def _get_xml(url, payload, **kwargs):
tries = 0
while tries < 5:
try:
out = utils.requests_pem_get(url, params=payload)
out.raise_for_status()
tt = xml_utils.string_to_node(out.content)
return tt
except:
tries += 1
out = utils.requests_pem_get(url, params=payload)
out.raise_for_status()
tt = xml_utils.string_to_node(out.content)
return tt
def get_doi_citation_datacite(doi):
"""
Parameters
----------
doi : str
DOI in the format "https://doi.org/10.1109/5.771073"
or "doi:10.5066/F70R9MFW"
or "http://dx.doi.org/10.1109/5.771073"
Returns
-------
dict with information pulled from datacite site
"""
endpoint = 'https://api.datacite.org/works'
response = utils.requests_pem_get(endpoint + '/' + doi)
cite_data = json.loads(response.text)['data']['attributes']
if 'container-title' not in cite_data:
cite_data['container-title'] = cite_data.pop('container_title')
if 'data-center-id' not in cite_data:
cite_data['data-center-id'] = cite_data.pop('data_center_id')
cite_data['publisher'] = cite_data['container-title']
cite_data['URL'] = 'https://doi.org/{}'.format(cite_data['doi'])
if 'data-center-id' in cite_data and \
'usgs' in cite_data['data-center-id']:
cite_data['container-title'] = None
cite_data['pubplace'] = 'https://www.sciencebase.gov'
cite_data['geoform'] = 'dataset'
else:
cite_data['geoform'] = 'publication'
cite_data['pubplace'] = 'n/a'
return cite_data
def load_iso(self):
self.ui.label_search_term.hide()
self.ui.search_term.hide()
self.ui.button_search.hide()
self.ui.label_search_results.text = "ISO 19115 Topic Categories"
self.populate_thesauri_lookup()
iso_url = "https://www2.usgs.gov/science/term.php?thcode=15&text=ISO 19115 Topic Category"
results = utils.requests_pem_get(iso_url).json()
thesaurus_name = "ISO 19115 Topic Category"
branch = QStandardItem(thesaurus_name)
branch.setFont(QFont('Arial', 11))
for item in results['nt']:
childnode = QStandardItem(item['name'])
childnode.setFont(QFont('Arial', 9))
branch.appendRow([childnode])
model = QStandardItemModel(0, 0)
rootNode = model.invisibleRootItem()
rootNode.appendRow(branch)
self.ui.treeview_results.setModel(model)
self.ui.treeview_results.expandAll()
def get_doi_citation_datacite(doi):
"""
Parameters
----------
doi : str
DOI in the format "https://doi.org/10.1109/5.771073"
or "doi:10.5066/F70R9MFW"
or "http://dx.doi.org/10.1109/5.771073"
Returns
-------
dict with information pulled from datacite site
"""
endpoint = "https://api.datacite.org/works"
response = utils.requests_pem_get(endpoint + "/" + doi)
cite_data = json.loads(response.text)["data"]["attributes"]
if "container-title" not in cite_data:
cite_data["container-title"] = cite_data.pop("container_title")
if "data-center-id" not in cite_data:
cite_data["data-center-id"] = cite_data.pop("data_center_id")
cite_data["publisher"] = cite_data["container-title"]
cite_data["URL"] = "https://doi.org/{}".format(cite_data["doi"])
if "data-center-id" in cite_data and "usgs" in cite_data["data-center-id"]:
cite_data["container-title"] = None
cite_data["pubplace"] = "https://www.sciencebase.gov"
cite_data["geoform"] = "dataset"
else:
cite_data["geoform"] = "publication"
cite_data["pubplace"] = "n/a"
return cite_data
def get_result(self, url):
try:
return utils.requests_pem_get(url).json()
except requests.exceptions.ConnectionError:
msg = "We're having trouble connecting to the controlled vocabularies service"
msg += "\n Check that you have an internet connect, or try again latter"
QMessageBox.warning(self, "Connection error", msg)
self.close_form()
def __init__(self, contents):
"""
contents must be one of the following
1) File path/name on the local filesystem that exists and can be read
2) String containing an XML Record.
