#!/usr/bin/env python3
from tbselenium.tbdriver import TorBrowserDriver
import pickle
tbpath = "tor-browser_en-US"
with open('onions.sav', 'rb') as f:
potential_onions = pickle.load(f)
print("Loaded {} onions".format(len(potential_onions)))
driver = TorBrowserDriver(tbpath)
driver.set_page_load_timeout(60)
good_onions = []
for onion in potential_onions:
try:
driver.load_url(onion)
good_onions.append(onion)
except Exception as e:
print(e)
print("Good onions")
for onion in good_onions:
print(onion)
with open('good-onions.sav', 'wb') as f:
pickle.dump(good_onions, f)
class Crawler:
"""Crawls your onions, but also manages Tor, drives Tor Browser, and uses
information from your Tor cell log and stem to collect cell sequences."""
def __init__(
self,
take_ownership=True, # Tor dies when the Crawler does
torrc_config={"CookieAuth": "1"},
tor_log="/var/log/tor/tor.log",
tor_cell_log="/var/log/tor/tor_cell_seq.log",
control_port=9051,
socks_port=9050,
run_in_xvfb=True,
tbb_path=join("/opt", "tbb", "tor-browser_en-US"),
tb_log_path=join(_log_dir, "firefox.log"),
tb_tor_cfg=USE_RUNNING_TOR,
page_load_timeout=20,
wait_on_page=5,
wait_after_closing_circuits=0,
restart_on_sketchy_exception=True,
additional_control_fields={},
db_handler=None):
self.logger = setup_logging(_log_dir, "crawler")
# Set stem logging level to INFO - "high level library activity"
stem.util.log.get_logger().setLevel(stem.util.log.Runlevel.INFO)
self.torrc_config = torrc_config
self.socks_port = find_free_port(socks_port, control_port)
self.torrc_config.update({"SocksPort": str(self.socks_port)})
self.control_port = find_free_port(control_port, self.socks_port)
self.torrc_config.update({"ControlPort": str(self.control_port)})
self.torrc_config.update({"Log": "INFO file {}".format(tor_log)})
self.logger.info("Starting tor process with config "
"{torrc_config}.".format(**locals()))
self.tor_process = launch_tor_with_config(
config=self.torrc_config, take_ownership=take_ownership)
self.authenticate_to_tor_controlport()
self.logger.info("Opening cell log stream...")
self.cell_log = open(tor_cell_log, "rb")
if run_in_xvfb:
self.logger.info("Starting Xvfb...")
self.run_in_xvfb = True
self.virtual_framebuffer = start_xvfb()
self.logger.info("Starting Tor Browser...")
self.tb_driver = TorBrowserDriver(tbb_path=tbb_path,
tor_cfg=tb_tor_cfg,
tbb_logfile_path=tb_log_path,
socks_port=self.socks_port,
control_port=self.control_port)
self.wait_after_closing_circuits = wait_after_closing_circuits
self.page_load_timeout = page_load_timeout
self.tb_driver.set_page_load_timeout(page_load_timeout)
self.wait_on_page = wait_on_page
self.restart_on_sketchy_exception = restart_on_sketchy_exception
self.control_data = self.get_control_data(page_load_timeout,
wait_on_page,
wait_after_closing_circuits,
additional_control_fields)
self.db_handler = db_handler
if db_handler:
self.crawlid = self.db_handler.add_crawl(self.control_data)
def authenticate_to_tor_controlport(self):
self.logger.info("Authenticating to the tor controlport...")
try:
self.controller = Controller.from_port(port=self.control_port)
except stem.SocketError as exc:
panic("Unable to connect to tor on port {self.control_port}: "
"{exc}".format(**locals()))
try:
self.controller.authenticate()
except stem.connection.MissingPassword:
panic("Unable to authenticate to tor controlport. Please add "
"`CookieAuth 1` to your tor configuration file.")
def get_control_data(self, page_load_timeout, wait_on_page,
wait_after_closing_circuits,
additional_control_fields):
"""Gather metadata about the crawler instance."""
control_data = {}
# Configuration settings
control_data["page_load_timeout"] = page_load_timeout
control_data["wait_on_page"] = wait_on_page
control_data["wait_after_closing_circuits"] = \
wait_after_closing_circuits
if additional_control_fields:
control_data.update(additional_control_fields)
# System facts
control_data["kernel"] = platform.system()
control_data["kernel_version"] = platform.release()
control_data["os"] = platform.version()
control_data["python_version"] = platform.python_version()
ip = urlopen("https://api.ipify.org").read().decode()
control_data["ip"] = ip
# This API seems to be unstable and we haven't found a suitable
# alternative :(
try:
asn_geoip = urlopen("http://api.moocher.io/ip/{}".format(ip))
asn_geoip = literal_eval(asn_geoip.read().decode())
control_data["asn"] = asn_geoip.get("ip").get("as").get("asn")
control_data["city"] = asn_geoip.get("ip").get("city")
control_data["country"] = asn_geoip.get("ip").get("country")
except urllib.error.HTTPError:
self.logger.warning("Unable to query ASN API and thus some "
"control data may be missing from this run.")
control_data["tor_version"] = self.controller.get_version().version_str
control_data["tb_version"] = self.tb_driver.tb_version
# Tor will have multiple entry nodes in its state file, but will
# choose the first sequential one that is up as its entry guard.
entry_nodes = self.controller.get_info("entry-guards").split('\n')
control_data["entry_node"] = next(
re.search("[0-9A-F]{40}", g).group(0) for g in entry_nodes
if re.search("up", g))
control_data["crawler_version"] = _version
return control_data
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, traceback):
self.close()
return self
def __del__(self):
self.close()
def close(self):
self.logger.info("Beginning Crawler exit process...")
if "tb_driver" in dir(self):
self.logger.info("Closing Tor Browser...")
self.tb_driver.quit()
if "virtual_framebuffer" in dir(self):
self.logger.info("Closing the virtual framebuffer...")
# A bug in pyvirtualdisplay triggers a KeyError exception when closing a
# virtual framebuffer if the $DISPLAY environment variable is not set.
try:
stop_xvfb(self.virtual_framebuffer)
except KeyError:
pass
if "cell_log" in dir(self):
self.logger.info("Closing the Tor cell stream...")
self.cell_log.close()
if "tor_process" in dir(self):
self.logger.info("Killing the tor process...")
self.tor_process.kill()
self.logger.info("Crawler exit completed.")
def collect_onion_trace(self,
url,
hsid=None,
extra_fn=None,
trace_dir=None,
iteration=0):
"""Crawl an onion service and collect a complete cell sequence for the
activity at the time. Also, record additional information about the
circuits with stem. Optionally, pass a function to execute additional
actions after the page has loaded."""
