | add_link() |
| 1000 | + | |
| 1001 | + | if engine_str == "darksearchio": |
| 1002 | + | for r in data_obj: |
| 1003 | + | name = clear(r["title"]) |
| 1004 | + | link = clear(r["link"]) |
| 1005 | + | add_link() |
| 1006 | + | |
| 1007 | + | if engine_str == "deeplink": |
| 1008 | + | for tr in data_obj.find_all('tr'): |
| 1009 | + | cels = tr.find_all('td') |
| 1010 | + | if cels is not None and len(cels) == 4: |
| 1011 | + | name = clear(cels[1].get_text()) |
| 1012 | + | link = clear(cels[0].find('a')['href']) |
| 1013 | + | add_link() |
| 1014 | + | |
| 1015 | + | if engine_str == "evosearch": |
| 1016 | + | for r in data_obj.select("#results .title a"): |
| 1017 | + | name = clear(r.get_text()) |
| 1018 | + | link = get_parameter(r['href'], 'url') |
| 1019 | + | add_link() |
| 1020 | + | |
| 1021 | + | if engine_str == "grams": |
| 1022 | + | for i in data_obj.find_all("div", attrs={"class": "media-body"}): |
| 1023 | + | if not i.find('span'): |
| 1024 | + | for r in i.select(".searchlinks a"): |
| 1025 | + | name = clear(r.get_text()) |
| 1026 | + | link = clear(r['href']) |
| 1027 | + | add_link() |
| 1028 | + | |
| 1029 | + | if engine_str == "grams1": |
| 1030 | + | for r in data_obj.select(".searchlinks a"): |
| 1031 | + | name = clear(r.get_text()) |
| 1032 | + | link = clear(r['href']) |
| 1033 | + | add_link() |
| 1034 | + | |
| 1035 | + | if engine_str == "haystack": |
| 1036 | + | for r in data_obj.select(".result b a"): |
| 1037 | + | name = clear(r.get_text()) |
| 1038 | + | link = get_parameter(r['href'], 'url') |
| 1039 | + | add_link() |
| 1040 | + | |
| 1041 | + | if engine_str == "multivac": |
| 1042 | + | for r in data_obj.select("dl dt a"): |
| 1043 | + | if r['href'] != "": |
| 1044 | + | name = clear(r.get_text()) |
| 1045 | + | link = clear(r['href']) |
| 1046 | + | add_link() |
| 1047 | + | else: |
| 1048 | + | break |
| 1049 | + | |
| 1050 | + | if engine_str == "notevil": |
| 1051 | + | for r in data_obj.select('#content > div > p > a:not([target])'): |
| 1052 | + | name = clear(r.get_text()) |
| 1053 | + | link = get_parameter(r['href'], 'url') |
| 1054 | + | add_link() |
| 1055 | + | |
| 1056 | + | if engine_str == "oneirun": |
| 1057 | + | for td in data_obj.find_all('td', attrs={"style": "vertical-align: top;"}): |
| 1058 | + | name = clear(td.find('h5').get_text()) |
| 1059 | + | link = clear(td.find('a')['href']) |
| 1060 | + | add_link() |
| 1061 | + | |
| 1062 | + | if engine_str == "onionland": |
| 1063 | + | for r in data_obj.select('.result-block .title a'): |
| 1064 | + | if not r['href'].startswith('/ads/'): |
| 1065 | + | name = clear(r.get_text()) |
| 1066 | + | link = unquote(unquote(get_parameter(r['href'], 'l'))) |
| 1067 | + | add_link() |
| 1068 | + | |
| 1069 | + | if engine_str == "onionsearchengine": |
| 1070 | + | for r in data_obj.select("table a b"): |
| 1071 | + | name = clear(r.get_text()) |
| 1072 | + | link = get_parameter(r.parent['href'], 'u') |
| 1073 | + | add_link() |
| 1074 | + | |
| 1075 | + | if engine_str == "onionsearchserver": |
| 1076 | + | for r in data_obj.select('.osscmnrdr.ossfieldrdr1 a'): |
| 1077 | + | name = clear(r.get_text()) |
| 1078 | + | link = clear(r['href']) |
| 1079 | + | add_link() |
| 1080 | + | |
| 1081 | + | if engine_str == "phobos": |
