def trx_abstracts(m):
TRX = MaltegoTransform()
doi = m.getProperty("DOI")
if not doi:
TRX.addUIMessage(
'A DOI is needed to perform this search. Please run "Search on Crossref" and, if a DOI is found, try again here'
)
return TRX.returnOutput()
client_id = Tokens.MendeleyID
client_secret = Tokens.MendeleySecret
mendeley = Mendeley(client_id, client_secret=client_secret)
auth = mendeley.start_client_credentials_flow()
session = auth.authenticate()
try:
abstract = session.catalog.by_identifier(doi=doi).abstract
except:
TRX.addUIMessage("Cannot find document on Mendeley")
else:
new = TRX.addEntity("me.Article", title)
new.addProperty("abstract", "Abstract", 'loose',
abstract.encode('utf-8'))
TRX.addUIMessage(abstract)
logging(TRX.returnOutput(), m.Maltegoxml)
return TRX.returnOutput()
def trx_searchauthor(m):
TRX = MaltegoTransform()
authore = m.getProperty("person.fullname")
client_id = Tokens.MendeleyID
client_secret = Tokens.MendeleySecret
mendeley = Mendeley(client_id, client_secret=client_secret)
auth = mendeley.start_client_credentials_flow()
session = auth.authenticate()
page = session.catalog.advanced_search(author=authore).list()
if len(page.items) < 12:
limit = len(page.items)
else:
limit = m.Slider
# print m.Slider
# print limit
for n in range(limit):
doc = page.items[n]
titlee = clean_obsession(doc.title)
new = TRX.addEntity("me.Article", titlee)
new.setWeight(100 - n)
try:
new.addProperty("abstract", "Abstract", 'strict',
clean_obsession(doc.abstract).encode('utf-8'))
new.addProperty("year", "Year", 'strict', str(doc.year))
new.addProperty("DOI", "DOI", 'strict', doc.identifiers['doi'])
authori = [
doc.authors[n].first_name.encode('utf-8') + ' ' +
doc.authors[n].last_name.encode('utf-8')
for n in range(len(doc.authors))
]
new.addProperty("author", "Author", 'strict',
clean_obsession('; '.join(authori)))
if doc.keywords:
doc_keywords = [
doc.keywords[n].encode('utf-8')
for n in range(len(doc.keywords))
]
new.addProperty("keywords", "Keywords", 'strict',
clean_obsession('; '.join(doc_keywords)))
except:
# pass
# print 'o dear'
TRX.addUIMessage('Article: ' + titlee +
'. Not all fields could be downloaded')
# print titlee
# print TRX.returnOutput()
# print 'santa madonna'
logging(TRX.returnOutput(), m.Maltegoxml)
return TRX.returnOutput()
def trx_searchciters(m):
TRX = MaltegoTransform()
title = m.getProperty("title.article")
title = unidecode(title)
# print title
DOI = m.getProperty("DOI")
if DOI:
query = DOI
else:
query = title
search_query = scholarly.search_pubs_query(query)
try:
result = next(search_query)
except StopIteration:
TRX.addUIMessage("""The DOI could not be found on Google Scholar,
which very likely means Google Scholar has never heard of this article before"""
)
return TRX.returnOutput()
titlemaybe = result.bib['title']
TRX.addUIMessage(
"""Title found: %s.
If this is not what you were looking for, add the article's DOI and search again"""
% make_unicode(clean_obsession(titlemaybe)), UIM_INFORM)
limit = m.slider
count = 0
for citation in result.get_citedby():
if count == limit:
break
for i in bastardi:
title = citation.bib['title'].replace(i, '')
new = TRX.addEntity("me.Article", title.encode('utf-8'))
# new.setLinkLabel('Cited by')
# new.setLinkColor('blue')
# new.setLinkThickness(2)
authors = '; '.join(
[authore for authore in citation.bib['author'].split(' and ')])
for i in bastardi:
authors = authors.replace(i, '')
new.addProperty("author", "Author", "loose", authors.encode('utf-8'))
count += 1
logging(TRX.returnOutput(), m.Maltegoxml)
return TRX.returnOutput()
def trx_searchtitle(m):
TRX = MaltegoTransform()
#me.parseArguments(sys.argv)
title = m.getProperty("title.article")
url = 'http://api.crossref.org/works?query='
r = requests.get(url + title + '&rows=1')
titler = r.json()['message']['items'][0]['title'][0]
doi = r.json()['message']['items'][0]['DOI']
URL = r.json()['message']['items'][0]['URL']
try:
year = str(r.json()['message']['items'][0]['published-print'])
except:
try:
year = str(r.json()['message']['items'][0]['published-online']
['date-parts'])
except:
year = str(
r.json()['message']['items'][0]['created']['date-parts'])
year = year.translate(None, "{}abcdefghijklmnopqrstuvz':[]-,")
try:
u = r.json()['message']['items'][0]['author']
authori = []
for i in u:
authore = i['family'].encode('utf-8') + ' ' + i['given'].encode(
'utf-8') + '; '
authori.append(authore)
except:
authori = []
authori.append(r.json()['message']['items'][0]['publisher'])
new = TRX.addEntity("me.Article", title)
new.addProperty("DOI", "DOI", 'strict', str(doi))
new.addDisplayInformation(
'<a href="%s"> click here to go to the webpage </a>' % URL, 'DOI URL')
new.addProperty("url", "url", 'strict', str(URL))
new.addProperty("year", "Year", 'strict', str(year))
new.addProperty("author", "Author", 'loose', ''.join(authori))
new.setValue(
titler.encode('utf-8')) #what the hell is this???????????????????
