def validate_xml(coll, article_id, issue_id, api_host='localhost', api_port='7000'):
"""
Validate article agains WOS Schema. Flaging his attribute validated_scielo to True if
the document is valid.
"""
xsd = open('ThomsonReuters_publishing.xsd', 'r').read()
sch = Schema(xsd)
xml_url = 'http://{0}:{1}/api/v1/article?code={2}&format=xml&show_citation=True'.format(api_host, api_port, article_id)
xml = urllib2.urlopen(xml_url, timeout=30).read()
try:
result = sch.validate(xml)
except etree.XMLSyntaxError as e:
msg = "{0}: Problems reading de XML, {1}".format(article_id, e.text)
write_log(article_id,
issue_id,
sch,
xml,
msg)
return None
if result:
coll.update({'code': article_id}, {'$set': {'validated_scielo': 'True'}})
return xml
else:
msg = ""
for error in sch.get_validation_errors(xml):
msg += "{0}: {1}\r\n".format(article_id, error[2])
write_log(article_id,
issue_id,
sch,
xml,
msg)
return None
def __init__(self,
crossref_api_url=API_URL,
query_email=QUERY_EMAIL,
user=USER,
passwd=PASSWD,
xsd='../xsd/crossref_query_input2.0.xsd'):
"""
Create a Brocker instance.
xsd default for queries
"""
xsd = open(xsd).read()
self.porteira = Schema(xsd)
self.crossref_api_url = crossref_api_url
self.user = user
self.passwd = passwd
self.query_email = query_email
class Brocker(object):
def __init__(self,
crossref_api_url=API_URL,
query_email=QUERY_EMAIL,
user=USER,
passwd=PASSWD,
xsd='../xsd/crossref_query_input2.0.xsd'):
"""
Create a Brocker instance.
xsd default for queries
"""
xsd = open(xsd).read()
self.porteira = Schema(xsd)
self.crossref_api_url = crossref_api_url
self.user = user
self.passwd = passwd
self.query_email = query_email
def query_doi(self, xml):
"""
Returns a DOI number according to metadata contained into a given valid XML.
The XML must be compatible with crossref_query_input2.0.xsd
This method will return 'False' or a 'DOI number'.
"""
if self.porteira.validate(xml):
request_url = "{0}query/?format=xsd_xml&pid={1}&qdata={2}".format(
self.crossref_api_url,
self.query_email,
urllib2.quote(xml))
query_result = urllib2.urlopen(request_url).read()
dec = BeautifulSoup(query_result)
try:
return dec.query_result.doi.string
except AttributeError:
return None
else:
return None
def is_resolved(self, doi):
"""
Returns True or False for a given DOI number
"""
request_url = "{0}query/?format=xsd_xml&pid={1}&id={2}".format(
self.crossref_api_url,
self.query_email,
doi)
query_result = urllib2.urlopen(request_url).read()
dec = BeautifulSoup(query_result)
if dec.query_result.query['status'] == 'resolved':
return True
else:
return False
def request(self, xml):
"""
Returns True if the request was well done and False if their was an error
while sending the request to Crossref
"""
if self.porteira.validate(xml):
xml_file = StringIO()
xml_file.write(xml)
form = MultiPartForm()
url = "{0}deposit".format(self.crossref_api_url)
form.add_field('operation', 'doMDUpload')
form.add_field('login_id', self.user)
form.add_field('login_passwd', self.passwd)
form.add_file('fname', 'crossref_query.xml', fileHandle=xml_file)
body = str(form)
request = urllib2.Request(url)
request.add_header('Content-type', form.get_content_type())
request.add_header('Content-length', len(body))
request.add_data(body)
response = urllib2.urlopen(request).read()
return True
else:
return None
def xml_is_valid(xml):
sch = Schema(str_schema)
return sch.validate(xml)