| 1082 | + | for r in data_obj.select('.serp .titles'): |
| 1083 | + | name = clear(r.get_text()) |
| 1084 | + | link = clear(r['href']) |
| 1085 | + | add_link() |
| 1086 | + | |
| 1087 | + | if engine_str == "tor66": |
| 1088 | + | for i in data_obj.find('hr').find_all_next('b'): |
| 1089 | + | if i.find('a'): |
| 1090 | + | name = clear(i.find('a').get_text()) |
| 1091 | + | link = clear(i.find('a')['href']) |
| 1092 | + | add_link() |
| 1093 | + | |
| 1094 | + | if engine_str == "torch": |
| 1095 | + | for r in data_obj.select("dl > dt > a"): |
| 1096 | + | name = clear(r.get_text()) |
| 1097 | + | link = clear(r['href']) |
| 1098 | + | add_link() |
| 1099 | + | |
| 1100 | + | if engine_str == "torch1": |
| 1101 | + | for r in data_obj.select("dl > dt > a"): |
| 1102 | + | name = clear(r.get_text()) |
| 1103 | + | link = clear(r['href']) |
| 1104 | + | add_link() |
| 1105 | + | |
| 1106 | + | if engine_str == "tordex": |
| 1107 | + | for r in data_obj.select('.container h5 a'): |
| 1108 | + | name = clear(r.get_text()) |
| 1109 | + | link = clear(r['href']) |
| 1110 | + | add_link() |
| 1111 | + | |
| 1112 | + | if engine_str == "torgle": |
| 1113 | + | for i in data_obj.find_all('ul', attrs={"id": "page"}): |
| 1114 | + | for j in i.find_all('a'): |
| 1115 | + | if str(j.get_text()).startswith("http"): |
| 1116 | + | link = clear(j.get_text()) |
| 1117 | + | else: |
| 1118 | + | name = clear(j.get_text()) |
| 1119 | + | add_link() |
| 1120 | + | |
| 1121 | + | if engine_str == "torgle1": |
| 1122 | + | for r in data_obj.select("#results a.title"): |
| 1123 | + | name = clear(r.get_text()) |
| 1124 | + | link = clear(r['href']) |
| 1125 | + | add_link() |
| 1126 | + | |
| 1127 | + | if engine_str == "tormax": |
| 1128 | + | for r in data_obj.select("#search-results article a.title"): |
| 1129 | + | name = clear(r.get_text()) |
| 1130 | + | link = clear(r.find_next_sibling('div', {'class': 'url'}).get_text()) |
| 1131 | + | add_link() |
| 1132 | + | |
| 1133 | + | if engine_str == "torsearchengine": |
| 1134 | + | for i in data_obj.find_all('h3', attrs={'class': 'title text-truncate'}): |
| 1135 | + | name = clear(i.find('a').get_text()) |
| 1136 | + | link = i.find('a')['data-uri'] |
| 1137 | + | add_link() |
| 1138 | + | |
| 1139 | + | if engine_str == "torsearchengine1": |
| 1140 | + | for r in data_obj.find_all('span', {'style': 'font-size:1.2em;font-weight:bold;color:#1a0dab'}): |
| 1141 | + | name = clear(r.get_text()) |
| 1142 | + | link = r.find_next_sibling('a')['href'] |
| 1143 | + | add_link() |
| 1144 | + | |
| 1145 | + | if engine_str == "visitor": |
| 1146 | + | for r in data_obj.select(".hs_site h3 a"): |
| 1147 | + | name = clear(r.get_text()) |
| 1148 | + | link = clear(r['href']) |
| 1149 | + | add_link() |
| 1150 | + | |
| 1151 | + | if args.continuous_write and not csv_file.closed: |
| 1152 | + | csv_file.close() |
| 1153 | + | |
| 1154 | + | return found_links |
| 1155 | + | |
| 1156 | + | |
| 1157 | + | def run_method(method_name_and_argument): |
| 1158 | + | method_name = method_name_and_argument.split(':')[0] |
| 1159 | + | argument = method_name_and_argument.split(':')[1] |
| 1160 | + | ret = [] |
| 1161 | + | try: |
| 1162 | + | ret = globals()[method_name](argument) |
| 1163 | + | except ConnectionError: |