3) URL containing an XML record
Parameters
----------
contents : str, lxml node
url, file path, string xml snippet
"""
try:
contents_path = Path(contents)
try:
exists = contents_path.exists()
except OSError:
exists = False
if exists:
self.fname = str(contents_path.absolute())
# they passde us a file path
self.record = lxml.parse(self.fname)
self._root = self.record.getroot()
else:
from pymdwizard.core import utils
try:
if utils.url_validator(contents):
contents = utils.requests_pem_get(contents).text
except:
pass
self.fname = None
if contents[:3] == "":
# string contents start with the BOM strip this
contents = contents[3:]
if type(contents) == str:
# we need bytes not string
contents = contents.encode("utf-8")
self._root = string_to_node(contents)
self.record = etree.ElementTree(self._root)
except etree.XMLSyntaxError:
self.fname = None
self.record = lxml.fromstring(contents)
self._root = self.record.getroot()
self.tag = self._root.tag
self.__dict__[self._root.tag] = XMLNode(self.record.getroot())
self._contents = self.__dict__[self._root.tag]
def __init__(self, contents):
try:
if os.path.exists(contents[:255]):
self.fname = contents
# they passed us a file path
self.record = lxml.parse(self.fname)
self._root = self.record.getroot()
else:
from pymdwizard.core import utils
if utils.url_validator(contents):
print('is url')
contents = utils.requests_pem_get(contents).text
self.fname = None
self._root = string_to_node(contents)
self.record = etree.ElementTree(self._root)
except etree.XMLSyntaxError:
self.fname = None
self.record = lxml.fromstring(contents)
self._root = self.record.getroot()
self.tag = self._root.tag
self.__dict__[self._root.tag] = XMLNode(self.record.getroot())
self._contents = self.__dict__[self._root.tag]
def show_details(self, index):
clicked_item = self.ui.treeview_results.model().itemFromIndex(index)
parent = clicked_item.parent()
if clicked_item.hasChildren():
thcode = self.thesauri_lookup_r[clicked_item.text()]
thname = clicked_item.text()
THESAURUS_DETAILS_URL = "https://www2.usgs.gov/science/thesaurus.php?format=json&thcode={}"
thesaurus_details_url = THESAURUS_DETAILS_URL.format(thcode)
details = utils.requests_pem_get(thesaurus_details_url).json()
details_msg = ''
details_msg += '<b><font size="5" face="arial">{}</font></b><br>'.format(
thname)
uri = details['vocabulary']['uri']
if uri:
details_msg += '<a href="{}"><u><i><font size="4" face="arial" style="color:#386EC4">{}</font></i></u></a><br><br>'.format(
uri, uri)
details_msg += details['vocabulary']['scope']
else:
thcode = self.thesauri_lookup_r[parent.text()]
item_text = clicked_item.text().split(' (use: ')[0]
details_url = "https://www2.usgs.gov/science/term.php?thcode={}&text={}".format(
thcode, quote(item_text))
try:
details = utils.requests_pem_get(details_url).json()
if type(details) == dict:
details = [details]
details_msg = ''
search_term = self.ui.search_term.text()
prefered_shown = False
for detail in details:
term = detail["term"]
uf = detail["uf"]
bt = detail["bt"]
nt = detail["nt"]
rt = detail["rt"]
if term['name'].lower() != search_term and \
not prefered_shown:
term_count = 0
prefered_shown = True
for alt_term in uf:
if alt_term['name'].lower() in search_term.lower():
term_count += 1
if term_count == 1:
details_msg += "The query matches the following non-preferred terms: "
else:
details_msg += ', '
details_msg += "<u>{}</u>".format(
alt_term['name'])
if term_count > 0:
details_msg += '<br><br>'
details_msg += '<b><font size="5" face="arial">{}</font></b><br>'.format(
term['name'])
details_msg += '<font size="4" face="arial">{}<br><br>'.format(
term['scope'])
if bt:
details_msg += "Broader terms: "
details_msg += " > ".join([
'<a href="{0}"><u>{0}</u></a>'.format(item['name'])
for item in bt[::-1]
])
details_msg += '<br>'
if nt:
details_msg += " Narrower terms: "
details_msg += ", ".join([
'<a href="{0}"><u>{0}</u></a>'.format(item['name'])
for item in nt
])
details_msg += '<br>'
if rt:
details_msg += " Related terms: "
details_msg += ", ".join([
'<a href="{0}"><u>{0}</u></a>'.format(item['name'])
for item in rt
])
details_msg += '<br>'
except:
details_msg = 'error getting details'
self.ui.textBrowser.setText(details_msg)
def _get_xml(url, payload, **kwargs):
out = utils.requests_pem_get(url, params=payload)
out.raise_for_status()
tt = xml_utils.string_to_node(out.content)
return tt