# Todo: create collect_trace method that works for regular sites as
# well
assert ".onion" in url, ("This method is only suitable for crawling "
"onion services.")
self.logger.info("{url}: closing existing circuits before starting "
"crawl.".format(**locals()))
for circuit in self.controller.get_circuits():
self.controller.close_circuit(circuit.id)
sleep(self.wait_after_closing_circuits)
if not trace_dir:
trace_dir = self.make_ts_dir()
trace_name = urllib.parse.quote(url, safe="") + "-" + str(iteration)
trace_path = join(trace_dir, trace_name)
start_idx = self.get_cell_log_pos()
try:
self.crawl_url(url)
rend_circ_ids = self.get_rend_circ_ids(url)
if extra_fn:
self.execute_extra_fn(url, trace_path, start_idx)
except CrawlerLoggedError:
return "failed"
except CrawlerNoRendCircError:
self.save_debug_log(url, trace_path, start_idx)
return "failed"
except:
self.logger.exception("{url}: unusual exception "
"encountered:".format(**locals()))
# Also log active circuit info
self.controller.get_circuits()
exc_type, exc_value, exc_traceback = exc_info()
if exc_type in _sketchy_exceptions:
self.save_debug_log(url, trace_path, start_idx)
if self.restart_on_sketchy_exception:
self.restart_tb()
return "failed"
self.logger.info("{url}: saving full trace...".format(**locals()))
end_idx = self.get_cell_log_pos()
full_trace = self.get_full_trace(start_idx, end_idx)
# Save the trace to the database or write to file
if self.db_handler:
try:
new_example = {
'hsid': hsid,
'crawlid': self.crawlid,
't_scrape': get_timestamp("db")
}
except NameError:
panic("If using the database, and calling collect_onion_trace "
"directly, you must specify the hsid of the site.")
exampleid = self.db_handler.add_example(new_example)
self.db_handler.add_trace(str(full_trace), exampleid)
else:
with open(trace_path + "-full", "wb") as fh:
fh.write(full_trace)
return "succeeded"
def make_ts_dir(self, parent_dir=_log_dir, raw_dir_name="batch"):
"""Creates a timestamped folder to hold a group of traces."""
raw_dirpath = join(parent_dir, raw_dir_name)
ts = get_timestamp("log")
ts_dir = timestamp_file(raw_dirpath, ts, is_dir=True)
symlink_cur_to_latest(raw_dirpath, ts)
with open(join(ts_dir, "control.pickle"), "wb") as fh:
pickle.dump(self.control_data, fh)
return ts_dir
def get_cell_log_pos(self):
"""Returns the current position of the last byte in the Tor cell log."""
return self.cell_log.seek(0, SEEK_END)
def crawl_url(self, url):
"""Load a web page in Tor Browser and optionally pass a function
to execute custom actions on it."""
self.logger.info("{url}: starting page load...".format(**locals()))
try:
self.tb_driver.load_url(url,
wait_on_page=self.wait_on_page,
wait_for_page_body=True)
except TimeoutException:
self.logger.warning("{url}: timed out.".format(**locals()))
raise CrawlerLoggedError
except http.client.CannotSendRequest:
self.logger.warning("{url}: cannot send request--improper "
"connection state.".format(**locals()))
raise CrawlerLoggedError
# Make sure we haven't just hit an error page or nothing loaded
try:
if (self.tb_driver.is_connection_error_page
or self.tb_driver.current_url == "about:newtab"):
raise CrawlerReachedErrorPage
except CrawlerReachedErrorPage:
self.logger.warning("{url}: reached connection error "
"page.".format(**locals()))
raise CrawlerLoggedError
self.logger.info("{url}: successfully loaded.".format(**locals()))
def get_rend_circ_ids(self, url):
"""Returns the rendezvous circuit id(s) associated with a given onion
service."""
self.logger.info("{url}: collecting circuit "
"information...".format(**locals()))
active_circs = self.controller.get_circuits()
rend_circ_ids = set()
for circ in active_circs:
if (circ.purpose == "HS_CLIENT_REND" and circ.socks_username
and circ.socks_username in url):
rend_circ_ids.add(circ.id)
# If everything goes perfect, we should only see one. Multiple indicate
# the first failed. Zero indicates one closed abruptly (or there's an
# error with stem--still waiting on data to confirm or deny).
rend_circ_ct = len(rend_circ_ids)
self.logger.info(
"{url}: {rend_circ_ct} associated rendezvous circuits "
"discovered.".format(**locals()))
if rend_circ_ct == 0:
raise CrawlerNoRendCircError
return rend_circ_ids
def execute_extra_fn(self, url, trace_path, start_idx):
self.logger.info("{url}: executing extra function "
"code...".format(**locals()))
extra_fn(self, url, trace_path, start_idx)
self.logger.info("{url}: extra function executed "
"successfully.".format(**locals()))
def save_debug_log(self, url, trace_path, start_idx):
self.logger.warning("{url}: saving debug log...".format(**locals()))
exc_time = self.get_cell_log_pos()
trace = self.get_full_trace(start_idx, exc_time)
with open(trace_path + "@debug", "wb") as fh:
fh.write(trace)
def get_full_trace(self, start_idx, end_idx):
"""Returns the Tor DATA cells transmitted over a circuit during a
specified time period."""
# Sanity check
assert start_idx >= 0 and end_idx > 0, ("Invalid (negative) logfile "
"position")
assert end_idx > start_idx, ("logfile section end_idx must come "
"after start_idx")
self.cell_log.seek(start_idx, SEEK_SET)
return self.cell_log.read(end_idx - start_idx)
def restart_tb(self):
"""Restarts the Tor Browser."""
self.logger.info("Restarting the Tor Browser...")
self.tb_driver.quit()
self.tb_driver = TorBrowserDriver(tbb_path=tbb_path,
tor_cfg=USE_RUNNING_TOR,
tbb_logfile_path=tb_log_path,
socks_port=self.socks_port,
control_port=self.control_port)
self.logger.info("Tor Browser restarted...")
def collect_set_of_traces(self,
url_set,
extra_fn=None,
trace_dir=None,
iteration=0,
shuffle=True,
retry=True,
url_to_id_mapping=None):
"""Collect a set of traces."""
if self.db_handler:
if not url_to_id_mapping:
url_to_id_mapping = url_set
trace_dir = None
elif not trace_dir:
trace_dir = self.make_ts_dir()
set_size = len(url_set)
self.logger.info("Saving set of {set_size} traces to "
"{trace_dir}.".format(**locals()))
# Converts both sets (from pickle files) and dicts (whose keys are
# URLs--from database) to URL lists
url_set = list(url_set)
if shuffle:
random.shuffle(url_set)
failed_urls = []
for url_idx in range(set_size):
self.logger.info("Collecting trace {} of "
"{set_size}...".format(url_idx + 1, **locals()))
url = url_set[url_idx]
if self.db_handler:
hsid = url_to_id_mapping[url]
else:
hsid = None
if (self.collect_onion_trace(url,
hsid=hsid,
extra_fn=extra_fn,
trace_dir=trace_dir,
iteration=iteration) == "failed"
and retry):
failed_urls.append(url)
if failed_urls:
failed_ct = len(failed_urls)
self.logger.info("Retrying {failed_ct} of {set_size} traces that "
"failed.".format(**locals()))
self.collect_set_of_traces(failed_urls,
extra_fn=extra_fn,
trace_dir=trace_dir,
iteration=iteration,
shuffle=shuffle,
retry=False,
url_to_id_mapping=url_to_id_mapping)
def crawl_monitored_nonmonitored(self,
monitored_class,
nonmonitored_class,
extra_fn=None,
shuffle=True,
retry=True,
monitored_name="monitored",
nonmonitored_name="nonmonitored",
url_to_id_mapping=None,
ratio=40):
"""Crawl a monitored class ratio times interspersed between the
crawling of a(n ostensibly larger) non-monitored class."""