| 1164 | + | print("Error: unable to connect") |
| 1165 | + | except OSError: |
| 1166 | + | print("Error: unable to connect") |
| 1167 | + | except ProtocolError: |
| 1168 | + | print("Error: unable to connect") |
| 1169 | + | return ret |
| 1170 | + | |
| 1171 | + | |
| 1172 | + | def scrape(): |
| 1173 | + | global filename |
| 1174 | + | |
| 1175 | + | start_time = datetime.now() |
| 1176 | + | |
| 1177 | + | # Building the filename |
| 1178 | + | filename = str(filename).replace("$DATE", start_time.strftime("%Y%m%d%H%M%S")) |
| 1179 | + | search = str(args.search).replace(" ", "") |
| 1180 | + | if len(search) > 10: |
| 1181 | + | search = search[0:9] |
| 1182 | + | filename = str(filename).replace("$SEARCH", search) |
| 1183 | + | |
| 1184 | + | func_args = [] |
| 1185 | + | stats_dict = {} |
| 1186 | + | if args.engines and len(args.engines) > 0: |
| 1187 | + | eng = args.engines[0] |
| 1188 | + | for e in eng: |
| 1189 | + | try: |
| 1190 | + | if not (args.exclude and len(args.exclude) > 0 and e in args.exclude[0]): |
| 1191 | + | func_args.append("{}:{}".format(e, args.search)) |
| 1192 | + | stats_dict[e] = 0 |
| 1193 | + | except KeyError: |
| 1194 | + | print("Error: search engine {} not in the list of supported engines".format(e)) |
| 1195 | + | else: |
| 1196 | + | for e in supported_engines.keys(): |
| 1197 | + | if not (args.exclude and len(args.exclude) > 0 and e in args.exclude[0]): |
| 1198 | + | func_args.append("{}:{}".format(e, args.search)) |
| 1199 | + | stats_dict[e] = 0 |
| 1200 | + | |
| 1201 | + | # Doing multiprocessing |
| 1202 | + | units = min((cpu_count() - 1), len(func_args)) |
| 1203 | + | if args.mp_units and args.mp_units > 0: |
| 1204 | + | units = min(args.mp_units, len(func_args)) |
| 1205 | + | print("search.py started with {} processing units...".format(units)) |
| 1206 | + | freeze_support() |
| 1207 | + | |
| 1208 | + | results = {} |
| 1209 | + | with Pool(units, initializer=tqdm.set_lock, initargs=(tqdm.get_lock(),)) as p: |
| 1210 | + | results_map = p.map(run_method, func_args) |
| 1211 | + | results = reduce(lambda a, b: a + b if b is not None else a, results_map) |
76 | 1212 | | |
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 |
| 1213 | + | stop_time = datetime.now() |
| 1214 | + | |
| 1215 | + | if not args.continuous_write: |
| 1216 | + | with open(filename, 'w', newline='') as csv_file: |
| 1217 | + | csv_writer = csv.writer(csv_file, delimiter=field_delim, quoting=csv.QUOTE_ALL) |
| 1218 | + | for r in results: |
| 1219 | + | write_to_csv(csv_writer, r) |
| 1220 | + | |
| 1221 | + | total = 0 |
| 1222 | + | print("\nReport:") |
| 1223 | + | print(" Execution time: %s seconds" % (stop_time - start_time)) |
| 1224 | + | print(" Results per engine:") |
| 1225 | + | for r in results: |
| 1226 | + | stats_dict[r['engine']] += 1 |
| 1227 | + | for s in stats_dict: |
| 1228 | + | n = stats_dict[s] |
| 1229 | + | print(" {}: {}".format(s, str(n))) |
| 1230 | + | total += n |
| 1231 | + | print(" Total: {} links written to {}".format(str(total), filename)) |
90 | 1232 | | |
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 | 1233 | | |
106 | | - | f.close() |
107 | | - | scrape() |
| 1234 | + | if __name__ == "__main__": |
| 1235 | + | scrape() |
108 | 1236 | | |