def download_parse_pdf(pdf_url):
raw_pdf = requests.get(f'https://www.boe.es{pdf_url}',
allow_redirects=True)
pdf_path = f"/tmp/{pdf_url.split('/')[-1]}"
open(pdf_path, 'wb').write(raw_pdf.content)
bormeparser.parse(pdf_path,
bormeparser.SECCION.A).to_json(f"{pdf_path}.json")
with open(f"{pdf_path}.json") as f:
data = json.load(f)
os.remove(f"{pdf_path}.json")
os.remove(pdf_path)
return data
def import_borme_pdf(filename, create_json=True):
"""
Import BORME PDF to database
"""
results = {
'created_anuncios': 0,
'created_bormes': 0,
'created_companies': 0,
'created_persons': 0,
'errors': 0
}
try:
borme = bormeparser.parse(filename)
results = _import1(borme)
if create_json:
json_path = get_borme_json_path(borme.date)
os.makedirs(json_path, exist_ok=True)
json_filepath = os.path.join(json_path, '%s.json' % borme.cve)
borme.to_json(json_filepath)
except Exception as e:
logger.error('[X] Error grave en bormeparser.parse(): %s' % filename)
logger.error('[X] %s: %s' % (e.__class__.__name__, e))
if not all(map(lambda x: x == 0, results.values())):
print_results(results, borme)
return True, results
def from_pdf_file(filename, create_json=True):
"""Importa un archivo BORME-PDF en la BD.
:param filename: Archivo a importar
:param create_json: Crear BORME-JSON como paso intermedio
:type filename: str
:type create_json: bool
:rtype: (bool, dict)
"""
results = {
'created_anuncios': 0,
'created_bormes': 0,
'created_companies': 0,
'created_persons': 0,
'errors': 0
}
try:
borme = bormeparser.parse(filename, bormeparser.SECCION.A)
results = _from_instance(borme)
if create_json:
json_path = get_borme_json_path(borme.date)
os.makedirs(json_path, exist_ok=True)
json_filepath = os.path.join(json_path, '%s.json' % borme.cve)
borme.to_json(json_filepath)
except Exception as e:
logger.error('[X] Error grave (III) en bormeparser.parse(): %s' % filename)
logger.error('[X] %s: %s' % (e.__class__.__name__, e))
if not all(map(lambda x: x == 0, results.values())):
_print_results(results, borme)
return True, results
def from_pdf_file(filename, create_json=True):
"""Importa un archivo BORME-PDF en la BD.
:param filename: Archivo a importar
:param create_json: Crear BORME-JSON como paso intermedio
:type filename: str
:type create_json: bool
:rtype: (bool, dict)
"""
results = {
'created_anuncios': 0,
'created_bormes': 0,
'created_companies': 0,
'created_persons': 0,
'errors': 0
}
try:
borme = bormeparser.parse(filename, bormeparser.SECCION.A)
results = _from_instance(borme)
if create_json:
json_path = get_borme_json_path(borme.date)
os.makedirs(json_path, exist_ok=True)
json_filepath = os.path.join(json_path, '%s.json' % borme.cve)
borme.to_json(json_filepath)
except Exception as e:
logger.error('[X] Error grave (III) en bormeparser.parse(): %s' %
filename)
logger.error('[X] %s: %s' % (e.__class__.__name__, e))
if not all(map(lambda x: x == 0, results.values())):
_print_results(results, borme)
return True, results
def setUpClass(cls):
super(TestBormeModel, cls).setUpClass()
global results
path = os.path.expanduser('~/.bormes/pdf/2015/02/10/BORME-A-2015-27-10.pdf')
borme = bormeparser.parse(path, bormeparser.SECCION.A)
results = _import1(borme)
def setUpClass(cls):
super(TestBormeModel, cls).setUpClass()
global results
path = os.path.expanduser(
'~/.bormes/pdf/2015/02/10/BORME-A-2015-27-10.pdf')
borme = bormeparser.parse(path, bormeparser.SECCION.A)
results = _import1(borme)
def run(self):
while True:
pdf_path, json_path = self.queue.get()
print('Creating %s ...' % json_path)
try:
borme = bormeparser.parse(pdf_path, bormeparser.SECCION.A)
borme.to_json(json_path)
print('{cve}: OK'.format(cve=borme.cve))
except Exception as e:
print('ERROR: {} ({})'.format(os.path.basename(pdf_path), e))
self.queue.task_done()
def run(self):
while True:
pdf_path, json_path = self.queue.get()
print('Creating %s ...' % json_path)
try:
borme = bormeparser.parse(pdf_path, bormeparser.SECCION.A)
borme.to_json(json_path)
print('{cve}: OK'.format(cve=borme.cve))