if self.db_handler:
if not url_to_id_mapping:
url_to_id_mapping = nonmonitored_class
url_to_id_mapping.update(monitored_class)
trace_dir, mon_trace_dir, nonmon_trace_dir = (None, ) * 3
else:
trace_dir = self.make_ts_dir()
mon_trace_dir = join(trace_dir, monitored_name)
mkdir(mon_trace_dir)
nonmon_trace_dir = join(trace_dir, nonmonitored_name)
mkdir(nonmon_trace_dir)
# db: calling list on a dict returns a list of its keys (URLs)
# pickle: calling list on set is necessary to make it shuffleable
nonmonitored_class = list(nonmonitored_class)
monitored_class = list(monitored_class)
nonmonitored_class_ct = len(nonmonitored_class)
chunk_size = int(nonmonitored_class_ct / ratio)
if shuffle:
random.shuffle(nonmonitored_class)
random.shuffle(monitored_class)
for iteration in range(ratio):
self.logger.info("Beginning iteration {i} of {ratio} in the "
"{monitored_name} class".format(i=iteration + 1,
**locals()))
self.collect_set_of_traces(monitored_class,
trace_dir=mon_trace_dir,
iteration=iteration,
url_to_id_mapping=url_to_id_mapping)
slice_lb = iteration * chunk_size
slice_ub = min((iteration + 1) * chunk_size, nonmonitored_class_ct)
self.logger.info("Crawling services {} through {slice_ub} of "
"{nonmonitored_class_ct} in the "
"{nonmonitored_name} "
"class".format(slice_lb + 1, **locals()))
self.collect_set_of_traces(nonmonitored_class[slice_lb:slice_ub],
trace_dir=nonmon_trace_dir,
iteration=iteration,
url_to_id_mapping=url_to_id_mapping)
class DescargarPdf:
def __init__(self):
self.tbb_dir = "/usr/local/share/tor-browser_en-US"
self.usuario = []
self.contraseñaTxT = []
self.conversor = '?convertedTo=pdf'
def iniciarTor(self):
self.zLibraty = TorBrowserDriver(self.tbb_dir,
tbb_logfile_path='test.log')
def iniciarSecion(self):
self.element = self.zLibraty.find_element_by_name("email")
self.element.send_keys(self.correo)
sleep(2)
self.element2 = self.zLibraty.find_elements_by_class_name(
"form-control")[1]
self.element2.send_keys(self.contraseña)
self.element2.send_keys(Keys.RETURN)
def paginaDescargas(self):
print("estoy en la funcion paginaDescagas")
sleep(4)
self.zLibraty.get(self.url)
self.html = self.zLibraty.page_source
def paginaPrinsipal(self, añoInicial, añoFinal):
self.urlAños = 'http://zlibraryexau2g3p.onion/s/?yearFrom=' + str(
añoInicial) + '&yearTo=' + str(añoFinal)
self.url = self.urlAños
def cambiarPagina(self, x):
self.url += '&page=' + str(x)
def Crearcsv(self):
self.carpetaUrl = '/home/dgc7/Documentos/zlibrary/libros1920-1921/url'
try:
os.mkdir(self.carpetaUrl)
except OSError as e:
if e.errno != errno.EEXIST:
raise
self.escrivirUrlWed = csv.writer(
open('/home/dgc7/Documentos/zlibrary/libros1920-1921/url/url2.csv',
'w'))
self.imprimirUrlPdf = csv.writer(
open(
'/home/dgc7/Documentos/zlibrary/libros1920-1921/url/urlDowload2.csv',
'w'))
def credenciales(self, numeroUsuario):
print("llegue")
self.correo = self.usuario[numeroUsuario]
self.contraseña = self.contraseñaTxT[numeroUsuario]
self.urlLoguin = 'http://zlibraryexau2g3p.onion'
self.zLibraty.get(self.urlLoguin)
def UsuariosYcontraseñas(self):
self.dir = '/home/dgc7/Documentos/zlibrary/credenciales/contraseñasYcorreos.txt'
self.data = open(self.dir, 'r+')
for self.i in range(0, 200):
if self.i % 2 == 0:
self.usuario.append(self.data.readline())
if self.i % 2 != 0:
self.contraseñaTxT.append(self.data.readline())
def urlPdf(self, ):
self.boleanoPdf = 0
self.respaldoContador = 0
self.contadorUsuarios = usuarioUsadosLeer()
self.contadorLibros = datosDescarga(4)
self.contadorLibros2 = self.contadorLibros % 10
self.Crearcsv()
self.soup = BeautifulSoup(self.html, 'html.parser')
try:
for self.urlwed in self.soup.find_all(itemprop="name"):
self.contador = 0
self.urlwed = self.urlwed.find('a', href=re.compile(''))
self.urlDowload = self.urlwed.get('href')
self.urlpdfGeleneralH = re.sub('/book/',
'https://b-ok.cc/book/',
self.urlDowload)
self.urlDowload = re.sub(
'/book/', 'http://zlibraryexau2g3p.onion/book/',
self.urlDowload)
self.escrivirUrlWed.writerow([self.urlDowload])
print(self.urlDowload)
voleano = validarFormato(self.urlpdfGeleneralH)
guardarNumeroDescargas(self.contadorLibros)
print(self.respaldoContador)
if self.contadorLibros == self.respaldoContador:
for self.urlRedirec in range(0, 1):
self.zLibraty.get(self.urlDowload)
sleep(5)
self.htmlPdf = self.zLibraty.page_source
self.soupRedirec = BeautifulSoup(
self.htmlPdf, 'html.parser')
self.urlDowloadPDF = self.soupRedirec.find(
class_="btn btn-primary dlButton addDownloadedBook"
)
self.urlDowloadPDF = self.urlDowloadPDF.get('href')
self.urlDowloadPDF = re.sub(
'/dl/', 'http://zlibraryexau2g3p.onion/dl/',
self.urlDowloadPDF)
self.imprimirUrlPdf.writerow([self.urlDowloadPDF])
print(self.urlDowloadPDF)
print("vamos a por el if")
sleep(10)
if voleano == True:
self.zLibraty.set_page_load_timeout(8)
try:
self.zLibraty.get(self.urlDowloadPDF)
except:
self.zLibraty.set_page_load_timeout(70)
self.zLibraty.refresh()
print("funciona PDF ")
voleano = False
sleep(5)
self.contadorLibros += 1
self.contadorLibros2 += 1
else:
try:
self.zLibraty.set_page_load_timeout(5)
try:
self.zLibraty.get(self.urlDowloadPDF)
except:
sleep(4)
pyautogui.press("down")
sleep(2)
pyautogui.press("enter")
self.zLibraty.set_page_load_timeout(70)
except:
print(
"\nerror al controlasr el teclado y dar enter\n"
)
raise
sleep(5)
self.zLibraty.refresh()
self.contadorLibros += 1
self.contadorLibros2 += 1
sleep(20)
tiempoDescarga()
informaiconPdf(self.urlpdfGeleneralH)
self.respaldoContador += 1
if self.contadorLibros == self.respaldoContador:
if self.contadorLibros2 % 10 == 0:
print((self.contadorLibros2 - 1) % 10)
self.contador += 1
pyautogui.hotkey("ctrl", "shift", "u")
sleep(2)
pyautogui.press("enter")
sleep(7)
pyautogui.press("enter")
sleep(15)
self.contadorUsuarios += 1
print(self.contadorUsuarios)
try:
self.zLibraty.switch_to_window(
self.zLibraty.window_handles[0])
except:
print("error al cambian de ventana")
usuarioUsadosReescrivir(self.contadorUsuarios)
print("por aqui¿¿¿¿¿¿")
self.credenciales(self.contadorUsuarios)
print("no por aqui¿¿¿¿¿¿")
sleep(23)
self.iniciarSecion()
sleep(7)
self.contadorLibros2 = 0
sleep(15)
print("numero de li bros por usuario ",
self.contadorLibros2)
if self.contador == 5:
self.contador = 0
except OSError as e:
print(e.strerror)
print("error en la urlPdf:::::")
guardarNumeroDescargas(self.contadorLibros)
usuarioUsadosReescrivir(self.contadorUsuarios)
print(self.contadorLibros)
raise
print("termine la pagina")
def DescargarContenido(self, _html):
self.contenido = _html
def serrarTor(self):
self.zLibraty.close()
class Crawler:
"""Crawls your onions, but also manages Tor, drives Tor Browser, and uses
information from your Tor cell log and stem to collect cell sequences."""
