def main():
args = parser.parse_args()
with open('./keys.json', 'r') as k:
keys = json.load(k)
p = Pyscape(**keys)
urls = []
with open(args.src, 'r') as s:
for line in s:
urls.append(line.rstrip())
data = []
for batch in batch_urls(urls, 10):
data.extend(p.batch_url_metrics(batch).json())
print('%s URLs returned' % (len(data)))
with codecs.open(args.dest, 'w', encoding='utf-8') as outfile:
write_csv(outfile, data)
def main():
args = parser.parse_args()
with open('./keys.json', 'r') as k:
keys = json.load(k)
p = Pyscape(**keys)
urls = []
with open(args.src, 'r') as s:
for line in s:
urls.append(line.rstrip())
data = []
for batch in batch_urls(urls, 10):
data.extend(p.batch_url_metrics(batch).json())
print('%s URLs returned' % (len(data)))
with codecs.open(args.dest, 'w', encoding='utf-8') as outfile:
write_csv(outfile, data)
class PyscapeAuthTestCase(unittest.TestCase):
def setUp(self):
self.valid_instance = Pyscape(**VALID_KEYS)
self.bad_instance = Pyscape(**BAD_KEYS)
def test_auth_success(self):
"""Test something."""
self.assertEqual(200, self.valid_instance.get_index_stats().status_code)
def test_auth_fail(self):
"""Test something."""
self.assertEqual(401, self.bad_instance.get_index_stats().status_code)
def test_get_url_metrics(self):
r = self.valid_instance.get_url_metrics('distilled.net')
return self.assertEqual('distilled.net/', r.json()['uu'])
def test_get_anchor_text(self):
r = self.valid_instance.get_anchor_text('distilled.net')
return self.assertTrue('aput' in r.json()[0])
def test_get_links(self):
r = self.valid_instance.get_links('distilled.net')
return self.assertTrue('luuu' in r.json()[0])
def test_get_top_pages(self):
r = self.valid_instance.get_top_pages('distilled.net')
return self.assertTrue('uu' in r.json()[0])
class PyscapeAuthTestCase(unittest.TestCase):
def setUp(self):
self.valid_instance = Pyscape(**VALID_KEYS)
self.bad_instance = Pyscape(**BAD_KEYS)
def test_auth_success(self):
"""Test something."""
self.assertEqual(200,
self.valid_instance.get_index_stats().status_code)
def test_auth_fail(self):
"""Test something."""
self.assertEqual(401, self.bad_instance.get_index_stats().status_code)
def test_get_url_metrics(self):
r = self.valid_instance.get_url_metrics('distilled.net')
return self.assertEqual('distilled.net/', r.json()['uu'])
def test_get_anchor_text(self):
r = self.valid_instance.get_anchor_text('distilled.net')
return self.assertTrue('aput' in r.json()[0])
def test_get_links(self):
r = self.valid_instance.get_links('distilled.net')
return self.assertTrue('luuu' in r.json()[0])
def test_get_top_pages(self):
r = self.valid_instance.get_top_pages('distilled.net')
return self.assertTrue('uu' in r.json()[0])
def setUp(self):
self.valid_instance = Pyscape(**VALID_KEYS)
self.bad_instance = Pyscape(**BAD_KEYS)
def downloadURL(self, url, check):
# on doit déjà regarder si c'est une url qui commence par http
if ( not url.startswith("http") ) :
return False
if check :
self.logMessage("down url CHECK : " + url)
if self.stopThread :
self._is_running = False
return
# on va indiquer si on doit regarder le whois et les stats du domaine
regardeWhois = False
traitement = False
try :
if check :
# on doit savoir si on vérifier le domaine ou toute l'url
if self.varRadioDomain.get() == 2 :
parsed_uri = urlparse(url)
url = '{uri.scheme}://{uri.netloc}/'.format(uri=parsed_uri)
if url in self.queueUrlsChecked :
return False
self.queueUrlsChecked.put(url)
self.maj_compteur()
self.logMessage("⌕ Check url : " + str(url), True)
else :
self.logMessage("⌛ Crawl url : " + str(url), True)
if url not in self.queueUrlsCrawled :
self.queueUrlsCrawled.put(url)
headers = { 'User-Agent' : self.user_agent, 'referer': url }
data = urllib.parse.urlencode({})
req = urllib.request.Request(url, data=None, headers=headers)
html_page = urllib.request.urlopen(req).read()
return html_page
except urllib.error.URLError as e:
print(e)
# il y a eu une erreur
if hasattr(e, 'code'):
#if e.code :
if check :
codeerreur = str(e.code)
self.logMessage("down url erreur : " + codeerreur)
whois_info = "Whois : ?"
