class DCrawl(consoleNg.Console):
def __init__(self,
threads=2,
reject=[],
store=False,
proxy=None,
cookie=None):
self.FormAnalysis = WebAnalyzer(forms=True)
self.running = False
self.stopped = False
self.CFG_threads = threads
self.runningThreads = 0
self.CFG_store = store
self.CFG_reject = reject + [
"jpg", "gif", "png", "zip", "exe", "doc", "swf", "rar", "pdf"
]
self.totalUrls = 0
self.doneUrls = 0
self.POOL = []
self.Done = {}
self.CFG_proxy = proxy
self.urlOKS = []
if cookie:
self.CFG_cookie = cookie
else:
self.CFG_cookie = None
self.threads_list = []
self.Semaphore = threading.BoundedSemaphore(value=self.CFG_threads)
self.Semaphore_Mutex = threading.BoundedSemaphore(value=1)
self.reReject = []
self.reNeeded = None
consoleNg.Console.__init__(self, "dcrawl> ")
self.Handler = None
self.Requests = []
def addReject(self, regex):
'''para paths que no se quieren visitar'''
self.reReject.append(re.compile(regex, re.I))
def getRejects(self):
return self.reReject
def addNeeded(self, regex):
'''Regexp que se debe cumplir para que se visite la url'''
if regex:
self.reNeeded = re.compile(regex, re.I)
else:
self.reNeeded = None
def reset(self):
self.running = False
self.stopped = True
self.Handler.join()
self.totalUrls = 0
self.doneUrls = 0
self.POOL = []
self.Done = {}
self.Requests = []
self.FormAnalysis = WebAnalyzer(forms=True)
def continueWith(self, url):
'''Logica que decide si se visita o no una URL'''
if url not in self.Done:
for i in self.reReject:
if i.findall(url):
return False
if self.reNeeded and not self.reNeeded.findall(url):
print url
return False
return True
return False
def __setattr__(self, item, value):
'''Utilizado nada mas para la version consola'''
if item == "CFG_threads":
if self.running:
raise Exception, "Crawler running!!! Wait to finish"
self.__dict__[item] = value
self.Semaphore = threading.BoundedSemaphore(value=self.CFG_threads)
return
self.__dict__[item] = value
def __getattr__(self, item):
'''Utilizado nada mas para la version consola'''
if item == "CFG_threads":
return self.threads
else:
raise AttributeError(item)
def status(self):
return self.doneUrls, self.totalUrls
def stop(self):
self.running = False
self.stopped = True
if self.Handler:
self.Handler.join()
def restart(self):
self.running = True
self.stopped = False
self.Launch()
def append(self, url):
'''append una url en el pool de salida y ejecuta el carwler si esta parado'''
if self.continueWith(url):
self.Semaphore_Mutex.acquire()
self.totalUrls += 1
self.POOL.append(url)
self.Done[url] = True
if url[-1] != "/":
tmp = url.split("/")
url = "/".join(tmp[:-1]) + "/"
self.Semaphore_Mutex.release()
if not self.running and not self.stopped:
self.running = True
self.Launch()
def postFetch(self, str, url):
'''Funcion que agrega las urls al pool final o bien guarda todo a HDD'''
if str:
if self.CFG_store:
_, dom, path, pre, vars, _ = urlparse(url)
if path[-1] == '/' and not pre and not vars:
path = [dom] + path.split('/')
file = "index.html"
else:
path = path.split('/')
file = path[-1]
if pre:
file += ";" + pre
if vars:
file += "?" + vars
path = [dom] + path[:-1]
path = [i for i in path if i]
dirs = ""
for i in path:
dirs = os.path.join(dirs, i)
try:
os.makedirs(dirs)
print "Making dir: ", dirs
except:
pass
finalpath = os.path.join(dirs, file)
f = open(finalpath, "w")
f.write(str)
print "writting: ", finalpath
f.close()
else:
self.FormAnalysis.appendPage(str, url)