def __init__(self,
take_ownership=True, # Tor dies when the Crawler does
torrc_config={"CookieAuth": "1"},
tor_log="/var/log/tor/tor.log",
tor_cell_log="/var/log/tor/tor_cell_seq.log",
control_port=9051,
socks_port=9050,
run_in_xvfb=True,
tbb_path=join("/opt","tbb","tor-browser_en-US"),
tb_log_path=join(_log_dir,"firefox.log"),
tb_tor_cfg=USE_RUNNING_TOR,
page_load_timeout=20,
wait_on_page=5,
wait_after_closing_circuits=0,
restart_on_sketchy_exception=True,
additional_control_fields={},
db_handler=None):
self.logger = setup_logging(_log_dir, "crawler")
# Set stem logging level to INFO - "high level library activity"
stem.util.log.get_logger().setLevel(stem.util.log.Runlevel.INFO)
self.torrc_config = torrc_config
self.socks_port = find_free_port(socks_port, control_port)
self.torrc_config.update({"SocksPort": str(self.socks_port)})
self.control_port = find_free_port(control_port, self.socks_port)
self.torrc_config.update({"ControlPort": str(self.control_port)})
self.torrc_config.update({"Log": "INFO file {}".format(tor_log)})
self.logger.info("Starting tor process with config "
"{torrc_config}.".format(**locals()))
self.tor_process = launch_tor_with_config(config=self.torrc_config,
take_ownership=take_ownership)
self.authenticate_to_tor_controlport()
self.logger.info("Opening cell log stream...")
self.cell_log = open(tor_cell_log, "rb")
if run_in_xvfb:
self.logger.info("Starting Xvfb...")
self.run_in_xvfb = True
self.virtual_framebuffer = start_xvfb()
self.logger.info("Starting Tor Browser...")
self.tb_driver = TorBrowserDriver(tbb_path=tbb_path,
tor_cfg=tb_tor_cfg,
tbb_logfile_path=tb_log_path,
socks_port=self.socks_port,
control_port=self.control_port)
self.wait_after_closing_circuits = wait_after_closing_circuits
self.page_load_timeout = page_load_timeout
self.tb_driver.set_page_load_timeout(page_load_timeout)
self.wait_on_page = wait_on_page
self.restart_on_sketchy_exception = restart_on_sketchy_exception
self.control_data = self.get_control_data(page_load_timeout,
wait_on_page,
wait_after_closing_circuits,
additional_control_fields)
self.db_handler = db_handler
if db_handler:
self.crawlid = self.db_handler.add_crawl(self.control_data)
def authenticate_to_tor_controlport(self):
self.logger.info("Authenticating to the tor controlport...")
try:
self.controller = Controller.from_port(port=self.control_port)
except stem.SocketError as exc:
panic("Unable to connect to tor on port {self.control_port}: "
"{exc}".format(**locals()))
try:
self.controller.authenticate()
except stem.connection.MissingPassword:
panic("Unable to authenticate to tor controlport. Please add "
"`CookieAuth 1` to your tor configuration file.")
def get_control_data(self, page_load_timeout, wait_on_page,
wait_after_closing_circuits,
additional_control_fields):
"""Gather metadata about the crawler instance."""
control_data = {}
# Configuration settings
control_data["page_load_timeout"] = page_load_timeout
control_data["wait_on_page"] = wait_on_page
control_data["wait_after_closing_circuits"] = \
wait_after_closing_circuits
if additional_control_fields:
control_data.update(additional_control_fields)
# System facts
control_data["kernel"] = platform.system()
control_data["kernel_version"] = platform.release()
control_data["os"] = platform.version()
control_data["python_version"] = platform.python_version()
ip = urlopen("https://api.ipify.org").read().decode()
control_data["ip"] = ip
# This API seems to be unstable and we haven't found a suitable
# alternative :(
try:
asn_geoip = urlopen("http://api.moocher.io/ip/{}".format(ip))
asn_geoip = literal_eval(asn_geoip.read().decode())
control_data["asn"] = asn_geoip.get("ip").get("as").get("asn")
control_data["city"] = asn_geoip.get("ip").get("city")
control_data["country"] = asn_geoip.get("ip").get("country")
except urllib.error.HTTPError:
self.logger.warning("Unable to query ASN API and thus some "
"control data may be missing from this run.")
control_data["tor_version"] = self.controller.get_version().version_str
control_data["tb_version"] = self.tb_driver.tb_version
# Tor will have multiple entry nodes in its state file, but will
# choose the first sequential one that is up as its entry guard.
entry_nodes = self.controller.get_info("entry-guards").split('\n')
control_data["entry_node"] = next(re.search("[0-9A-F]{40}", g).group(0)
for g in entry_nodes
if re.search("up", g))
control_data["crawler_version"] = _version
return control_data
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, traceback):
self.close()
return self
def __del__(self):
self.close()
def close(self):
self.logger.info("Beginning Crawler exit process...")
if "tb_driver" in dir(self):
self.logger.info("Closing Tor Browser...")
self.tb_driver.quit()
if "virtual_framebuffer" in dir(self):
self.logger.info("Closing the virtual framebuffer...")
