def get_compare_dict(self):
json_url = 'https://storage.googleapis.com/storage/v1/b/us-ed-scraping/o/compare-statistics.json?alt=media'
json_s3_file = os.path.join(os.getenv('ED_OUTPUT_PATH'), 'tools',
'stats', 's3_compare-statistics.json')
json_local_file = os.path.join(os.getenv('ED_OUTPUT_PATH'),
'statistics.json')
try:
req = requests.get(json_url)
req.raise_for_status()
with open(json_s3_file, 'wb') as json_file:
json_file.write(req.content)
except:
pass
try:
result = json.loads(json_s3_file)
except JSONDecodeError:
try:
with open(json_local_file) as json_file:
result = json.load(json_file)
except FileNotFoundError:
logger.error('Comparison statistics JSON not found!')
raise
return result
def __init__(self):
logger.debug("Creating statistics...")
if os.path.exists(
self.METRICS_OUTPUT_XLSX): # check if excel sheet exist
os.remove(self.METRICS_OUTPUT_XLSX) # remove the excel sheet
try:
self.datopian_out_df = pd.read_csv(os.path.join(
os.getenv('ED_OUTPUT_PATH'), 'out_df.csv'),
header=0)
except Exception as e:
logger.error(
'Could not load the Datopian CSV, please generate it first.')
# read the AIR csv into a dataframe
try:
air_csv_url = 'https://storage.googleapis.com/storage/v1/b/us-ed-scraping/o/AIR.csv?alt=media'
req = requests.get(air_csv_url)
air_df_path = pathlib.Path(os.getenv('ED_OUTPUT_PATH'), 'tools',
"stats", 'data', 'air_df.csv')
# make the required path/directories
pathlib.Path.resolve(air_df_path).parent.mkdir(parents=True,
exist_ok=True)
# write the downloded file to disk
with open(air_df_path, 'wb') as air_df_file:
air_df_file.write(req.content)
self.air_out_df = pd.read_csv(air_df_path, header=0)
except Exception as e:
logger.error('Could not load the AIR CSV.')
def transform(name=None, input_file=None):
"""
function is responsible for transforming raw datasets into Collections
"""
if not name: # user has not provided a scraper name to get collections with
logger.error('Scraper/Office name not provided. Cannot generate collections')
sys.exit(1)
try:
# load the Graph representing the deduplicated scraped datasets
GraphWrapper.load_graph(file_dir_path=Path(OUTPUT_DIR, 'graphs', name),
file_stem_name=f'{name}.deduplicate')
except:
# load the Graph representing the scraped datasets
GraphWrapper.load_graph(file_dir_path=Path(OUTPUT_DIR, 'graphs', name),
file_stem_name=name)
# get the loaded graph
graph = GraphWrapper.get_graph()
# identify collections within the graph
identify_collections_within_graph(graph)
# link dataset vertices to their appropriate collection(s) within the graph
link_datasets_to_collections_in_graph(graph)
# write the identified collections to the raw dataset files
add_collections_to_raw_datasets(graph=graph,
output_dir=OUTPUT_DIR)
# write the graph to files
# this method is explicitly thread/proccess safe, so no need for lock
GraphWrapper.write_graph(file_dir_path=Path(os.getenv('ED_OUTPUT_PATH'),
"graphs", f"{name}"),
file_stem_name=f'{name}.collections')
# create the page legend file for this graph
GraphWrapper.create_graph_page_legend(file_dir_path=Path(os.getenv('ED_OUTPUT_PATH'),
"graphs", f"{name}"),
file_stem_name=f'{name}.collections')
# create the collections.json file
collections_list = [] # holds the list of collections acquired from graph
with graph.graph_lock:
for collection in graph.vs.select(is_collection_eq=True, name_ne='base_vertex'):
collections_list.append({'collection_id': collection['collection_id'],
'collection_title': collection['title'],
'collection_url': collection['name']})
# get a list of non-duplicate collections
collections_list = get_distinct_collections_from(collections_list,
min_occurence_counter=1)
# get the path were the gotten Collections will be saved to on local disk
file_output_path = f'{CURRENT_TRANSFORMER_OUTPUT_DIR}/{(name or "all")}.collections.json'
# write to file the collections gotten from 'name' scraped output
h.write_file(file_output_path, collections_list)
# write file the collections gotten from 'name' scraped out to S3 bucket
h.upload_to_s3_if_configured(file_output_path,
f'{(name or "all")}.collections.json')
def read_json_file():
try:
with open(file_path) as json_file:
data = json.load(json_file)
except:
logger.error('Cannot read statistics.json file!')
