def fetch_data(
self
): #TODO: MUST be splitted into several methods, it is too huge and ugly!
"""Queries Entrez EUtils to retrieve information on a reference."""
if self.pmid:
try:
handle = Entrez.esummary(db="pubmed", id=self.pmid)
r = Entrez.read(handle)
# print r
r = r[0] # reference.
self.title = unicode(r['Title'])
self.volume = r.get('Volume', None) or None
self.issue = r.get('Issue', None) or None
self.pages = r['Pages']
self.authors = unicode('; '.join(r['AuthorList']))
self.journal = r['FullJournalName']
self.alternate_journal = r['Source']
self.year = int(r['PubDate'].split(' ')[0])
self.language = r['LangList'][0]
self.doi = r.get('DOI', None)
handle = Entrez.efetch(db="pubmed",
id=self.pmid,
rettype="medline",
retmode="text")
records = Medline.parse(handle)
for record in records:
pass
self.abstract = record.get('AB', None)
s = record['EDAT']
#print "; ".join(record.get('MH', ''))
self.keywords = "; ".join(record.get('MH',
'')) or None # MeSH terms
except Exception as e:
print "Failed fetching information"
print e, self
if not self.title:
from denigma.library import Bibliography
bib = Bibliography()
r = bib.efetch(id=self.pmid)
#print("datasets.Reference.fetch_data")
self.__dict__.update(r.__dict__)
# Transforming lists into strings:
self.keywords = "; ".join(self.keywords)
self.authors = "; ".join(self.authors)
self.date = normalize_time(s)
def fetch_data(self):
"""Queries Entrez EUtils to retrieve information on a reference."""
if self.pmid:
try:
handle = Entrez.esummary(db="pubmed", id=self.pmid)
r = Entrez.read(handle)
# print r
r = r[0] # reference.
self.title = unicode(r['Title'])
self.volume = r.get('Volume', None) or None
self.issue = r.get('Issue', None) or None
self.pages = r['Pages']
self.authors = unicode('; '.join(r['AuthorList']))
self.journal = r['FullJournalName']
self.alternate_journal = r['Source']
self.year = int(r['PubDate'].split(' ')[0])
self.language = r['LangList'][0]
self.doi = r.get('DOI', None)
handle = Entrez.efetch(db="pubmed", id=self.pmid, rettype="medline", retmode="text")
records = Medline.parse(handle)
for record in records: pass
self.abstract = record.get('AB', None)
s = record['EDAT']
#print "; ".join(record.get('MH', ''))
self.keywords = "; ".join(record.get('MH', '')) or None # MeSH terms
except Exception as e:
print "Failed fetching information"
print e, self
if not self.title:
from denigma.library import Bibliography
bib = Bibliography()
r = bib.efetch(id=self.pmid)
#print("datasets.Reference.fetch_data")
self.__dict__.update(r.__dict__)
# Transforming lists into strings:
self.keywords = "; ".join(self.keywords)
self.authors = "; ".join(self.authors)
self.date = normalize_time(s)
def save(self, update=False, *args, **kwargs):
print('Saving')
if not self.pk or update:
# This code only happens if the objects is not in the database yet.
# Otherwise it would have pk.
try:
#Reference._for_write = True
if self.pmid or 'pmid' in kwargs:
print "Did not failed"
return Reference.objects.get(pmid=self.pmid) #, False
elif self.title or 'title' in kwargs:
#print self.title
handle = Entrez.esearch(db='pubmed', term=self.title)
print "Got handle"
record = Entrez.read(handle)
print "Got record", record
print record['Count'], type(record['Count'])
if record['Count'] == "1":
print "Record count is 1"
self.pmid = record['IdList'][0]
#print self.title, self.pmid
Reference.fetch_data(self)
print("Saving")
super(Reference, self).save(*args, **kwargs)
print("Saved")
else:
from denigma.library import Bibliography # This statement at the top breaks Denigma for unknown reason.
#print("Trying it different. %s" % type(self.title))
# Google:
bib = Bibliography()
#print("googling")
r = bib.google(self.title)
if r:
r = r[0]
self.pmid = r.pmid
#print("Google successufull: %s" % self.pmid)
else:
#print("Google failed.")
# r = bib.find(self.title)[0]
# self.pmid = r.pmid
# print self.pmid
#print("Trying it different.")
r = bib.find(unicode(self.title))
if len(r) == 1:
r = r[0]
self.pmid = r.pmid
print self.pmid
elif len(r) > 1:
title = normalize_title(self.title)
for areference in r:
if normalize_title(areference.title) == title:
r = areference
print("datasets.Reference.save()")
self.__dict__.update(r.__dict__)
print r
print vars(r)
self.date = normalize_time(r.date)
print "# Transforming lists into strings:"
self.keywords = "; ".join(self.keywords)
self.authors = "; ".join(self.authors)
print "calling super"
print self.pmid
try: super(Reference, self).save(*args, **kwargs) # Just save the given information.
except Exception as e:
print e
print "called super"
# Raise Exception and state the the given information yielded more than one reference.
else:
super(Reference, self).save(*args, **kwargs)
except Reference.DoesNotExist as e:
print "Error", e
Reference.fetch_data(self)
super(Reference, self).save(*args, **kwargs)
else:
super(Reference, self).save(*args, **kwargs)
def save(self, update=False, *args, **kwargs):
if not self.pk or update:
# This code only happens if the objects is not in the database yet.
# Otherwise it would have pk.
try:
#Reference._for_write = True
if self.pmid or 'pmid' in kwargs:
print "Did not failed"
return Reference.objects.get(pmid=self.pmid) #, False
elif self.title or 'title' in kwargs:
#print self.title
handle = Entrez.esearch(db='pubmed', term=self.title)
print "Got handle"
record = Entrez.read(handle)
print "Got record", record
print record['Count'], type(record['Count'])
if record['Count'] == "1":
print "Record count is 1"
self.pmid = record['IdList'][0]
#print self.title, self.pmid
Reference.fetch_data(self)
print("Saving")
super(Reference, self).save(*args, **kwargs)
print("Saved")
else:
from denigma.library import Bibliography # This statement at the top breaks Denigma for unknown reason.
#print("Trying it different. %s" % type(self.title))
# Google:
bib = Bibliography()
#print("googling")
r = bib.google(self.title)
if r:
r = r[0]
self.pmid = r.pmid
#print("Google successufull: %s" % self.pmid)
else:
#print("Google failed.")
# r = bib.find(self.title)[0]
# self.pmid = r.pmid
# print self.pmid
#print("Trying it different.")
r = bib.find(unicode(self.title))
if len(r) == 1:
r = r[0]
self.pmid = r.pmid
print self.pmid
elif len(r) > 1:
title = normalize_title(self.title)
for areference in r:
if normalize_title(
areference.title) == title:
r = areference
print("datasets.Reference.save()")
self.__dict__.update(r.__dict__)
print r
print vars(r)
self.date = normalize_time(r.date)
print "# Transforming lists into strings:"
self.keywords = "; ".join(self.keywords)
self.authors = "; ".join(self.authors)
print "calling super"
print self.pmid
try:
super(Reference, self).save(
*args,
**kwargs) # Just save the given information.
except Exception as e:
print e
print "called super"
# Raise Exception and state the the given information yielded more than one reference.
else:
super(Reference, self).save(*args, **kwargs)
except Reference.DoesNotExist as e:
print "Error", e
Reference.fetch_data(self)
super(Reference, self).save(*args, **kwargs)
else:
super(Reference, self).save(*args, **kwargs)