# A bug in pyvirtualdisplay triggers a KeyError exception when closing a
# virtual framebuffer if the $DISPLAY environment variable is not set.
try:
stop_xvfb(self.virtual_framebuffer)
except KeyError:
pass
if "cell_log" in dir(self):
self.logger.info("Closing the Tor cell stream...")
self.cell_log.close()
if "tor_process" in dir(self):
self.logger.info("Killing the tor process...")
self.tor_process.kill()
self.logger.info("Crawler exit completed.")
def collect_onion_trace(self, url, hsid=None, extra_fn=None, trace_dir=None,
iteration=0):
"""Crawl an onion service and collect a complete cell sequence for the
activity at the time. Also, record additional information about the
circuits with stem. Optionally, pass a function to execute additional
actions after the page has loaded."""
# Todo: create collect_trace method that works for regular sites as
# well
assert ".onion" in url, ("This method is only suitable for crawling "
"onion services.")
self.logger.info("{url}: closing existing circuits before starting "
"crawl.".format(**locals()))
for circuit in self.controller.get_circuits():
self.controller.close_circuit(circuit.id)
sleep(self.wait_after_closing_circuits)
if not trace_dir:
trace_dir = self.make_ts_dir()
trace_name = urllib.parse.quote(url, safe="") + "-" + str(iteration)
trace_path = join(trace_dir, trace_name)
start_idx = self.get_cell_log_pos()
try:
self.crawl_url(url)
rend_circ_ids = self.get_rend_circ_ids(url)
if extra_fn:
self.execute_extra_fn(url, trace_path, start_idx)
except CrawlerLoggedError:
return "failed"
except CrawlerNoRendCircError:
self.save_debug_log(url, trace_path, start_idx)
return "failed"
except:
self.logger.exception("{url}: unusual exception "
"encountered:".format(**locals()))
# Also log active circuit info
self.controller.get_circuits()
exc_type, exc_value, exc_traceback = exc_info()
if exc_type in _sketchy_exceptions:
self.save_debug_log(url, trace_path, start_idx)
if self.restart_on_sketchy_exception:
self.restart_tb()
return "failed"
self.logger.info("{url}: saving full trace...".format(**locals()))
end_idx = self.get_cell_log_pos()
full_trace = self.get_full_trace(start_idx, end_idx)
# Save the trace to the database or write to file
if self.db_handler:
try:
new_example = {'hsid': hsid,
'crawlid': self.crawlid,
't_scrape': get_timestamp("db")}
except NameError:
panic("If using the database, and calling collect_onion_trace "
"directly, you must specify the hsid of the site.")
exampleid = self.db_handler.add_example(new_example)
self.db_handler.add_trace(str(full_trace), exampleid)
else:
with open(trace_path+"-full", "wb") as fh:
fh.write(full_trace)
return "succeeded"
def make_ts_dir(self, parent_dir=_log_dir, raw_dir_name="batch"):
"""Creates a timestamped folder to hold a group of traces."""
raw_dirpath = join(parent_dir, raw_dir_name)
ts = get_timestamp("log")
ts_dir = timestamp_file(raw_dirpath, ts, is_dir=True)
symlink_cur_to_latest(raw_dirpath, ts)
with open(join(ts_dir, "control.pickle"), "wb") as fh:
pickle.dump(self.control_data, fh)
return ts_dir
def get_cell_log_pos(self):
"""Returns the current position of the last byte in the Tor cell log."""
return self.cell_log.seek(0, SEEK_END)
def crawl_url(self, url):
"""Load a web page in Tor Browser and optionally pass a function
to execute custom actions on it."""
self.logger.info("{url}: starting page load...".format(**locals()))
try:
self.tb_driver.load_url(url, wait_on_page=self.wait_on_page,
wait_for_page_body=True)
except TimeoutException:
self.logger.warning("{url}: timed out.".format(**locals()))
raise CrawlerLoggedError
except http.client.CannotSendRequest:
self.logger.warning("{url}: cannot send request--improper "
"connection state.".format(**locals()))
raise CrawlerLoggedError
# Make sure we haven't just hit an error page or nothing loaded
try:
if (self.tb_driver.is_connection_error_page
or self.tb_driver.current_url == "about:newtab"):
raise CrawlerReachedErrorPage
except CrawlerReachedErrorPage:
self.logger.warning("{url}: reached connection error "
"page.".format(**locals()))
raise CrawlerLoggedError
self.logger.info("{url}: successfully loaded.".format(**locals()))
def get_rend_circ_ids(self, url):
"""Returns the rendezvous circuit id(s) associated with a given onion
service."""
self.logger.info("{url}: collecting circuit "
"information...".format(**locals()))
active_circs = self.controller.get_circuits()
rend_circ_ids = set()
for circ in active_circs:
if (circ.purpose == "HS_CLIENT_REND" and
circ.socks_username and
circ.socks_username in url):
rend_circ_ids.add(circ.id)
# If everything goes perfect, we should only see one. Multiple indicate
# the first failed. Zero indicates one closed abruptly (or there's an
# error with stem--still waiting on data to confirm or deny).
rend_circ_ct = len(rend_circ_ids)
self.logger.info("{url}: {rend_circ_ct} associated rendezvous circuits "
"discovered.".format(**locals()))
if rend_circ_ct == 0:
raise CrawlerNoRendCircError
return rend_circ_ids
def execute_extra_fn(self, url, trace_path, start_idx):
self.logger.info("{url}: executing extra function "
"code...".format(**locals()))
extra_fn(self, url, trace_path, start_idx)
self.logger.info("{url}: extra function executed "
"successfully.".format(**locals()))
def save_debug_log(self, url, trace_path, start_idx):
self.logger.warning("{url}: saving debug log...".format(**locals()))
exc_time = self.get_cell_log_pos()
trace = self.get_full_trace(start_idx, exc_time)
with open(trace_path + "@debug", "wb") as fh:
fh.write(trace)
def get_full_trace(self, start_idx, end_idx):
"""Returns the Tor DATA cells transmitted over a circuit during a
specified time period."""
