def get_tieba_page(page):
req = urllib2.Request(page)
web = urllib2.urlopen(req)
praser = urllister.URLLister()
praser.feed(web.read())
web.close()
praser.close()
return praser
def getURL(self, url): #getURL(url)用来将HTML中的url放入urls列表中
try:
try:
usock = urllib.urlopen(url)
except:
print 'get url excepton'
return []
parser = urllister.URLLister()
parser.feed(usock.read())
usock.close()
parser.close()
urls = parser.urls
return urls
except Exception, e:
print u"getURL", e
return 0
#!/usr/bin/python2
# -*-coding:Utf-8 -*
import urllib, urllister
usock = urllib.urlopen(
"http://www.lefigaro.fr/sante/2011/06/15/01004-20110615ARTFIG00354-vers-une-vache-capable-de-produire-du-lait-maternel.php"
)
parser = urllister.URLLister()
parser.feed(usock.read())
usock.close()
parser.close()
for url in parser.urls:
print url
print parser.tags
# vim:set shiftwidth=4 tabstop=4 expandtab textwidth=79:
def prezzoLib(s):
one=False
ris=-1
good=False
max=999.99
x=s.replace(' ','+')
x=x.encode("utf-8")
url="http://www.libreriauniversitaria.it/ricerca/query/"+x
try:sock= urllib.urlopen(url)
except IOError:
return -1
parser = urllister.URLLister()
z=s.split(' ')
l=len(z)
for pz in range(l-1):
if len(z[pz])<2:
z.pop(pz)
pz=pz-1
l=len(z)
parser.feed(sock.read())
if(l==0):
return -1
if l==1:
eee=0
for i in parser.urls:
if(z[0] in i and "query" not in i and "libri"not in i):
eee=eee+1
ris =cercaprezzo(i)
Tp=cercaTitolo(i)
if(float(ris)<max and ris!=-1):
session['TitoloLIB']=Tp
max=float(ris)
if(eee == 4):
break
ris=-1
return max
z.sort(key=len)
second=False
PX=0
count=0
ki=0
kount=0
for i in parser.urls:
kount+=1
if l==2:
if(z[0] in i and z[1] in i and "query" not in i and "libri" not in i):
ris=cercaprezzo(i)
PX=PX+1
else:
for j in range(l-1,0,-1):
if(z[j] in i and "query" not in i and "libri" not in i):
count=count+1
if(count==l-2):
ris=cercaprezzo(i)
PX=PX+1
ki=PX
count=0
break
count=0
jk=float(ris)
ris=-1
if (PX>=ki-1 and jk<max and jk!=0.0 and jk!=-1):
newT=cercaTitolo(i)
newt=newT.lower()
print(newT)
potto=0
for y in range(len(z)):
if(z[y].lower() in newt):
potto+=1
if potto==len(z):
good=True
potto=0
Aut=cercaAutore(i)
if(one==False):
if good :
max=jk
session['TitoloLIB']=newT
good=False
one=True
AF=Aut
if PX==10 or kount==150:
break
continue
elif one==True and second==False and Aut==AF:
if good :
max=jk
session['TitoloLIB']=newT
good=False
second=True
if PX==10 or kount==150:
break
continue
else:
if good and (newt==s or ("ediz. integrale" in newt and s in newt)or ("edizione" in newt and s in newt)) and Aut==AF:
max=jk
session['TitoloLIB']=newT
good=False
if PX==10 or kount==150:
break
sock.close()
parser.close()
return max
def getDataFromRefDB2PubDBs(br_filename):
"""
look for published data in RefDB+PubDBs
and write a file with block:location
"""
## get the content of the RefDB2PubDBs map page
PubDBCentralUrl_ = 'http://cmsdoc.cern.ch/cms/production/www/PubDB/'
RefDBPubDBsmapPhp_ = 'GetPublishedCollectionInfoFromRefDB.php'
primaryUrl = PubDBCentralUrl_ + RefDBPubDBsmapPhp_
logging.debug("MapListUrl=" + primaryUrl)
try:
sock = urllib.urlopen(primaryUrl)
except IOError:
raise RefDBError(primaryUrl)
parser = urllister.URLLister()
parser.feed(sock.read())
sock.close()
parser.close()
## HREF dataset-discovery.php (for a dataset/owner)
## HREF PubDBURL for collecitons.php
## HREF mantainer
## parsing the RefDB2PubDBs map to find the published dataset/owner and their PubDB URL
List_blockreplica = []
br_file = open(br_filename, 'w')
## regexp to get the dataset/owner
reDsOw = re.compile(r'DSPattern=(\w+)&OwPattern=(\w+)')
reDsOw2 = re.compile(r'DSPattern=(\w+\-\w+)&OwPattern=(\w+)')
reDsOw3 = re.compile(r'DSPattern=(\w+\.\w+\.\w+)&OwPattern=(\w+)')
## mu04_mu_pt10._eta0.0
recollid = re.compile(r'collid=(\d+)')
count = 0
for url in parser.linksList:
count = count + 1
if string.find(url, 'dataset-discovery.php') != -1:
#`print "trying with url "+url
try:
dsow = reDsOw.search(string.strip(url))
ds = dsow.group(1)
ow = dsow.group(2)
except:
try:
dsow = reDsOw2.search(string.strip(url))
ds = dsow.group(1)
ow = dsow.group(2)
pass
except:
dsow = reDsOw3.search(string.strip(url))
ds = dsow.group(1)
ow = dsow.group(2)
pass
## PubDB URL is the next URL
puburl = parser.linksList[count]
#print "Dataset/Owner is "+ds+"/"+ow+" PubDB URL is "+puburl
logging.debug("Dataset/Owner is " + ds + "/" + ow +
" PubDB URL is " + puburl)
end = string.rfind(puburl, '/')
collid = recollid.search(string.strip(puburl)).group(1)
## get location from PubDB
if (checkPubDBversion(puburl[:end + 1])):
## for PubDB V4
locationList = getPubDBInfo(puburl[:end + 1], collid)
else:
## for PubDB V3
collid = recollid.search(string.strip(puburl)).group(1)
#print ' collid '+collid+' Do nothing for PubDB V3....'
PubDBError(puburl, ' still PubDB V3')
locationList = ['Null']
## save block-replica to a file
block = ow + '/' + ds
for location in locationList:
blockreplica = block + ':' + location
List_blockreplica.append(blockreplica)
br_file.write(blockreplica + '\n')
br_file.close()