return data
def parse(res):
""" function parses content to create a dataset model
or return None if no resource in content"""
# ensure that the response text gotten is a string
if not isinstance(getattr(res, 'text', None), str):
return None
try:
soup_parser = bs4.BeautifulSoup(res.text, 'html5lib')
except:
return None
# check if the content contains any of the extensions
if soup_parser.body.find(name='a',
href=base_parser.resource_checker,
recursive=True) is None:
# no resource on this page, so return None
return None
# if code gets here, at least one resource was found
# check if the parser is working on OSERS web page
if soup_parser.body.find(name='div', id='maincontent',
recursive=True) is not None:
# parse the page with the parser and return result
return parsers.parser1.parse(res)
# check if the parser is working on OCTAE web page (variant 2)
if soup_parser.body.select_one('.headersLevel1') is not None:
# parse the page with the parser and return result
return parsers.parser2.parse(res)
else:
logger.error('Page doesnt fit in any structure:')
logger.error(res)
return None
def transform(name, input_file=None):
if input_file is None:
file_list = traverse_output(name)
else:
try:
with open(input_file, 'r') as fp:
file_list = [line.rstrip() for line in fp]
except:
logger.warning(
f'Cannot read from list of output files at {input_file}, falling back to all collected data!'
)
file_list = traverse_output(name)
logger.debug(f'{len(file_list)} files to transform.')
catalog = Catalog()
catalog.catalog_id = "datopian_data_json_" + (name or 'all')
# keep track/stata for item transformed
datasets_number = 0
resources_number = 0
sources_number = 0
collections_number = 0
# loop through the list of filepaths to be transformed
for file_path in file_list:
data = read_file(file_path)
if not data:
continue
dataset = _transform_scraped_dataset(data, name)
if not dataset: # no dataset was returned (i.e. dataset probably marked for removal)
continue
catalog.datasets.append(dataset)
datasets_number += 1
resources_number += len(dataset.distribution)
# TODO WORK FROM BELOW HERE
# get the list of Sources for this catalog
catalog_sources = list()
try:
# read the list of preprocessed (but still 'raw') Sources from file
catalog_sources = read_file(
f"{h.get_output_path('sources')}/{(name or 'all')}.sources.json")
# transform the list of preprocessed Sources to a list of Source objects acceptable for the catalog object
catalog_sources = _transform_preprocessed_sources(catalog_sources)
except:
logger.warning(
f'"sources transformer" output file ({(name or "all")}.sources.json) not found. This datajson output will have no "source" field'
)
# add the list of Source objects to the catalog
catalog.sources = catalog_sources or []
# update the number fo transformed Sources
sources_number = len(catalog_sources or [])
# get the list of Collections for this catalog
catalog_collections = list()
try:
# read the list of preprocessed (but still 'raw') Collections from file
catalog_collections = read_file(
f"{h.get_output_path('collections')}/{(name or 'all')}.collections.json"
)
# transform the list of preprocessed Collections to a list of Collection objects acceptable for the catalog object
catalog_collections = _transform_preprocessed_collections(
catalog_collections)
except:
logger.warning(
f'"sources transformer" output file ({(name or "all")}.collections.json) not found. This datajson output will have no "collection" field'
)
# add the list of Collection objects to the catalog
catalog.collections = catalog_collections or []
# update the number fo transformed Collections
collections_number = len(catalog_collections or [])
# validate the catalog object
if not catalog.validate_catalog(pls_fix=True):
logger.error(f"catalog validation Failed! Ending transform process")
return
logger.debug('{} Sources transformed.'.format(sources_number))
logger.debug('{} Collections transformed.'.format(collections_number))
logger.debug('{} datasets transformed.'.format(datasets_number))
logger.debug('{} resources transformed.'.format(resources_number))
output_path = h.get_output_path('datajson')
file_path = os.path.join(output_path, f'{(name or "all")}.data.json')
with open(file_path, 'w') as output:
output.write(catalog.dump())
logger.debug(f'Output file: {file_path}')
h.upload_to_s3_if_configured(file_path, f'{(name or "all")}.data.json')
import os
import sys
import json
from edscrapers.cli import logger
OUTPUT_PATH = os.getenv('ED_OUTPUT_PATH')
try:
file_path = os.path.join(OUTPUT_PATH, 'statistics.json')
except TypeError:
logger.error('ED_OUTPUT_PATH env var not set!')
sys.exit(1)
def read_json_file():
try:
with open(file_path) as json_file:
data = json.load(json_file)
except:
logger.error('Cannot read statistics.json file!')
return data
def get_stats():
return read_json_file()
def get_total_datasets_number():
data = read_json_file()
return data['total']['datopian']['datasets']
def get_total_datasets_data():