except Exception as e:
print('ERROR: {} ({})'.format(os.path.basename(pdf_path), e))
self.queue.task_done()
def import_borme_pdf(filename, create_json=True):
"""
Import BORME PDF to database
"""
results = {'created_anuncios': 0, 'created_bormes': 0, 'created_companies': 0, 'created_persons': 0, 'errors': 0}
try:
borme = bormeparser.parse(filename, bormeparser.SECCION.A)
results = _import1(borme)
if create_json:
json_path = get_borme_json_path(borme.date)
os.makedirs(json_path, exist_ok=True)
json_filepath = os.path.join(json_path, '%s.json' % borme.cve)
borme.to_json(json_filepath)
except Exception as e:
logger.error('[X] Error grave en bormeparser.parse(): %s' % filename)
logger.error('[X] %s: %s' % (e.__class__.__name__, e))
if not all(map(lambda x: x == 0, results.values())):
print_results(results, borme)
return True, results
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
import bormeparser
import bormeparser.borme
import logging
import os
import sys
if __name__ == '__main__':
if len(sys.argv) == 1:
print('Usage: %s <filename.pdf> [--debug]')
sys.exit(1)
# set logger DEBUG
if len(sys.argv) == 3 and sys.argv[2] == '--debug':
bormeparser.borme.logger.setLevel(logging.DEBUG)
# filename
filename = os.path.basename(sys.argv[1]).replace('.pdf', '.json')
borme = bormeparser.parse(sys.argv[1])
borme.to_json(filename)
print()
print('Created %s' % os.path.abspath(filename))
def _import_borme_download_range2(begin, end, seccion, local_only, strict=False, create_json=True):
"""
strict: Para en caso de error grave
"""
next_date = begin
total_results = {'created_anuncios': 0, 'created_bormes': 0, 'created_companies': 0, 'created_persons': 0,
'total_anuncios': 0, 'total_bormes': 0, 'total_companies': 0, 'total_persons': 0, 'errors': 0}
total_start_time = time.time()
try:
while next_date and next_date <= end:
xml_path = get_borme_xml_filepath(next_date)
try:
bxml = BormeXML.from_file(xml_path)
if bxml.next_borme is None:
bxml = BormeXML.from_date(next_date)
os.makedirs(os.path.dirname(xml_path), exist_ok=True)
bxml.save_to_file(xml_path)
except FileNotFoundError:
bxml = BormeXML.from_date(next_date)
os.makedirs(os.path.dirname(xml_path), exist_ok=True)
bxml.save_to_file(xml_path)
# Add FileHandlers
logpath = os.path.join(settings.BORME_LOG_ROOT, 'imports', '%02d-%02d' % (bxml.date.year, bxml.date.month))
os.makedirs(logpath, exist_ok=True)
fh1_path = os.path.join(logpath, '%02d_info.txt' % bxml.date.day)
fh1 = logging.FileHandler(fh1_path)
fh1.setLevel(logging.INFO)
logger.addHandler(fh1)
fh2_path = os.path.join(logpath, '%02d_error.txt' % bxml.date.day)
fh2 = logging.FileHandler(fh2_path)
fh2.setLevel(logging.WARNING)
logger.addHandler(fh2)
json_path = get_borme_json_path(bxml.date)
pdf_path = get_borme_pdf_path(bxml.date)
os.makedirs(pdf_path, exist_ok=True)
logger.info('============================================================')
logger.info('Ran import_borme_download at %s' % timezone.now())
logger.info(' Import date: %s. Section: %s' % (bxml.date.isoformat(), seccion))
logger.info('============================================================')
print('\nPATH: %s\nDATE: %s\nSECCION: %s\n' % (pdf_path, bxml.date, seccion))
bormes = []
if not local_only:
_, files = bxml.download_borme(pdf_path, seccion=seccion)
for filepath in files:
if filepath.endswith('-99.pdf'):
continue
logger.info('%s' % filepath)
total_results['total_bormes'] += 1
try:
bormes.append(bormeparser.parse(filepath, seccion))
except Exception as e:
logger.error('[X] Error grave (I) en bormeparser.parse(): %s' % filepath)
logger.error('[X] %s: %s' % (e.__class__.__name__, e))
if strict:
logger.error('[X] Una vez arreglado, reanuda la importación:')
logger.error('[X] python manage.py importbormetoday local')
return False, total_results
else:
cves = bxml.get_cves(bormeparser.SECCION.A)
files_json = list(map(lambda x: os.path.join(json_path, '%s.json' % x), cves))
files_pdf = list(map(lambda x: os.path.join(pdf_path, '%s.pdf' % x), cves))
