def handle(self, *args, **options):
start = datetime.now()
files_found = 0
for d, _, files in os.walk(SAMPLE_FILE_DIR):
for i, this_file in enumerate(files):
files_found += 1
file_path = SAMPLE_FILE_DIR + this_file
# ignore files that aren't .html in case any got mixed in there
# may want to filter on other criteria here too
if file_path.find(".html") > 0 and i < FILE_ENTRY_CAP:
doc_id = this_file.replace(".html", "")
print "Entering file number %s data from: %s" % (i,
file_path)
try:
enter_document(file_path, doc_id)
except PageCountError:
print "Error entering file number %s from %s - entire document skipped. " % (
i, file_path)
print traceback.print_exc()
if files_found == 0:
print warning_message
else:
end = datetime.now()
elapsed = end - start
print "Time elapsed: %s" % (elapsed)
def handle(self, *args, **options):
start = datetime.now()
files_found = 0
for d, _, files in os.walk(SAMPLE_FILE_DIR):
for i, this_file in enumerate(files):
files_found += 1
file_path = SAMPLE_FILE_DIR + this_file
# ignore files that aren't .html in case any got mixed in there
# may want to filter on other criteria here too
if file_path.find(".html") > 0 and i < FILE_ENTRY_CAP:
doc_id = this_file.replace(".html", "")
print "Entering file number %s data from: %s" % (i, file_path)
try:
enter_document(file_path, doc_id)
except PageCountError:
print "Error entering file number %s from %s - entire document skipped. " % (i, file_path)
print traceback.print_exc()
if files_found ==0:
print warning_message
else:
end = datetime.now()
elapsed = end-start
print "Time elapsed: %s" % (elapsed)
def handle(self, *args, **options):
# just try one that's weird.
if False:
file_path = "parser/hocr_sample/02-0575282_990EZ_201212.html"
doc_id = "02-0575282_990EZ_201212"
enter_document(file_path, doc_id)
assert False
start = datetime.now()
for d, _, files in os.walk(SAMPLE_FILE_DIR):
for i, this_file in enumerate(files):
file_path = SAMPLE_FILE_DIR + this_file
# ignore files that aren't .html in case any got mixed in there
# may want to filter on other criteria here too
if file_path.find(".html") > 0 and i < FILE_ENTRY_CAP:
doc_id = this_file.replace(".html", "")
print "Entering file number %s data from: %s" % (i, file_path)
try:
enter_document(file_path, doc_id)
except PageCountError:
print "Error entering file number %s from %s - entire document skipped. " % (i, file_path)
print traceback.print_exc()
end = datetime.now()
elapsed = end-start
print "Time elapsed: %s" % (elapsed)
def handle(self, *args, **options):
# sample file included with repo, hopefully
this_file = os.path.join(BASE_DIR, 'hocr_parser/test_hocr/58-1723645_990_201204.html')
doc_id = "58-1723645_990_201204"
start = datetime.now()
enter_document(this_file, doc_id)
end = datetime.now()
elapsed = end-start
print "Time elapsed: %s" % (elapsed)
def handle(self, *args, **options):
this_file = "parser/test_hocr/58-1723645_990_201204.html"
doc_id = "58-1723645_990_201204"
start = datetime.now()
enter_document(this_file, doc_id)
end = datetime.now()
elapsed = end-start
print "Time elapsed: %s" % (elapsed)
def handle(self, *args, **options):
# sample file included with repo, hopefully
#doc_id = "1088501-adventuretime-alta-p1"
doc_id = "14400741771771-p2"
this_file = SAMPLE_FILE_DIR + doc_id + ".html"
# 1088501-adventuretime-alta-p1.png
start = datetime.now()
enter_document(this_file, doc_id, DOCUMENT_COLLECTION_SLUG, only_enter_new_pages=False)
end = datetime.now()
elapsed = end-start
print "Time elapsed: %s" % (elapsed)