logging(TRX.returnOutput(), m.Maltegoxml)
return TRX.returnOutput()
def trx_basesearch(m):
limit = m.slider
url = "https://api.base-search.net/cgi-bin/BaseHttpSearchInterface.fcgi?func=PerformSearch&format=json&query=dccreator:"
TRX = MaltegoTransform()
author = m.getProperty("person.fullname").strip()
r = requests.get(url + '"' + author + '"' + "&hits=" + str(limit))
# import pprint
# pprint.pprint(r.json())
for doc in r.json()['response']['docs']:
try:
new = TRX.addEntity("me.Article", doc['dctitle'])
except:
# print('No title')
continue
try:
new.addProperty("year", "Year", 'strict', str(doc['dcyear']))
except:
pass
link = doc['dclink']
new.addDisplayInformation('<a href="' + link + '"> ' + link + ' </a>',
'Link to file')
try:
author = doc['dccreator']
except:
# print 'no author'
pass
else:
if type(author) is list:
authors = '; '.join(o for o in author)
new.addProperty("author", "Author", "strict", authors)
# print 'author is list'
elif type(author) is unicode:
new.addProperty("author", "Author", "strict", author)
# print 'author is one'
try:
new.addProperty("abstract", "Abstract", "strict",
doc['dcdescription'])
except:
pass
logging(TRX.returnOutput(), m.Maltegoxml)
return TRX.returnOutput()
def trx_extractauthors(m):
# data=open('/home/ubuntu/1.pdf','rb').read()
TRX = MaltegoTransform()
try:
authorss = m.getProperty("author")
except:
TRX.addUIMessage('Sorry, it appears the article has no Author')
return TRX.returnOutput()
authors = authorss.split("; ")
for i in authors:
if i is not '':
new=TRX.addEntity("maltego.Person",i)
# new.addProperty('binary','Binary','strict',data)
new.addDisplayInformation('<a href="C:\\Users\\carla\\Documents\\aa.pdf"> rrr </a>','rrr')
# logging(TRX.returnOutput(),m.testo)
logging(TRX.returnOutput(),m.Maltegoxml)
return TRX.returnOutput()
def trx_cermine(m):
TRX = MaltegoTransform()
path = str(m.getProperty('article.path'))
print path
data = open(path.replace('"', ''), 'rb').read()
url = 'http://cermine.ceon.pl/extract.do'
headers = {'Content-Type': 'application/binary'}
r = requests.post(url, data=data, headers=headers)
if r.status_code == 200 and 'application/xml' in r.headers['content-type']:
testo = r.content.decode('ISO-8859-2').encode('utf8')
root = ET.fromstring(testo)
articles = []
for title in root.iter('article-title'):
articles.append([title.text])
else:
TRX.addUIMessage(
'Something went wrong, Cermine could not process your file')
return TRX.returnOutput()
for art in articles:
title = art[0]
new = TRX.addEntity('me.Article', title)
try:
author = art[1]
year = art[2]
new.addProperty('author', 'Author', 'loose', author)
new.addProperty('year', 'Year', 'strict', str(year))
except:
pass
logging(TRX.returnOutput(), m.Maltegoxml)
return TRX.returnOutput()
def trx_keywords(m):
TRX = MaltegoTransform()
try:
keywords=[x for x in (m.getProperty("keywords").split('; '))]
keywords=keywords[:12]
except AttributeError:
TRX.addUIMessage('Silly, there are no keywords for this article. But you could insert them yourself and then try again!')
return TRX.returnOutput()
limit=12
# limit=m.getTransformSetting('HowMany')
print limit
# if not limit.isdigit():
# TRX.addUIMessage('Silly! That has to be a number')
# return TRX.returnOutput()
if limit>40:
TRX.addUIMessage("Sorry, that's too many! Currently the limit is 12 with the free Maltego, otherwise 50")
return TRX.returnOutput()
elif limit>12:
TRX.addUIMessage("You set a value > than 12. If you are using the free Maltego, you are still going to get 12")
return TRX.returnOutput()
client_id=Tokens.MendeleyID
client_secret= Tokens.MendeleySecret
mendeley = Mendeley(client_id, client_secret=client_secret)
auth = mendeley.start_client_credentials_flow()
session = auth.authenticate()
try:
pages = [session.catalog.search(keyword).list() for keyword in keywords]
except UnicodeEncodeError:
TRX.addUIMessage("""Sorry, Mendeley doesn't accept keywords with non-latin characters.
Please change them yourself and try again""")
return TRX.returnOutput()
n_results_per_key = limit / len(pages)
if n_results_per_key == 0:
n_results_per_key == 1
keyplace=0
for page in pages:
if len(page.items) < n_results_per_key:
limit=len(page.items)
else:
limit=n_results_per_key
for n in range(limit):
doc=page.items[n]
new = TRX.addEntity("me.Article", doc.title.encode('utf-8'))
new.setWeight(100-n)
# new.setLinkColor('0x808000')
new.setLinkLabel(keywords[keyplace].encode('utf-8'))
try:
new.addProperty("abstract","Abstract", True, doc.abstract.encode('utf-8'))
new.addProperty("year","Year", False, str(doc.year))
authori=[doc.authors[n].first_name.encode('utf-8')+' '+doc.authors[n].last_name.encode('utf-8') for n in range(0,len(doc.authors))]
new.addProperty("author","Author", True, '; '.join(authori))
doc_keywords=[doc.keywords[n].encode('utf-8') for n in range(len(doc.keywords))]
new.addProperty("keywords","Keywords",True, '; '.join(doc_keywords))
new.addProperty("DOI","DOI",'strict', doc.identifiers['doi'])
except:
TRX.addUIMessage('Article: '+doc.title.encode('utf-8')+'. Not all fields could be downloaded, probably keywords..')
keyplace+=1
logging(TRX.returnOutput(),m.Maltegoxml)
return TRX.returnOutput()