if files_exist(files_json):
for filepath in files_json:
logger.info('%s' % filepath)
total_results['total_bormes'] += 1
try:
bormes.append(bormeparser.Borme.from_json(filepath))
except Exception as e:
logger.error('[X] Error grave (I) en bormeparser.Borme.from_json(): %s' % filepath)
logger.error('[X] %s: %s' % (e.__class__.__name__, e))
if strict:
logger.error('[X] Una vez arreglado, reanuda la importación:')
logger.error('[X] python manage.py importbormetoday local') # TODO: --from date
return False, total_results
elif files_exist(files_pdf):
for filepath in files_pdf:
logger.info('%s' % filepath)
total_results['total_bormes'] += 1
try:
bormes.append(bormeparser.parse(filepath, seccion))
except Exception as e:
logger.error('[X] Error grave (II) en bormeparser.parse(): %s' % filepath)
logger.error('[X] %s: %s' % (e.__class__.__name__, e))
if strict:
logger.error('[X] Una vez arreglado, reanuda la importación:')
logger.error('[X] python manage.py importbormetoday local') # TODO: --from date
return False, total_results
else:
logger.error('[X] Faltan archivos PDF y JSON que no se desea descargar.')
logger.error('[X] JSON: %s' % ' '.join(files_json))
logger.error('[X] PDF: %s' % ' '.join(files_pdf))
if strict:
return False, total_results
for filepath in files_json:
if not os.path.exists(filepath):
logger.warn('[X] Missing JSON: %s' % filepath)
continue
logger.info('%s' % filepath)
total_results['total_bormes'] += 1
try:
bormes.append(bormeparser.Borme.from_json(filepath))
except Exception as e:
logger.error('[X] Error grave (II) en bormeparser.Borme.from_json(): %s' % filepath)
logger.error('[X] %s: %s' % (e.__class__.__name__, e))
for borme in sorted(bormes):
total_results['total_anuncios'] += len(borme.get_anuncios())
start_time = time.time()
try:
results = _import1(borme)
except Exception as e:
logger.error('[%s] Error grave en _import1:' % borme.cve)
logger.error('[%s] %s' % (borme.cve, e))
logger.error('[%s] Prueba importar manualmente en modo detallado para ver el error:' % borme.cve)
logger.error('[%s] python manage.py importbormepdf %s -v 3' % (borme.cve, borme.filename))
if strict:
logger.error('[%s] Una vez arreglado, reanuda la importación:' % borme.cve)
logger.error('[%s] python manage.py importbormetoday local' % borme.cve)
return False, total_results
if create_json:
os.makedirs(json_path, exist_ok=True)
json_filepath = os.path.join(json_path, '%s.json' % borme.cve)
borme.to_json(json_filepath)
total_results['created_anuncios'] += results['created_anuncios']
total_results['created_bormes'] += results['created_bormes']
total_results['created_companies'] += results['created_companies']
total_results['created_persons'] += results['created_persons']
total_results['total_companies'] += results['total_companies']
total_results['total_persons'] += results['total_persons']
total_results['errors'] += results['errors']
if not all(map(lambda x: x == 0, total_results.values())):
print_results(results, borme)
elapsed_time = time.time() - start_time
logger.info('[%s] Elapsed time: %.2f seconds' % (borme.cve, elapsed_time))
# Remove handlers
logger.removeHandler(fh1)
logger.removeHandler(fh2)
next_date = bxml.next_borme
except KeyboardInterrupt:
logger.info('\nImport aborted.')
elapsed_time = time.time() - total_start_time
logger.info('\nBORMEs creados: %d/%d' % (total_results['created_bormes'], total_results['total_bormes']))
logger.info('Anuncios creados: %d/%d' % (total_results['created_anuncios'], total_results['total_anuncios']))
logger.info('Empresas creadas: %d/%d' % (total_results['created_companies'], total_results['total_companies']))
logger.info('Personas creadas: %d/%d' % (total_results['created_persons'], total_results['total_persons']))
logger.info('Total elapsed time: %.2f seconds' % elapsed_time)
return True, total_results
def _import_borme_download_range(begin, end, seccion, local_only,
strict=False, create_json=True):
"""Importa los BORMEs data un rango de fechas.