def getForms(self):
'''deprecated'''
dic = self.FormAnalysis.formSummary()
for i, j in dic.items():
print j, i
def getDynPages(self):
'''deprecated'''
for i in self.FormAnalysis.getDynPages():
print i
def getInfo(self):
'''deprecated'''
print self.FormAnalysis.infoSummary()
def wait(self):
while self.running:
sleep(1)
def getAllPools(self):
res = self.POOL
self.POOL = []
return res
def Launch(self):
self.Handler = threading.Thread(target=self.threadHandler, kwargs={})
self.Handler.start()
def threadHandler(self):
while self.running:
urls = self.getAllPools()
if not urls:
self.running = False
break
for url in urls:
if not self.running:
break
path = urlparse(url)[2]
if "." in path:
ext = urlparse(url)[2].split(".")[-1]
else:
ext = ""
if ext in self.CFG_reject:
self.postFetch(None, url)
self.doneUrls += 1
continue
self.Semaphore.acquire()
th = threading.Thread(target=self.crawl, kwargs={"url": url})
th.start()
self.threads_list.append(th)
temp = []
for thr in self.threads_list:
if not thr.isAlive():
temp.append(thr)
for i in temp:
i.join()
self.threads_list.remove(i)
if not self.running:
for i in self.threads_list:
i.join()
self.threads_list = []
def crawl(self, url):
try:
sl = SearchLinks(url)
sl.setProxy(self.CFG_proxy)
sl.addCookie(self.CFG_cookie)
for j in sl:
self.append(j)
if sl.status != "Ok":
print "fallo en", url
else:
self.Semaphore_Mutex.acquire()
self.Requests.append(sl.getRequest())
self.Semaphore_Mutex.release()
self.urlOKS.append(url)
#self.CFG_cookie=sl.getCookie()
self.postFetch(sl.getResponse(), url)
except Exception, er:
print "Crawler: ", er
self.Semaphore_Mutex.acquire()
self.doneUrls += 1
self.Semaphore_Mutex.release()
self.Semaphore.release()
class DCrawl(consoleNg.Console):
def __init__(self, threads=2, reject=[], store=False, proxy=None, cookie=None):
self.FormAnalysis = WebAnalyzer(forms=True)
self.running = False
self.stopped = False
self.CFG_threads = threads
self.runningThreads = 0
self.CFG_store = store
self.CFG_reject = reject + ["jpg", "gif", "png", "zip", "exe", "doc", "swf", "rar", "pdf"]
self.totalUrls = 0
self.doneUrls = 0
self.POOL = []
self.Done = {}
self.CFG_proxy = proxy
self.urlOKS = []
if cookie:
self.CFG_cookie = cookie
else:
self.CFG_cookie = None
self.threads_list = []
self.Semaphore = threading.BoundedSemaphore(value=self.CFG_threads)
self.Semaphore_Mutex = threading.BoundedSemaphore(value=1)
self.reReject = []
self.reNeeded = None
consoleNg.Console.__init__(self, "dcrawl> ")
self.Handler = None
self.Requests = []
def addReject(self, regex):
"""para paths que no se quieren visitar"""
self.reReject.append(re.compile(regex, re.I))
def getRejects(self):
return self.reReject
def addNeeded(self, regex):
"""Regexp que se debe cumplir para que se visite la url"""
if regex:
self.reNeeded = re.compile(regex, re.I)
else:
self.reNeeded = None
def reset(self):
self.running = False
self.stopped = True
self.Handler.join()
self.totalUrls = 0
self.doneUrls = 0
self.POOL = []
self.Done = {}
self.Requests = []
self.FormAnalysis = WebAnalyzer(forms=True)
def continueWith(self, url):
"""Logica que decide si se visita o no una URL"""
if url not in self.Done:
for i in self.reReject:
if i.findall(url):
return False
if self.reNeeded and not self.reNeeded.findall(url):
print url
return False
return True
return False
def __setattr__(self, item, value):
"""Utilizado nada mas para la version consola"""