# Sanity check
assert start_idx >= 0 and end_idx > 0, ("Invalid (negative) logfile "
"position")
assert end_idx > start_idx, ("logfile section end_idx must come "
"after start_idx")
self.cell_log.seek(start_idx, SEEK_SET)
return self.cell_log.read(end_idx - start_idx)
def restart_tb(self):
"""Restarts the Tor Browser."""
self.logger.info("Restarting the Tor Browser...")
self.tb_driver.quit()
self.tb_driver = TorBrowserDriver(tbb_path=tbb_path,
tor_cfg=USE_RUNNING_TOR,
tbb_logfile_path=tb_log_path,
socks_port=self.socks_port,
control_port=self.control_port)
self.logger.info("Tor Browser restarted...")
def collect_set_of_traces(self, url_set, extra_fn=None, trace_dir=None,
iteration=0, shuffle=True, retry=True,
url_to_id_mapping=None):
"""Collect a set of traces."""
if self.db_handler:
if not url_to_id_mapping:
url_to_id_mapping = url_set
trace_dir = None
elif not trace_dir:
trace_dir = self.make_ts_dir()
set_size = len(url_set)
self.logger.info("Saving set of {set_size} traces to "
"{trace_dir}.".format(**locals()))
# Converts both sets (from pickle files) and dicts (whose keys are
# URLs--from database) to URL lists
url_set = list(url_set)
if shuffle:
random.shuffle(url_set)
failed_urls = []
for url_idx in range(set_size):
self.logger.info("Collecting trace {} of "
"{set_size}...".format(url_idx+1, **locals()))
url = url_set[url_idx]
if self.db_handler:
hsid = url_to_id_mapping[url]
else:
hsid = None
if (self.collect_onion_trace(url, hsid=hsid, extra_fn=extra_fn,
trace_dir=trace_dir,
iteration=iteration) == "failed"
and retry):
failed_urls.append(url)
if failed_urls:
failed_ct = len(failed_urls)
self.logger.info("Retrying {failed_ct} of {set_size} traces that "
"failed.".format(**locals()))
self.collect_set_of_traces(failed_urls, extra_fn=extra_fn,
trace_dir=trace_dir,
iteration=iteration, shuffle=shuffle,
retry=False,
url_to_id_mapping=url_to_id_mapping)
def crawl_monitored_nonmonitored(self, monitored_class, nonmonitored_class,
extra_fn=None, shuffle=True, retry=True,
monitored_name="monitored",
nonmonitored_name="nonmonitored",
url_to_id_mapping=None, ratio=40):
"""Crawl a monitored class ratio times interspersed between the
crawling of a(n ostensibly larger) non-monitored class."""
if self.db_handler:
if not url_to_id_mapping:
url_to_id_mapping = nonmonitored_class
url_to_id_mapping.update(monitored_class)
trace_dir, mon_trace_dir, nonmon_trace_dir = (None,) * 3
else:
trace_dir = self.make_ts_dir()
mon_trace_dir = join(trace_dir, monitored_name)
mkdir(mon_trace_dir)
nonmon_trace_dir = join(trace_dir, nonmonitored_name)
mkdir(nonmon_trace_dir)
# db: calling list on a dict returns a list of its keys (URLs)
# pickle: calling list on set is necessary to make it shuffleable
nonmonitored_class = list(nonmonitored_class)
monitored_class = list(monitored_class)
nonmonitored_class_ct = len(nonmonitored_class)
chunk_size = int(nonmonitored_class_ct / ratio)
if shuffle:
random.shuffle(nonmonitored_class)
random.shuffle(monitored_class)
for iteration in range(ratio):
self.logger.info("Beginning iteration {i} of {ratio} in the "
"{monitored_name} class".format(i=iteration+1,
**locals()))
self.collect_set_of_traces(monitored_class,
trace_dir=mon_trace_dir,
iteration=iteration,
url_to_id_mapping=url_to_id_mapping)
slice_lb = iteration * chunk_size
slice_ub = min((iteration + 1) * chunk_size, nonmonitored_class_ct)
self.logger.info("Crawling services {} through {slice_ub} of "
"{nonmonitored_class_ct} in the "
"{nonmonitored_name} "
"class".format(slice_lb + 1, **locals()))
self.collect_set_of_traces(nonmonitored_class[slice_lb:slice_ub],
trace_dir=nonmon_trace_dir,
iteration=iteration,
url_to_id_mapping=url_to_id_mapping)
class Visit(object):
"""Hold info about a particular visit to a page."""
def __init__(self, batch_num, site_num, instance_num, page_url, base_dir, tor_controller, bg_site=None,
experiment=cm.EXP_TYPE_WANG_AND_GOLDBERG, xvfb=False, capture_screen=True):
self.batch_num = batch_num
self.site_num = site_num
self.instance_num = instance_num
self.page_url = page_url
self.bg_site = bg_site
self.experiment = experiment
self.base_dir = base_dir
self.visit_dir = None
self.visit_log_dir = None
self.tbb_version = cm.RECOMMENDED_TBB_VERSION
self.capture_screen = capture_screen
self.tor_controller = tor_controller
self.xvfb = xvfb
self.init_visit_dir()
self.pcap_path = os.path.join(
self.visit_dir, "{}.pcap".format(self.get_instance_name()))
if self.xvfb and not cm.running_in_CI:
wl_log.info("Starting XVFBm %sX%s" % (cm.XVFB_W, cm.XVFB_H))
self.vdisplay = Xvfb(width=cm.XVFB_W, height=cm.XVFB_H)
self.vdisplay.start()
# Create new instance of TorBrowser driver
TorBrowserDriver.add_exception(self.page_url)
self.tb_driver = TorBrowserDriver(tbb_path=cm.TBB_PATH,
tbb_logfile_path=join(self.visit_dir, "logs", "firefox.log"))
self.sniffer = Sniffer() # sniffer to capture the network traffic
def init_visit_dir(self):
"""Create results and logs directories for this visit."""
visit_name = str(self.instance_num)
self.visit_dir = os.path.join(self.base_dir, visit_name)
ut.create_dir(self.visit_dir)
self.visit_log_dir = os.path.join(self.visit_dir, 'logs')
ut.create_dir(self.visit_log_dir)
def get_instance_name(self):
"""Construct and return a filename for the instance."""
inst_file_name = '{}_{}_{}' \
.format(self.batch_num, self.site_num, self.instance_num)
return inst_file_name
def filter_guards_from_pcap(self):
guard_ips = set([ip for ip in self.tor_controller.get_all_guard_ips()])
wl_log.debug("Found %s guards in the concensus.", len(guard_ips))
orig_pcap = self.pcap_path + ".original"
copyfile(self.pcap_path, orig_pcap)
try:
preader = PcapReader(orig_pcap)
pcap_filtered = []
for p in preader:
if IP not in p:
pcap_filtered.append(p)
continue
ip = p.payload
if ip.dst in guard_ips or ip.src in guard_ips:
pcap_filtered.append(p)
wrpcap(self.pcap_path, pcap_filtered)
except Exception as e:
wl_log.error("ERROR: filtering pcap file: %s. Check old pcap: %s",
e, orig_pcap)
else:
os.remove(orig_pcap)
def post_crawl(self):
pass
# TODO: add some sanity checks?
def cleanup_visit(self):
"""Kill sniffer and Tor browser if they're running."""
wl_log.info("Cleaning up visit.")
wl_log.info("Cancelling timeout")
ut.cancel_timeout()
if self.sniffer and self.sniffer.is_recording:
wl_log.info("Stopping sniffer...")
self.sniffer.stop_capture()
# remove non-tor traffic
self.filter_guards_from_pcap()
if self.tb_driver and self.tb_driver.is_running:
# shutil.rmtree(self.tb_driver.prof_dir_path)
wl_log.info("Quitting selenium driver...")
