def get_figure_listing(self, report_id, chapter_id=None):
chapter_filter = '/chapter/' + chapter_id if chapter_id else ''
url = '{b}/report/{rpt}{chap}/figure'.format(b=self.base_url,
rpt=report_id,
chap=chapter_filter)
resp = self.s.get(url, params={'all': '1'}, verify=False)
try:
return [Figure(figure) for figure in resp.json()]
except ValueError:
raise Exception(resp.text)
def get_figure(self, report_id, figure_id, chapter_id=None):
chapter_filter = '/chapter/' + chapter_id if chapter_id else ''
url = '{b}/report/{rpt}{chap}/figure/{fig}'.format(b=self.base_url,
rpt=report_id,
chap=chapter_filter,
fig=figure_id)
resp = self.s.get(url, params={'all': '1'}, verify=False)
try:
return Figure(resp.json())
except ValueError:
raise Exception(resp.text)
def get_webform(self, fig_url, download_images=False):
full_url = '{b}{url}?token={t}'.format(b=self.base_url,
url=fig_url,
t=self.token)
webform_json = requests.get(full_url).json()
#TODO: refactor the service so this isn't necessary
webform_nid = webform_json.keys()[0]
figure_json = webform_json[webform_nid]['figure'][0]
f = Figure(figure_json, trans=trans.FIG_TRANSLATIONS)
#Add contributor info
if 'list_the_creator_of_the_figure' in figure_json:
f.add_contributor(
parse_creators(figure_json['list_the_creator_of_the_figure']))
#Add provenance information (wasDerivedFrom parent)
if 'what_type_of_source_provided_this_figure' in figure_json and figure_json[
'what_type_of_source_provided_this_figure'] == 'published_source':
f.add_parent(
Parent(deepcopy(f.original),
trans=trans.PARENT_TRANSLATIONS,
pubtype_map=trans.PARENT_PUBTYPE_MAP,
search_hints=trans.PARENT_SEARCH_HINTS))
if 'images' in webform_json[webform_nid]:
for img_idx, image in enumerate(
webform_json[webform_nid]['images']):
image_obj = Image(
image,
local_path=self.get_local_image_path(image),
remote_path=self.get_remote_image_path(image),
trans=trans.IMG_TRANSLATIONS)
#Add contributor info
if 'list_the_creator_of_the_image' in image:
image_obj.add_contributor(
parse_creators(image['list_the_creator_of_the_image']))
#TODO: this just keeps getting worse
if 'datasources' in webform_json[webform_nid]['images'][
img_idx]:
for dataset_json in webform_json[webform_nid]['images'][
img_idx]['datasources']:
dataset = Dataset(dataset_json,
trans=trans.DATASET_TRANSLATIONS,
known_ids=trans.DATASET_IDS)
#Commence the hacks
try:
dataset.temporal_extent = ' '.join([
parse(dataset_json[field]).isoformat()
for field in ['start_time', 'end_time']
])
except TypeError, e:
print 'Problem with start/end time: ', fig_url, f.title, e
print dataset_json['start_time'], dataset_json[
'end_time']
dataset.temporal_extent = None
except ValueError, e:
print 'Problem with start/end time: ', fig_url, f.title, e
print dataset_json['start_time'], dataset_json[
'end_time']
dataset.temporal_extent = None
dataset.spatial_extent = ' '.join([
'{k}: {v};'.format(k=key, v=dataset_json[key])
for key in [
'maximum_latitude', 'minimum_latitude',
'maximum_longitude', 'minimum_longitude'
]
])
#Filter overlapping Dataset keys out
activity_json = {
k: dataset_json[k]
for k in dataset_json if k not in [
'href', 'uri', 'identifier', 'start_time',
'end_time'
]
}
#Add synthetic identifier
activity_json['identifier'] = '-'.join(
(image_obj.identifier.split('-')[0],
dataset.identifier, 'process'))
dataset.activity = Activity(
activity_json, trans=trans.ACT_TRANSLATIONS)
#TODO: Extract DOIs from citation
image_obj.datasets.append(dataset)
f.images.append(image_obj)
def get_webform(self, fig_url, download_images=False):
full_url = '{b}{url}?token={t}'.format(b=self.base_url, url=fig_url, t=self.token)
webform_json = requests.get(full_url).json()
#TODO: refactor the service so this isn't necessary
webform_nid = webform_json.keys()[0]
figure_json = webform_json[webform_nid]['figure'][0]
f = Figure(figure_json, trans=trans.FIG_TRANSLATIONS)
#Add contributor info
if 'list_the_creator_of_the_figure' in figure_json:
f.add_contributor(parse_creators(figure_json['list_the_creator_of_the_figure']))
#Add provenance information (wasDerivedFrom parent)
if 'what_type_of_source_provided_this_figure' in figure_json and figure_json[
'what_type_of_source_provided_this_figure'] == 'published_source':
f.add_parent(Parent(deepcopy(f.original), trans=trans.PARENT_TRANSLATIONS, pubtype_map=trans.PARENT_PUBTYPE_MAP))
if 'images' in webform_json[webform_nid]:
for img_idx, image in enumerate(webform_json[webform_nid]['images']):
image_obj = Image(image, local_path=self.get_local_image_path(image),
remote_path=self.get_remote_image_path(image), trans=trans.IMG_TRANSLATIONS)
#Add contributor info
if 'list_the_creator_of_the_image' in image:
image_obj.add_contributor(parse_creators(image['list_the_creator_of_the_image']))
#TODO: this just keeps getting worse
if 'datasources' in webform_json[webform_nid]['images'][img_idx]:
for dataset_json in webform_json[webform_nid]['images'][img_idx]['datasources']:
dataset = Dataset(dataset_json, trans=trans.DATASET_TRANSLATIONS, known_ids=trans.DATASET_IDS)
#Commence the hacks
try:
dataset.temporal_extent = ' '.join(
[parse(dataset_json[field]).isoformat() for field in ['start_time', 'end_time']]
)
except TypeError, e:
print 'Problem with start/end time: ', fig_url, f.title, e
print dataset_json['start_time'], dataset_json['end_time']
dataset.temporal_extent = None
except ValueError, e:
print 'Problem with start/end time: ', fig_url, f.title, e
print dataset_json['start_time'], dataset_json['end_time']
dataset.temporal_extent = None
dataset.spatial_extent = ' '.join(['{k}: {v};'.format(k=key, v=dataset_json[key]) for key in
['maximum_latitude', 'minimum_latitude', 'maximum_longitude',
'minimum_longitude']])
#Filter overlapping Dataset keys out
activity_json = {k: dataset_json[k] for k in dataset_json if
k not in ['href', 'uri', 'identifier', 'start_time', 'end_time']}
#Add synthetic identifier
activity_json['identifier'] = '-'.join((image_obj.identifier.split('-')[0], dataset.identifier, 'process'))
dataset.activity = Activity(activity_json, trans=trans.ACT_TRANSLATIONS)
# TODO: Extract DOIs from citation
# image_obj.datasets.append(dataset)
f.images.append(image_obj)