def get_requests_from_robots(self, request):
purl = urlsplit(request.url)
url = "%s://%s/robots.txt" % (purl.scheme, purl.netloc)
getreq = Request(REQTYPE_LINK, "GET", url)
try:
# request, timeout, retries=None, useragent=None, proxy=None):
httpget = HttpGet(getreq, 10, 1, "Googlebot", Shared.options['proxy'])
lines = httpget.get_file().split("\n")
except urllib2.HTTPError:
return []
except:
raise
requests = []
for line in lines:
directive = ""
url = None
try:
directive, url = re.sub("\#.*","",line).split(":",1)
except:
continue # ignore errors
if re.match("(dis)?allow", directive.strip(), re.I):
req = Request(REQTYPE_LINK, "GET", url.strip(), parent=request)
requests.append(req)
return adjust_requests(requests) if requests else []
def get_requests_from_robots(self, request):
purl = urlsplit(request.url)
url = "%s://%s/robots.txt" % (purl.scheme, purl.netloc)
getreq = Request(REQTYPE_LINK,
"GET",
url,
extra_headers=Shared.options['extra_headers'])
try:
# request, timeout, retries=None, useragent=None, proxy=None):
httpget = HttpGet(getreq, 10, 1, "Googlebot",
Shared.options['proxy'])
lines = httpget.get_file().split("\n")
except urllib.error.HTTPError:
return []
except:
return []
#raise
requests = []
for line in lines:
directive = ""
url = None
try:
directive, url = re.sub("\#.*", "", line).split(":", 1)
except:
continue # ignore errors
if re.match("(dis)?allow", directive.strip(), re.I):
req = Request(REQTYPE_LINK, "GET", url.strip(), parent=request)
requests.append(req)
return adjust_requests(requests) if requests else []
def crawl(self):
while True:
url = None
cookies = []
requests = []
requests_to_crawl = []
redirects = 0
errors = []
try:
request = self.wait_request()
except ThreadExitRequestException:
if os.path.exists(self.cookie_file):
os.remove(self.cookie_file)
return
except Exception as e:
print "-->" + str(e)
continue
url = request.url
purl = urlsplit(url)
probe = None
probe = self.send_probe(request, errors)
if probe:
if probe.status == "ok" or probe.errcode == ERROR_PROBE_TO:
requests = probe.requests
if probe.html:
request.html = probe.html
else:
errors.append(ERROR_PROBEFAILURE)
# get urls with python to continue crawling
if Shared.options['use_urllib_onerror'] == False:
continue
try:
hr = HttpGet(request, Shared.options['process_timeout'],
self.process_retries,
Shared.options['useragent'],
Shared.options['proxy'])
requests = hr.get_requests()
except Exception as e:
errors.append(str(e))
# set out_of_scope, apply user-supplied filters to urls (ie group_qs)
adjust_requests(requests)
Shared.main_condition.acquire()
res = CrawlResult(request, requests, errors)
Shared.crawl_results.append(res)
Shared.main_condition.notify()
Shared.main_condition.release()
def crawl(self): while True: url = None cookies = [] requests = [] requests_to_crawl = [] redirects = 0 errors = [] try: request = self.wait_request() except ThreadExitRequestException: if os.path.exists(self.cookie_file): os.remove(self.cookie_file) return except Exception as e: print "-->"+str(e) continue url = request.url purl = urlsplit(url) probe = None probe = self.send_probe(request, errors) if probe: if probe.status == "ok" or probe.errcode == ERROR_PROBE_TO: requests = probe.requests if probe.html: request.html = probe.html else : errors.append(ERROR_PROBEFAILURE) # get urls with python to continue crawling if Shared.options['use_urllib_onerror'] == False: continue try: hr = HttpGet(request, Shared.options['process_timeout'], self.process_retries, Shared.options['useragent'], Shared.options['proxy']) requests = hr.get_requests() except Exception as e: errors.append(str(e)) # set out_of_scope, apply user-supplied filters to urls (ie group_qs) adjust_requests(requests) Shared.main_condition.acquire() res = CrawlResult(request, requests, errors) Shared.crawl_results.append(res) Shared.main_condition.notify() Shared.main_condition.release()
def crawl(self):
while True:
if self.exit:
return
requests = []
errors = []
try:
request = self.wait_request()
except ThreadExitRequestException:
if os.path.exists(self.cookie_file):
os.remove(self.cookie_file)
return
except Exception as e:
print("crawl_thread err -->" + e)
continue