self.tb_driver.quit()
# close all open streams to prevent pollution
self.tor_controller.close_all_streams()
if self.xvfb and not cm.running_in_CI:
wl_log.info("Stopping display...")
self.vdisplay.stop()
# after closing driver and stoping sniffer, we run postcrawl
self.post_crawl()
def take_screenshot(self):
try:
out_png = os.path.join(self.visit_dir, 'screenshot.png')
wl_log.info("Taking screenshot of %s to %s" % (self.page_url,
out_png))
self.tb_driver.get_screenshot_as_file(out_png)
if cm.running_in_CI:
wl_log.debug("Screenshot data:image/png;base64,%s"
% self.tb_driver.get_screenshot_as_base64())
except:
wl_log.info("Exception while taking screenshot of: %s"
% self.page_url)
def get_wang_and_goldberg(self):
"""Visit the site according to Wang and Goldberg (WPES'13) settings."""
ut.timeout(cm.HARD_VISIT_TIMEOUT) # set timeout to stop the visit
self.sniffer.start_capture(self.pcap_path,
'tcp and not host %s and not tcp port 22 and not tcp port 20'
% LOCALHOST_IP)
time.sleep(cm.PAUSE_BETWEEN_INSTANCES)
try:
self.tb_driver.set_page_load_timeout(cm.SOFT_VISIT_TIMEOUT)
except:
wl_log.info("Exception setting a timeout {}".format(self.page_url))
wl_log.info("Crawling URL: {}".format(self.page_url))
t1 = time.time()
self.tb_driver.get(self.page_url)
page_load_time = time.time() - t1
wl_log.info("{} loaded in {} sec"
.format(self.page_url, page_load_time))
time.sleep(cm.WAIT_IN_SITE)
if self.capture_screen:
self.take_screenshot()
self.cleanup_visit()
def get_multitab(self):
"""Open two tab, use one to load a background site and the other to
load the real site."""
PAUSE_BETWEEN_TAB_OPENINGS = 0.5
ut.timeout(cm.HARD_VISIT_TIMEOUT) # set timeout to kill running procs
# load a blank page - a page is needed to send keys to the browser
self.tb_driver.get(BAREBONE_HOME_PAGE)
self.sniffer.start_capture(self.pcap_path,
'tcp and not host %s and not tcp port 22 and not tcp port 20'
% LOCALHOST_IP)
time.sleep(cm.PAUSE_BETWEEN_INSTANCES)
try:
self.tb_driver.set_page_load_timeout(cm.SOFT_VISIT_TIMEOUT)
except:
wl_log.info("Exception setting a timeout {}".format(self.page_url))
wl_log.info("Crawling URL: {} with {} in the background".
format(self.page_url, self.bg_site))
body = self.tb_driver.find_element_by_tag_name("body")
body.send_keys(Keys.CONTROL + 't') # open a new tab
# now that the focus is on the address bar, load the background
# site by "typing" it to the address bar and "pressing" ENTER (\n)
# simulated by send_keys function
body.send_keys('%s\n' % self.bg_site)
# the delay between the loading of background and real sites
time.sleep(PAUSE_BETWEEN_TAB_OPENINGS)
body = self.tb_driver.find_element_by_tag_name("body")
body.send_keys(Keys.CONTROL + 't') # open a new tab
t1 = time.time()
self.tb_driver.get(self.page_url) # load the real site in the 2nd tab
page_load_time = time.time() - t1
wl_log.info("{} loaded in {} sec"
.format(self.page_url, page_load_time))
time.sleep(cm.WAIT_IN_SITE)
if self.capture_screen:
self.take_screenshot()
self.cleanup_visit()
def get(self):
"""Call the specific visit function depending on the experiment."""
if self.experiment == cm.EXP_TYPE_WANG_AND_GOLDBERG:
self.get_wang_and_goldberg()
elif self.experiment == cm.EXP_TYPE_MULTITAB_ALEXA:
self.get_multitab()
else:
raise ValueError("Cannot determine experiment type")
from datetime import datetime
from tbselenium.tbdriver import TorBrowserDriver
from xvfbwrapper import Xvfb
tor_dir = '../tor-browser-patched/Primary/'
vdisplay = Xvfb()
vdisplay.start()
# open list of urls for testing
with open('alexa-top-1000.txt', 'r') as url_file:
test_urls = url_file.readlines()
driver = TorBrowserDriver(tor_dir) #, pref_dict=rfp)
driver.set_page_load_timeout(15)
# do 10 runs
uses = 0
notUses = 0
inconclusive = 0
for i, url in enumerate(test_urls):
try:
# request url from list
#print("Fetching " + str(url),end='')
url = 'https://' + url
driver.get(url)
# pull window.performance.timing after loading the page and add information about url and number of run
perf_timings = driver.execute_script(
"return window.performance.getEntries()")
#print(perf_timings)
class DescargarPdf:
def __init__(self):
self.contadorCredenciales=0
self.tbb_dir = "/usr/local/share/tor-browser_en-US"
self.usuario=[]
self.contraseñaTxT=[]
self.conversor='?convertedTo=pdf'
def iniciarTor(self):
self.zLibraty = TorBrowserDriver(self.tbb_dir, tbb_logfile_path='test.log')
def iniciarSecion(self):
self.element=self.zLibraty.find_element_by_name("email")
self.element.send_keys(self.correo)
sleep(2)
self.element2=self.zLibraty.find_elements_by_class_name("form-control")[1]
self.element2.send_keys(self.contraseña)
self.element2.send_keys(Keys.RETURN)
def paginaDescargas(self):
print("estoy en la funcion paginaDescagas")
self.zLibraty.load_url(self.url)
sleep(4)
self.html=self.zLibraty.page_source
def paginaPrinsipal(self,añoInicial,añoFinal):
self.urlAños='http://zlibraryexau2g3p.onion/s/?yearFrom='+str(añoInicial)+'&yearTo='+str(añoFinal)
self.url=self.urlAños
def cambiarPagina(self,x):
print("estoy en cambiar pagina prinsipal")
self.url+='&page='+str(x)
print(self.url)
def Crearcsv(self):
desde=datosDescarga(1)
asta=datosDescarga(2)
self.carpetaUrl='/home/dd/Documentos/zlibrary/libros'+str(desde)+'-'+str(asta)+'/url'
try :
os.mkdir(self.carpetaUrl)
except OSError as e:
if e.errno != errno.EEXIST:
raise
self.escrivirUrlWed=csv.writer(open('/home/dd/Documentos/zlibrary/libros'+str(desde)+'-'+str(asta)+'/url/url2.csv','w'))
self.imprimirUrlPdf=csv.writer(open('/home/dd/Documentos/zlibrary/libros'+str(desde)+'-'+str(asta)+'/url/urlDowload2.csv','w'))
def credenciales(self,numeroUsuario):
print("llegue")
if self.contadorCredenciales==0 or self.contadorCredenciales==20:
self.zLibraty.load_url("https://singlelogin.org/")
self.zLibraty.find_element_by_name("redirectToHost").click()
sleep(3)
pyautogui.press("down")
sleep(2)
pyautogui.press("down")
sleep(1)
pyautogui.press("enter")
sleep(5)
self.correo=self.usuario[numeroUsuario]
self.contraseña=self.contraseñaTxT[numeroUsuario]
def UsuariosYcontraseñas(self):
self.dir='/home/dd/Documentos/zlibrary/credenciales/contraseñasYcorreos.txt'
self.data=open(self.dir,'r+')
for self.i in range(0,200):
if self.i%2==0 :
self.usuario.append(self.data.readline())
if self.i%2!=0:
self.contraseñaTxT.append(self.data.readline())
def urlPdf(self,):
self.contadorCredenciales=1
self.boleanoPdf=0
self.respaldoContador=0
self.contadorUsuarios=usuarioUsadosLeer()
self.contadorLibros=datosDescarga(4)
self.contadorLibros2=self.contadorLibros%10
self.Crearcsv()
self.soup=BeautifulSoup(self.html,'html.parser')
try:
for self.urlwed in self.soup.find_all(itemprop = "name") :
self.contador=0
self.urlwed=self.urlwed.find('a',href=re.compile(''))
self.urlDowload=self.urlwed.get('href')
self.urlpdfGeleneralH=re.sub('/book/','https://b-ok.cc/book/',self.urlDowload)
self.urlDowload=re.sub('/book/','http://zlibraryexau2g3p.onion/book/',self.urlDowload)
self.escrivirUrlWed.writerow([self.urlDowload])
print(self.urlDowload)
self.voleano=validarFormato(self.urlpdfGeleneralH)
guardarNumeroDescargas(self.contadorLibros)
print(self.respaldoContador)
if self.contadorLibros==self.respaldoContador:
for self.urlRedirec in range(0,1):
self.zLibraty.load_url(self.urlDowload)
sleep(5)
self.htmlPdf=self.zLibraty.page_source
self.soupRedirec=BeautifulSoup(self.htmlPdf,'html.parser')
self.urlDowloadPDF=self.soupRedirec.find(class_="btn btn-primary dlButton addDownloadedBook")
self.urlDowloadPDF=self.urlDowloadPDF.get('href')
self.urlDowloadPDF=re.sub('/dl/','http://zlibraryexau2g3p.onion/dl/',self.urlDowloadPDF)
self.imprimirUrlPdf.writerow([self.urlDowloadPDF])
print(self.urlDowloadPDF)
print("vamos a por el if")
sleep(15)
if self.voleano==True:
self.zLibraty.set_page_load_timeout(12)
try:
self.zLibraty.load_url(self.urlDowloadPDF)
except:
sleep(5)
self.zLibraty.set_page_load_timeout(7000)
print("funciona PDF ")
self.voleano=False
sleep(5)
self.contadorLibros+=1
self.contadorLibros2+=1
else:
self.zLibraty.set_page_load_timeout(12)
try:
self.zLibraty.load_url(self.urlDowloadPDF)
except:
sleep(8)
pyautogui.press("down")
sleep(2)
pyautogui.press("enter")
self.zLibraty.set_page_load_timeout(7000)
sleep(5)
self.contadorLibros+=1
self.contadorLibros2+=1
self.zLibraty.load_url("about:downloads")
self.datosEsperaDescarga()
self.peticiones()
self.zLibraty.back()
informaiconPdf(self.urlpdfGeleneralH)
guardarNumeroDescargas(self.contadorLibros)
self.respaldoContador+=1
if self.contadorLibros==self.respaldoContador:
if self.contadorLibros2%10==0:
print((self.contadorLibros2-1)%10)
self.contador+=1
if self.contadorLibros==20:
self.contadorCredenciales=20
print("saliendo de secion¡¡¡¡¡¡")
pyautogui.moveTo(1707,245)
pyautogui.hotkey("ctrl","shift","u")
sleep(2)
pyautogui.press("enter")
sleep(7)
pyautogui.press("enter")
sleep(15)
else:
print("saliendo de secion")
self.zLibraty.get("http://zlibraryexau2g3p.onion/logout.php")
self.contadorUsuarios+=1
print(self.contadorUsuarios)
try:
self.zLibraty.switch_to_window(self.zLibraty.window_handles[0])
except:
print("error al cambian de ventana")
usuarioUsadosReescrivir(self.contadorUsuarios)
print("por aqui¿¿¿¿¿¿")
self.credenciales(self.contadorUsuarios)
self.contadorCredenciales=1
print("no por aqui¿¿¿¿¿¿")
sleep(20)
self.iniciarSecion()
sleep(15)
self.paginaDescargas()
sleep(7)
self.contadorLibros2=0
sleep(15)
print("numero de li bros por usuario ",self.contadorLibros2)
if self.contador==5:
self.contador=0
except OSError as e :
print(e.strerror)
print("error en la urlPdf:::::")
guardarNumeroDescargas(self.contadorLibros)
usuarioUsadosReescrivir(self.contadorUsuarios)
print(self.contadorLibros)
archivos=int(contarNueroArchivos())
print(archivos)
self.zLibraty.load_url("about:downloads")
self.datosEsperaDescarga()
self.peticiones()
self.zLibraty.back()
informaiconPdf(self.urlpdfGeleneralH)
def DescargarContenido(self,_html):
self.contenido=_html
def serrarTor(self):
self.zLibraty.close()
def datosEsperaDescarga(self):
sleep(4)
self.htmlValidador=self.zLibraty.page_source
def validarDescarga(self):
self.htmlFalce=self.zLibraty.page_source
self.soupFalce=BeautifulSoup(self.htmlFalce,"html.parser")
self.validarfalce=self.soupFalce.find_all("description",class_="downloadDetails downloadDetailsNormal")
self.respuestafalce=re.search("value=.+",str(self.validarfalce))
self.buscarFalse=self.respuestafalce.group()
if re.search("Canceled",self.buscarFalse):
print("se daño al descarga =(")
sleep(5)
pyautogui.click(1393,139)
sleep(5)
else :
if re.search("Failed",self.buscarFalse):
print("se daño al descarga pero vamos a solucionarlo =( ")
sleep(5)
pyautogui.click(1393,139)
sleep(5)
else:
print("la descarga va bien =)")
def peticiones(self):
self.validarDescarga()
self.carga=0
self.daño=0
self.conteo=0
while self.carga<100:
self.soup=BeautifulSoup(self.htmlValidador,"html.parser")
try:
self.archivoDescarga=self.soup.find_all("progress",class_="downloadProgress")
self.respaldo=re.split("value",str(self.archivoDescarga))
self.tiempo=re.search("[0-9]+",self.respaldo[1])
print(self.tiempo.group())
self.carga=int(self.tiempo.group())
self.datosEsperaDescarga()
sleep(3)
self.validarDescarga()
if self.conteo==3:
pyautogui.press("enter")
self.conteo=0
except:
print("o no ,se daño la descargar y no la e podido volver a iniciar")
if self.daño==7:
os.system('rm -r /home/dd/zlibros/libros1920-1921/libro/*.*')
raise
self.daño+=1
sleep(5)