if item == "CFG_threads":
if self.running:
raise Exception, "Crawler running!!! Wait to finish"
self.__dict__[item] = value
self.Semaphore = threading.BoundedSemaphore(value=self.CFG_threads)
return
self.__dict__[item] = value
def __getattr__(self, item):
"""Utilizado nada mas para la version consola"""
if item == "CFG_threads":
return self.threads
else:
raise AttributeError(item)
def status(self):
return self.doneUrls, self.totalUrls
def stop(self):
self.running = False
self.stopped = True
if self.Handler:
self.Handler.join()
def restart(self):
self.running = True
self.stopped = False
self.Launch()
def append(self, url):
"""append una url en el pool de salida y ejecuta el carwler si esta parado"""
if self.continueWith(url):
self.Semaphore_Mutex.acquire()
self.totalUrls += 1
self.POOL.append(url)
self.Done[url] = True
if url[-1] != "/":
tmp = url.split("/")
url = "/".join(tmp[:-1]) + "/"
self.Semaphore_Mutex.release()
if not self.running and not self.stopped:
self.running = True
self.Launch()
def postFetch(self, str, url):
"""Funcion que agrega las urls al pool final o bien guarda todo a HDD"""
if str:
if self.CFG_store:
_, dom, path, pre, vars, _ = urlparse(url)
if path[-1] == "/" and not pre and not vars:
path = [dom] + path.split("/")
file = "index.html"
else:
path = path.split("/")
file = path[-1]
if pre:
file += ";" + pre
if vars:
file += "?" + vars
path = [dom] + path[:-1]
path = [i for i in path if i]
dirs = ""
for i in path:
dirs = os.path.join(dirs, i)
try:
os.makedirs(dirs)
print "Making dir: ", dirs
except:
pass
finalpath = os.path.join(dirs, file)
f = open(finalpath, "w")
f.write(str)
print "writting: ", finalpath
f.close()
else:
self.FormAnalysis.appendPage(str, url)
def getForms(self):
"""deprecated"""
dic = self.FormAnalysis.formSummary()
for i, j in dic.items():
print j, i
def getDynPages(self):
"""deprecated"""
for i in self.FormAnalysis.getDynPages():
print i
def getInfo(self):
"""deprecated"""
print self.FormAnalysis.infoSummary()
def wait(self):
while self.running:
sleep(1)
def getAllPools(self):
res = self.POOL
self.POOL = []
return res
def Launch(self):
self.Handler = threading.Thread(target=self.threadHandler, kwargs={})
self.Handler.start()
def threadHandler(self):
while self.running:
urls = self.getAllPools()
if not urls:
self.running = False
break
for url in urls:
if not self.running:
break
path = urlparse(url)[2]
if "." in path:
ext = urlparse(url)[2].split(".")[-1]
else:
ext = ""
if ext in self.CFG_reject:
self.postFetch(None, url)
self.doneUrls += 1
continue
self.Semaphore.acquire()
th = threading.Thread(target=self.crawl, kwargs={"url": url})
th.start()
self.threads_list.append(th)
temp = []
for thr in self.threads_list:
if not thr.isAlive():
temp.append(thr)
for i in temp:
i.join()
self.threads_list.remove(i)
if not self.running:
for i in self.threads_list:
i.join()
self.threads_list = []
def crawl(self, url):
try:
sl = SearchLinks(url)
sl.setProxy(self.CFG_proxy)
sl.addCookie(self.CFG_cookie)
for j in sl:
self.append(j)
if sl.status != "Ok":
print "fallo en", url
else:
self.Semaphore_Mutex.acquire()
self.Requests.append(sl.getRequest())
self.Semaphore_Mutex.release()
self.urlOKS.append(url)
# self.CFG_cookie=sl.getCookie()
self.postFetch(sl.getResponse(), url)
except Exception, er:
print "Crawler: ", er
self.Semaphore_Mutex.acquire()
self.doneUrls += 1
self.Semaphore_Mutex.release()
self.Semaphore.release()