probe = self.send_probe(request, errors)
if probe:
requests = probe.requests
if probe.html:
request.html = probe.html
if probe.page_hash:
request.page_hash = probe.page_hash
if len(probe.user_output) > 0:
request.user_output = probe.user_output
errors.append(probe.errmessage)
else:
errors.append(ERROR_PROBEFAILURE)
# get urls with python to continue crawling
if not Shared.options['use_urllib_onerror']:
continue
try:
hr = HttpGet(request, Shared.options['process_timeout'], 1,
Shared.options['useragent'],
Shared.options['proxy'],
Shared.options['extra_headers'])
requests = hr.get_requests()
except Exception as e:
errors.append(str(e))
# set out_of_scope, apply user-supplied filters to urls (ie group_qs)
requests = adjust_requests(requests)
Shared.main_condition.acquire()
res = CrawlResult(request, requests, errors,
probe.page_hash if probe else "")
Shared.crawl_results.append(res)
Shared.main_condition.notify()
Shared.main_condition.release()
self.wait_pause()
def send(self, req_timeout=5, ignore_errors=False): http = HttpGet(self.request, req_timeout, proxy=self._scanner.proxy, useragent=self._scanner.user_agent, extra_headers=self._scanner.extra_headers) cookies = [] if self._scanner.cookies: cookies.extend(self._scanner.cookies) if self.cookie: cookies.extend(self.cookie) #cookies = self.cookie + (self._scanner.cookies if self._scanner.cookies else []) resp = http.send_request(method=self.method, url=self.url, data=self.body, cookies=cookies, ignore_errors=ignore_errors) return MutationResponse(self, resp)
def check_startrequest(self, request): h = HttpGet(request, Shared.options['process_timeout'], 2, Shared.options['useragent'], Shared.options['proxy']) try: h.get_requests() except NotHtmlException: print "\nError: Document is not html" sys.exit(1) except Exception as e: print "\nError: unable to open url: %s" % e sys.exit(1)
def check_startrequest(self, request): h = HttpGet(request, Shared.options['process_timeout'], 2, Shared.options['useragent'], Shared.options['proxy']) try: h.get_requests() except NotHtmlException: print "\nError: Document is not html" sys.exit(1) except Exception as e: print "\nError: unable to open url: %s" % e sys.exit(1)
def _crawl(self):
while True:
requests = []
errors = []
try:
request = self._wait_request()
except ThreadExitRequestException:
if os.path.exists(self._cookie_file):
os.remove(self._cookie_file)
return
except Exception as e:
print("-->" + str(e))
continue
probe = self._send_probe(request, errors)
if probe:
if probe.status == "ok" or probe.errcode == ERROR_PROBE_TO:
requests = probe.requests
if len(probe.user_output) > 0:
request.user_output = probe.user_output
# if the probe return some cookies set it has the last one
if probe.cookies:
Shared.end_cookies = probe.cookies
else:
errors.append(ERROR_PROBEFAILURE)
# get urls with python to continue crawling
if not Shared.options['use_urllib_onerror']:
continue
try:
hr = HttpGet(request, Shared.options['process_timeout'],
CrawlerThread._PROCESS_RETRIES,
Shared.options['user_agent'],
Shared.options['proxy'])
requests = hr.get_requests()
except Exception as e:
errors.append(str(e))
# set out_of_scope, apply user-supplied filters to urls (ie group_qs)
adjust_requests(requests)
Shared.main_condition.acquire()
res = CrawlResult(request, requests, errors)
Shared.crawl_results.append(res)
Shared.main_condition.notify()
Shared.main_condition.release()
def _check_request(request):
"""
check if the given request resolve and return proper html file
:param request:
:return:
"""
h = HttpGet(request, Shared.options['process_timeout'], 2,
Shared.options['user_agent'], Shared.options['proxy'])
try:
h.get_requests()
except NotHtmlException:
print("\nError: Document is not html")
sys.exit(1)
except Exception as e:
print("\nError: unable to open url: %s" % e)
sys.exit(1)
def send_request(self, req, url=None, method=None, data=None, cookies=None, user_agent=None, proxy=None, extra_headers=None, req_timeout=5, ignore_errors=False):
if not proxy:
proxy = self.proxy
if not user_agent:
user_agent = self.user_agent
if not extra_headers:
extra_headers = self.extra_headers