if self.varErreurAll.get() == 1 :
traitement = True
if (codeerreur == "403" and self.varErreur403.get() == 1) :
#self.logMessage("403 passe")
traitement = True
if (codeerreur == "404" and self.varErreur404.get() == 1) :
#self.logMessage("404 passe")
traitement = True
regardeWhois = True
if (codeerreur == "500" and self.varErreur500.get() == 1) :
#self.logMessage("500 passe")
traitement = True
if url in self.toutesUrlFinded :
traitement = False
else :
# il n'y a pas de code mais un probleme quand même
if hasattr(e, 'reason'):
print(str(e.reason))
regardeWhois = True
traitement = True
if self.varErreurExpired.get() == 1 :
codeerreur = "Address not reachable"
except urllib.error.URLError as e:
#print(e.reason)
self.logMessage(" **** Erreur request **** : " + str(e.reason))
except socket.timeout:
self.logMessage(" **** Erreur request **** : socket.timeout")
except socket.gaierror:
self.logMessage(" **** Erreur request **** : socket.gaierror")
regardeWhois = True
except SocketError as e:
self.logMessage(" **** Erreur socket **** : " + str(e.errno))
except Exception:
self.logMessage(" **** Erreur - une autre exception bizarre...")
resultat_whois = True
if regardeWhois == True :
# check whois pour être certain de son coup
# retourne un texte ainsi qu'une valeur False si le whois a échoué
whois_info, resultat_whois = self.checkWhois(url)
# on chope le résultat de Moz PA et DA
keys = {
"access_id": self.moz_access_id,
"secret_key": self.moz_secret_id
}
mozda = "?"
mozpa = "?"
mozlinks = "?"
retour = ""
if (self.moz_access_id != "" and self.moz_secret_id != "" and traitement) :
try:
p = Pyscape(**keys)
resultat = p.get_url_metrics(url).json()
mozda = str(round(resultat["pda"], 0))
mozpa = str(round(resultat["upa"], 0))
mozlinks = str(resultat["uid"])
#self.logMessage(resultat)
del keys
del resultat
except Exception :
self.logMessage("Problem reading Moz Rank (have you correctly configured config.cfg ?)")
# si on a demandé l'analyse d'erreurs
# ou si on est sur un check du domaine expiré et disponible uniquement
affiche_dans_liste = False
if traitement :
# on ne cherche vraiment que les expirés
if self.varErreurExpired.get() == 1 :
# on affiche uniquement si le whois n'a rien donné et pas seulement s'il y a une erreur
if resultat_whois == False :
affiche_dans_liste = True
else :
affiche_dans_liste = True
# si on affiche bien l'url trouvé dans la liste
if affiche_dans_liste == True :
if url not in self.toutesUrlFinded :
self.toutesUrlFinded.append(url)
temp = url + " | Error : " + codeerreur + " | DA : " + mozda + " | PA : " + mozpa + " | Links : " + mozlinks + " | " + whois_info
self.tree.insert("",0, text=str(temp))
with codecs.open(self.nomfichier,'a','utf-8') as file_:
file_.write(temp + "\n")
# cela n'a pas fonctionné on retourne False
return False
def setUp(self):
self.valid_instance = Pyscape(**VALID_KEYS)
self.bad_instance = Pyscape(**BAD_KEYS)