Itera en el rango de fechas. Por cada día:
* Genera los nombres de los archivos BORMEs a partir del archivo BORME-XML
* Carga los archivos BORME-JSON, o los BORME-PDF si no existieran los JSON
* Importa en la BD los datos de los BORME
:param begin: Fecha desde la que importar
:param end: Fecha hasta la que importar
:param seccion: Seccion del BORME
:param local_only: No descarga archivos, solo procesa archivos ya presentes
:param strict: Aborta el proceso tan pronto como se encuentre un error
:param create_json: Crear archivo BORME-JSON
:type date_from: datetime.date
:type date_to: datetime.date
:type seccion: bormeparser.SECCION
:type local_only: bool
:type strict: bool
:type create_json: bool
:rtype: (bool, dict)
"""
next_date = begin
total_results = {
'created_anuncios': 0,
'created_bormes': 0,
'created_companies': 0,
'created_persons': 0,
'total_anuncios': 0,
'total_bormes': 0,
'total_companies': 0,
'total_persons': 0,
'errors': 0
}
total_start_time = time.time()
try:
while next_date and next_date <= end:
xml_path = get_borme_xml_filepath(next_date)
try:
bxml = BormeXML.from_file(xml_path)
if bxml.next_borme is None:
bxml = BormeXML.from_date(next_date)
os.makedirs(os.path.dirname(xml_path), exist_ok=True)
bxml.save_to_file(xml_path)
except OSError:
bxml = BormeXML.from_date(next_date)
os.makedirs(os.path.dirname(xml_path), exist_ok=True)
bxml.save_to_file(xml_path)
# Add FileHandlers
directory = '%02d-%02d' % (bxml.date.year, bxml.date.month)
logpath = os.path.join(settings.BORME_LOG_ROOT,
'imports', directory)
os.makedirs(logpath, exist_ok=True)
fh1_path = os.path.join(logpath, '%02d_info.txt' % bxml.date.day)
fh1 = logging.FileHandler(fh1_path)
fh1.setLevel(logging.INFO)
logger.addHandler(fh1)
fh2_path = os.path.join(logpath, '%02d_error.txt' % bxml.date.day)
fh2 = logging.FileHandler(fh2_path)
fh2.setLevel(logging.WARNING)
logger.addHandler(fh2)
json_path = get_borme_json_path(bxml.date)
pdf_path = get_borme_pdf_path(bxml.date)
os.makedirs(pdf_path, exist_ok=True)
logger.info(
"===================================================\n"
"Ran import_borme_download at {now}\n"
" Import date: {borme_date}. Section: {section}\n"
"==================================================="
.format(now=timezone.now(), section=seccion,
borme_date=bxml.date.isoformat()))
print("\nPATH: {}"
"\nDATE: {}"
"\nSECCION: {}\n"
.format(pdf_path, bxml.date, seccion))
bormes = []
if not local_only:
_, files = bxml.download_borme(pdf_path, seccion=seccion)
for filepath in files:
if filepath.endswith('-99.pdf'):
continue
logger.info('%s' % filepath)
total_results['total_bormes'] += 1
try:
bormes.append(bormeparser.parse(filepath, seccion))
except Exception as e:
logger.error('[X] Error grave (I) en bormeparser.parse(): %s' % filepath)
logger.error('[X] %s: %s' % (e.__class__.__name__, e))
if strict:
logger_resume_import()
return False, total_results
else:
files_json, files_pdf = _generate_borme_files_list(bxml,
json_path,
pdf_path)
if files_exist(files_json):
bormes, err = _load_and_append(files_json, strict)
total_results["total_bormes"] += len(files_json)
if err:
return False, total_results
elif files_exist(files_pdf):
bormes, err = _load_and_append(files_pdf, strict, seccion)
total_results["total_bormes"] += len(files_pdf)
if err:
return False, total_results
else:
logger.error('[X] Faltan archivos PDF y JSON que no se desea descargar.')