http = HttpGet(req, req_timeout, proxy=proxy, useragent=user_agent, extra_headers=extra_headers ) #{"proto":"http", "host":"127.0.0.1","port":"8080"})
#http = HttpGet(self.request, req_timeout)
allcookies = []
if cookies:
allcookies.extend(cookies)
if self.cookies:
allcookies.extend(self.cookies)
http = HttpGet(req, req_timeout, proxy=proxy, useragent=user_agent, extra_headers=extra_headers)
return http.send_request(method=method, url=url, data=data, cookies=allcookies, ignore_errors=ignore_errors)
def _get_requests_from_robots(start_request):
"""
read robots.txt file (if any) and create a list of request based on it's content
:return: list of request
"""
purl = urlsplit(start_request.url)
url = "%s://%s/robots.txt" % (purl.scheme, purl.netloc)
getreq = Request(REQTYPE_LINK, "GET", url)
try:
# request, timeout, retries=None, user_agent=None, proxy=None):
httpget = HttpGet(getreq, 10, 1, "Googlebot",
Shared.options['proxy'])
lines = httpget.get_file().split("\n")
except urllib2.HTTPError:
return []
except:
raise
requests = []
for line in lines:
directive = ""
url = None
try:
directive, url = re.sub("\#.*", "", line).split(":", 1)
except Exception as e:
print(str(e))
continue # ignore errors
if re.match("(dis)?allow", directive.strip(), re.I):
req = Request(REQTYPE_LINK,
"GET",
url.strip(),
parent=start_request)
if request_is_crawlable(req):
requests.append(req)
return adjust_requests(requests) if requests else []
def rawsend(self,
url,
method=None,
data=None,
cookies=None,
user_agent=None,
proxy=None,
extra_headers=None,
req_timeout=5,
ignore_errors=False):
if not method:
method = METHOD_GET
req = Request(REQTYPE_LINK, method, url)
http = HttpGet(req,
req_timeout,
proxy=proxy,
useragent=user_agent,
extra_headers=extra_headers)
return http.send_request(method=method,
url=url,
data=data,
cookies=cookies,
ignore_errors=ignore_errors)
def crawl(self): while True: url = None cookies = [] requests = [] requests_to_crawl = [] redirects = 0 errors = [] try: request = self.wait_request() except ThreadExitRequestException: if os.path.exists(self.cookie_file): os.remove(self.cookie_file) return except Exception as e: print "-->"+str(e) continue url = request.url purl = urlsplit(url) if request_depth(request) > Shared.options['max_depth'] or request_post_depth(request) > Shared.options['max_post_depth']: Shared.th_lock_db.acquire() Shared.database.save_request_response_data(request.db_id, errors=[ERROR_CRAWLDEPTH]) Shared.th_lock_db.release() continue if request.out_of_scope: continue probe = None probe = self.send_probe(request, errors) if probe: if probe.status == "ok" or probe.errcode == ERROR_PROBE_TO: if probe.redirect: # @todo: should redirect of the first url replace Shared.starturl ??? redirects = request.redirects + 1 reqtypes_to_crawl = [REQTYPE_LINK, REQTYPE_REDIRECT] if Shared.options['mode'] == CRAWLMODE_AGGRESSIVE and Shared.options['crawl_forms']: reqtypes_to_crawl.append(REQTYPE_FORM) requests_to_crawl.extend(probe.get_requests_for_crawler(reqtypes_to_crawl)) requests = probe.requests if probe.html: request.html = probe.html else : errors.append(ERROR_PROBEFAILURE) # get urls with python to continue crawling if Shared.options['use_urllib_onerror'] == False: continue try: hr = HttpGet(request, Shared.options['process_timeout'], self.process_retries, Shared.options['useragent'], Shared.options['proxy']) requests = hr.get_requests() requests_to_crawl.extend(requests) except Exception as e: errors.append(str(e)) # set out_of_scope, apply user-supplied filters to urls (ie group_qs) adjust_requests(requests) notify = False Shared.th_condition.acquire() for req in requests_to_crawl: if req.redirects > Shared.options['max_redirects']: errors.append(ERROR_MAXREDIRECTS) # shoud use BREAK instead... if its a redirect len(requests_to_crawl) = 1 continue if not req in Shared.requests: Shared.requests.append(req) notify = True if notify: Shared.th_condition.notifyAll() Shared.th_condition.release() Shared.th_lock_db.acquire() Shared.database.save_request_response_data(request.db_id, errors=errors, html=request.html) Shared.database.connect() for r in requests: Shared.database.save_request(r) Shared.database.close() Shared.th_lock_db.release()