logger.error('[X] JSON: %s' % ' '.join(files_json))
logger.error('[X] PDF: %s' % ' '.join(files_pdf))
if strict:
return False, total_results
bormes, err = _load_and_append(files_pdf, strict, seccion)
total_results["total_bormes"] += len(files_pdf)
for borme in sorted(bormes):
total_results['total_anuncios'] += len(borme.get_anuncios())
start_time = time.time()
try:
results = _from_instance(borme)
except Exception as e:
logger.error('[%s] Error grave en _from_instance:' % borme.cve)
logger.error('[%s] %s' % (borme.cve, e))
logger.error('[%s] Prueba importar manualmente en modo detallado para ver el error:' % borme.cve)
logger.error('[%s] python manage.py importbormepdf %s -v 3' % (borme.cve, borme.filename))
if strict:
logger_resume_import(cve=borme.cve)
return False, total_results
if create_json:
os.makedirs(json_path, exist_ok=True)
json_filepath = os.path.join(json_path, '%s.json' % borme.cve)
borme.to_json(json_filepath)
for key in total_results.keys():
total_results[key] += results[key]
if not all(map(lambda x: x == 0, total_results.values())):
_print_results(results, borme)
elapsed_time = time.time() - start_time
logger.info('[%s] Elapsed time: %.2f seconds' % (borme.cve, elapsed_time))
# Remove handlers
logger.removeHandler(fh1)
logger.removeHandler(fh2)
next_date = bxml.next_borme
except KeyboardInterrupt:
logger.info('\nImport aborted.')
elapsed_time = time.time() - total_start_time
logger.info("\nBORMEs creados: {created_bormes}/{total_bormes}\n"
"Anuncios creados: {created_anuncios}/{total_anuncios}\n"
"Empresas creadas: {created_companies}/{total_companies}\n"
"Personas creadas: {created_persons}/{total_persons}"
.format(**total_results))
logger.info("Total elapsed time: %.2f seconds" % elapsed_time)
return True, total_results
import os
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description='Convert BORME A PDF files to JSON.')
parser.add_argument('filename', help='BORME A PDF filename')
parser.add_argument('--debug',
action='store_true',
default=False,
help='Debug mode')
parser.add_argument(
'-o',
'--output',
help='Output directory or filename (default is current directory)')
args = parser.parse_args()
# set logger DEBUG (Not working)
if args.debug:
bormeparser.borme.logger.setLevel(logging.DEBUG)
bormeparser.backends.pypdf2.parser.logger.setLevel(
logging.DEBUG) # FIXME: DEFAULT_PARSER
print('\nParsing {}'.format(args.filename))
borme = bormeparser.parse(args.filename, bormeparser.SECCION.A)
path = borme.to_json(args.output)
if path:
print('Created {}'.format(os.path.abspath(path)))
else:
print('Error creating JSON for {}'.format(args.filename))
def _import_borme_download_range(begin,
end,
seccion,
local_only,
strict=False,
create_json=True):
"""Importa los BORMEs data un rango de fechas.
Itera en el rango de fechas. Por cada día:
* Genera los nombres de los archivos BORMEs a partir del archivo BORME-XML
* Carga los archivos BORME-JSON, o los BORME-PDF si no existieran los JSON
* Importa en la BD los datos de los BORME
:param begin: Fecha desde la que importar
:param end: Fecha hasta la que importar
:param seccion: Seccion del BORME
:param local_only: No descarga archivos, solo procesa archivos ya presentes
:param strict: Aborta el proceso tan pronto como se encuentre un error
:param create_json: Crear archivo BORME-JSON
:type date_from: datetime.date
:type date_to: datetime.date
:type seccion: bormeparser.SECCION
:type local_only: bool
:type strict: bool
:type create_json: bool
:rtype: (bool, dict)
"""
next_date = begin
total_results = {
'created_anuncios': 0,
'created_bormes': 0,
'created_companies': 0,
'created_persons': 0,
'total_anuncios': 0,
'total_bormes': 0,
'total_companies': 0,
'total_persons': 0,
'errors': 0
}
total_start_time = time.time()
try:
while next_date and next_date <= end:
xml_path = get_borme_xml_filepath(next_date)
try:
bxml = BormeXML.from_file(xml_path)
if bxml.next_borme is None:
bxml = BormeXML.from_date(next_date)
os.makedirs(os.path.dirname(xml_path), exist_ok=True)
bxml.save_to_file(xml_path)
except OSError:
bxml = BormeXML.from_date(next_date)
os.makedirs(os.path.dirname(xml_path), exist_ok=True)
bxml.save_to_file(xml_path)
# Add FileHandlers
directory = '%02d-%02d' % (bxml.date.year, bxml.date.month)
logpath = os.path.join(settings.BORME_LOG_ROOT, 'imports',
directory)
os.makedirs(logpath, exist_ok=True)
fh1_path = os.path.join(logpath, '%02d_info.txt' % bxml.date.day)
fh1 = logging.FileHandler(fh1_path)
fh1.setLevel(logging.INFO)
logger.addHandler(fh1)
fh2_path = os.path.join(logpath, '%02d_error.txt' % bxml.date.day)
fh2 = logging.FileHandler(fh2_path)
fh2.setLevel(logging.WARNING)
logger.addHandler(fh2)
json_path = get_borme_json_path(bxml.date)
pdf_path = get_borme_pdf_path(bxml.date)
os.makedirs(pdf_path, exist_ok=True)
logger.info(
"===================================================\n"
"Ran import_borme_download at {now}\n"
" Import date: {borme_date}. Section: {section}\n"
"===================================================".format(
now=timezone.now(),
section=seccion,
borme_date=bxml.date.isoformat()))
print("\nPATH: {}"
"\nDATE: {}"
"\nSECCION: {}\n".format(pdf_path, bxml.date, seccion))
bormes = []
if not local_only:
_, files = bxml.download_borme(pdf_path, seccion=seccion)
for filepath in files:
if filepath.endswith('-99.pdf'):
continue
logger.info('%s' % filepath)
total_results['total_bormes'] += 1
try:
bormes.append(bormeparser.parse(filepath, seccion))
except Exception as e:
logger.error(
'[X] Error grave (I) en bormeparser.parse(): %s' %
filepath)
logger.error('[X] %s: %s' % (e.__class__.__name__, e))
if strict:
logger_resume_import()
return False, total_results
else:
files_json, files_pdf = _generate_borme_files_list(
bxml, json_path, pdf_path)
if files_exist(files_json):
bormes, err = _load_and_append(files_json, strict)
total_results["total_bormes"] += len(files_json)
if err:
return False, total_results
elif files_exist(files_pdf):
bormes, err = _load_and_append(files_pdf, strict, seccion)
total_results["total_bormes"] += len(files_pdf)
if err:
return False, total_results
else:
logger.error(
'[X] Faltan archivos PDF y JSON que no se desea descargar.'
)
logger.error('[X] JSON: %s' % ' '.join(files_json))
logger.error('[X] PDF: %s' % ' '.join(files_pdf))
if strict:
return False, total_results
bormes, err = _load_and_append(files_pdf, strict, seccion)
total_results["total_bormes"] += len(files_pdf)
for borme in sorted(bormes):
total_results['total_anuncios'] += len(borme.get_anuncios())
start_time = time.time()
try:
results = _from_instance(borme)
except Exception as e:
logger.error('[%s] Error grave en _from_instance:' %
borme.cve)
logger.error('[%s] %s' % (borme.cve, e))
logger.error(
'[%s] Prueba importar manualmente en modo detallado para ver el error:'
% borme.cve)
logger.error(
'[%s] python manage.py importbormepdf %s -v 3' %
(borme.cve, borme.filename))
if strict:
logger_resume_import(cve=borme.cve)
return False, total_results
if create_json:
os.makedirs(json_path, exist_ok=True)
json_filepath = os.path.join(json_path,
'%s.json' % borme.cve)
borme.to_json(json_filepath)
for key in total_results.keys():
total_results[key] += results[key]
if not all(map(lambda x: x == 0, total_results.values())):
_print_results(results, borme)
elapsed_time = time.time() - start_time
logger.info('[%s] Elapsed time: %.2f seconds' %
(borme.cve, elapsed_time))
# Remove handlers
logger.removeHandler(fh1)
logger.removeHandler(fh2)
next_date = bxml.next_borme
except KeyboardInterrupt:
logger.info('\nImport aborted.')
elapsed_time = time.time() - total_start_time
logger.info("\nBORMEs creados: {created_bormes}/{total_bormes}\n"
"Anuncios creados: {created_anuncios}/{total_anuncios}\n"
"Empresas creadas: {created_companies}/{total_companies}\n"
"Personas creadas: {created_persons}/{total_persons}".format(
**total_results))
logger.info("Total elapsed time: %.2f seconds" % elapsed_time)
return True, total_results
def setUpClass(cls):
super(TestBormeModel, cls).setUpClass()
filepath = os.path.join(FILES_PATH, 'BORME-A-2015-27-10.pdf')
borme = bormeparser.parse(filepath, bormeparser.SECCION.A)
TestBormeModel.results = _from_instance(borme)
def setUpClass(cls):
cls.borme = bormeparser.parse(
os.path.join(EXAMPLES_PATH, 'BORME-C-2011-20488.html'),
SECCION.C)
def setUpClass(cls):
cls.borme = bormeparser.parse(
os.path.join(EXAMPLES_PATH, 'BORME-A-2015-27-10.pdf'), SECCION.A)
def setUpClass(cls):
cls.borme = bormeparser.parse(
os.path.join(EXAMPLES_PATH, 'BORME-C-2011-20488.html'),
SECCION.C)
def _import_borme_download_range2(begin, end, seccion, local_only, strict=False, create_json=True):
"""
strict: Para en caso de error grave
"""
next_date = begin
total_results = {'created_anuncios': 0, 'created_bormes': 0, 'created_companies': 0, 'created_persons': 0,
'total_anuncios': 0, 'total_bormes': 0, 'total_companies': 0, 'total_persons': 0, 'errors': 0}
total_start_time = time.time()
try:
while next_date and next_date <= end:
xml_path = get_borme_xml_filepath(next_date)
try:
bxml = BormeXML.from_file(xml_path)
if bxml.next_borme is None:
bxml = BormeXML.from_date(next_date)
os.makedirs(os.path.dirname(xml_path), exist_ok=True)
bxml.save_to_file(xml_path)
except FileNotFoundError:
bxml = BormeXML.from_date(next_date)
os.makedirs(os.path.dirname(xml_path), exist_ok=True)
bxml.save_to_file(xml_path)
# Add FileHandlers
logpath = os.path.join(settings.BORME_LOG_ROOT, 'imports', '%02d-%02d' % (bxml.date.year, bxml.date.month))
os.makedirs(logpath, exist_ok=True)
fh1_path = os.path.join(logpath, '%02d_info.txt' % bxml.date.day)
fh1 = logging.FileHandler(fh1_path)
fh1.setLevel(logging.INFO)
logger.addHandler(fh1)
fh2_path = os.path.join(logpath, '%02d_error.txt' % bxml.date.day)
fh2 = logging.FileHandler(fh2_path)
fh2.setLevel(logging.WARNING)
logger.addHandler(fh2)
json_path = get_borme_json_path(bxml.date)
pdf_path = get_borme_pdf_path(bxml.date)
os.makedirs(pdf_path, exist_ok=True)
logger.info('============================================================')
logger.info('Ran import_borme_download at %s' % timezone.now())
logger.info(' Import date: %s. Section: %s' % (bxml.date.isoformat(), seccion))
logger.info('============================================================')
print('\nPATH: %s\nDATE: %s\nSECCION: %s\n' % (pdf_path, bxml.date, seccion))
bormes = []
if not local_only:
_, files = bxml.download_borme(pdf_path, seccion=seccion)
for filepath in files:
if filepath.endswith('-99.pdf'):
continue
logger.info('%s' % filepath)
total_results['total_bormes'] += 1
try:
bormes.append(bormeparser.parse(filepath, seccion))
except Exception as e:
logger.error('[X] Error grave en bormeparser.parse(): %s' % filepath)
logger.error('[X] %s: %s' % (e.__class__.__name__, e))
if strict:
logger.error('[X] Una vez arreglado, reanuda la importación:')
logger.error('[X] python manage.py importbormetoday local')
return False, total_results
else:
cves = bxml.get_cves(bormeparser.SECCION.A)
files_json = list(map(lambda x: os.path.join(json_path, '%s.json' % x), cves))
files_pdf = list(map(lambda x: os.path.join(pdf_path, '%s.pdf' % x), cves))
if files_exist(files_json):
for filepath in files_json:
logger.info('%s' % filepath)
total_results['total_bormes'] += 1
try:
bormes.append(bormeparser.Borme.from_json(filepath))
except Exception as e:
logger.error('[X] Error grave en bormeparser.Borme.from_json(): %s' % filepath)
logger.error('[X] %s: %s' % (e.__class__.__name__, e))
if strict:
logger.error('[X] Una vez arreglado, reanuda la importación:')
logger.error('[X] python manage.py importbormetoday local') # TODO: --from date
return False, total_results
elif files_exist(files_pdf):
for filepath in files_pdf:
logger.info('%s' % filepath)
total_results['total_bormes'] += 1
try:
bormes.append(bormeparser.parse(filepath, seccion))
except Exception as e:
logger.error('[X] Error grave en bormeparser.parse(): %s' % filepath)
logger.error('[X] %s: %s' % (e.__class__.__name__, e))
if strict:
logger.error('[X] Una vez arreglado, reanuda la importación:')
logger.error('[X] python manage.py importbormetoday local') # TODO: --from date
return False, total_results
else:
logger.error('[X] Faltan archivos PDF y JSON que no se desea descargar.')
logger.error('[X] JSON: %s' % ' '.join(files_json))
logger.error('[X] PDF: %s' % ' '.join(files_pdf))
if strict:
return False, total_results
for filepath in files_json:
if not os.path.exists(filepath):
logger.warn('[X] Missing JSON: %s' % filepath)
continue
logger.info('%s' % filepath)
total_results['total_bormes'] += 1
try:
bormes.append(bormeparser.Borme.from_json(filepath))
except Exception as e:
logger.error('[X] Error grave en bormeparser.Borme.from_json(): %s' % filepath)
logger.error('[X] %s: %s' % (e.__class__.__name__, e))
for borme in sorted(bormes):
total_results['total_anuncios'] += len(borme.get_anuncios())
start_time = time.time()
try:
results = _import1(borme)
except Exception as e:
logger.error('[%s] Error grave en _import1:' % borme.cve)
logger.error('[%s] %s' % (borme.cve, e))
logger.error('[%s] Prueba importar manualmente en modo detallado para ver el error:' % borme.cve)
logger.error('[%s] python manage.py importbormepdf %s -v 3' % (borme.cve, borme.filename))
if strict:
logger.error('[%s] Una vez arreglado, reanuda la importación:' % borme.cve)
logger.error('[%s] python manage.py importbormetoday local' % borme.cve)
return False, total_results
if create_json:
os.makedirs(json_path, exist_ok=True)
json_filepath = os.path.join(json_path, '%s.json' % borme.cve)
borme.to_json(json_filepath)
total_results['created_anuncios'] += results['created_anuncios']
total_results['created_bormes'] += results['created_bormes']
total_results['created_companies'] += results['created_companies']
total_results['created_persons'] += results['created_persons']
total_results['total_companies'] += results['total_companies']
total_results['total_persons'] += results['total_persons']
total_results['errors'] += results['errors']
if not all(map(lambda x: x == 0, total_results.values())):
print_results(results, borme)
elapsed_time = time.time() - start_time
logger.info('[%s] Elapsed time: %.2f seconds' % (borme.cve, elapsed_time))
# Remove handlers
logger.removeHandler(fh1)
logger.removeHandler(fh2)
next_date = bxml.next_borme
except KeyboardInterrupt:
logger.info('\nImport aborted.')
elapsed_time = time.time() - total_start_time
logger.info('\nBORMEs creados: %d/%d' % (total_results['created_bormes'], total_results['total_bormes']))
logger.info('Anuncios creados: %d/%d' % (total_results['created_anuncios'], total_results['total_anuncios']))
logger.info('Empresas creadas: %d/%d' % (total_results['created_companies'], total_results['total_companies']))
logger.info('Personas creadas: %d/%d' % (total_results['created_persons'], total_results['total_persons']))
logger.info('Total elapsed time: %.2f seconds' % elapsed_time)
return True, total_results
def setUpClass(cls):
cls.borme = bormeparser.parse(
os.path.join(EXAMPLES_PATH, 'BORME-A-2015-27-10.pdf'), SECCION.A)
import bormeparser.backends.pypdf2.parser
from bormeparser.backends.defaults import OPTIONS
OPTIONS['SANITIZE_COMPANY_NAME'] = True
import argparse
import logging
import os
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Convert BORME A PDF files to JSON.')
parser.add_argument('filename', help='BORME A PDF filename')
parser.add_argument('--debug', action='store_true', default=False, help='Debug mode')
parser.add_argument('-o', '--output', help='Output directory or filename (default is current directory)')
args = parser.parse_args()
# set logger DEBUG (Not working)
if args.debug:
bormeparser.borme.logger.setLevel(logging.DEBUG)
bormeparser.backends.pypdf2.parser.logger.setLevel(logging.DEBUG) # FIXME: DEFAULT_PARSER
print('\nParsing {}'.format(args.filename))
borme = bormeparser.parse(args.filename, bormeparser.SECCION.A)
path = borme.to_json(args.output)
if path:
print('Created {}'.format(os.path.abspath(path)))
else:
print('Error creating JSON for {}'.format(args.filename))
def setUpClass(cls):
super(TestBormeModel, cls).setUpClass()
filepath = os.path.join(FILES_PATH, 'BORME-A-2015-27-10.pdf')
borme = bormeparser.parse(filepath, bormeparser.SECCION.A)
TestBormeModel.results = _from_instance(borme)
