def create_title_bool_and(record: Dict[str, str]) -> str:
if 'Subtitle' in record.keys() and record["Subtitle"] not in ["N/A", ""]:
query_str = "(" + ")+AND+(".join([
normalize(str(record['Main Title'])),
normalize(str(record['Subtitle']))
]) + ")"
else:
query_str = normalize(record['Main Title'])
# logger.debug('Title Boolean phrase or string: ' + query_str)
return query_str
def look_up_book_in_worldcat(book_dict: Dict[str, str]) -> pd.DataFrame:
# Generate query string
full_title = create_full_title(book_dict)
logger.info(f'Looking for "{full_title}" in WorldCat...')
# Data currently has one author last name; otherwise I'd do what's commented below or process one-to-many relationship
# query_author = normalize(f"{book_dict['Author_First']} {book_dict['Author_Last']})
# Replacing apostrophe because they are breaking query strings when they occur
query_author = book_dict['Author_Last'].replace("'", " ")
query_title = normalize(full_title)
query_str = f'srw.ti all "{query_title}" and srw.au all "{query_author}"'
logger.debug(query_str)
params = {
'wskey': WC_API_KEY,
"query": query_str,
"maximumRecords": 100,
'frbrGrouping': 'off'
}
result = make_request_using_cache(WC_BIB_BASE_URL, params)
if not result:
return pd.DataFrame({})
records = parse_marcxml(result)
records_df = pd.DataFrame(records)
logger.info(f'Number of WorldCat records found: {len(records_df)}')
logger.debug(records_df.head(10))
return records_df
def main():
if len(sys.argv) != 3:
print("Usage:\npython extract_pov.py [SOURCE FILE/FOLDER] [SAVE_DIR]")
exit(1)
else:
source = sys.argv[1]
save_dir = sys.argv[2]
if not os.path.exists(save_dir):
print("Creating directory %s." % save_dir)
os.makedirs(save_dir)
if os.path.isdir(source):
print("Reading from directory %s." % source)
# Walk through the directory
for root, _, files in os.walk(source):
for f in files:
name, ext = os.path.splitext(f)
if ext == '.pcd':
print("Reading from file %s." % f)
pts = load_point_cloud(os.path.join(root, f))
x, y, z = normalize(pts)
if not os.path.exists(os.path.join(save_dir, name)):
os.makedirs(os.path.join(save_dir, name))
save_point_cloud(
pts,
os.path.join(save_dir, name,
name + '_normalized.pcd'))
# Create folder in save_dir
if not os.path.exists(os.path.join(save_dir, name)):
os.makedirs(os.path.join(save_dir, name))
# Generate VTK file for reconstructed surface
render3D(os.path.join(save_dir, name,
name + '_normalized.pcd'),
show=False)
subprocess.check_call([
'./extract_pov',
os.path.join(save_dir, name,
name + '_normalized_output.vtk'),
os.path.join(save_dir, name) + '/',
str(x[0]),
str(x[1]),
str(x[2]),
str(y[0]),
str(y[1]),
str(y[2]),
str(z[0]),
str(z[1]),
str(z[2])
])
print('Extracted PoV images to %s' %
os.path.join(save_dir, name))
else:
root, file = os.path.split(source)
name, ext = os.path.splitext(file)
if ext != '.pcd':
print('Invalid file.')
exit(1)
print("Reading from file %s." % source)
pts = load_point_cloud(source)
x, y, z = normalize(pts)
if not os.path.exists(os.path.join(save_dir, name)):
os.makedirs(os.path.join(save_dir, name))
save_point_cloud(
pts, os.path.join(save_dir, name, name + '_normalized.pcd'))
# Create folder in save_dir
if not os.path.exists(os.path.join(save_dir, name)):
os.makedirs(os.path.join(save_dir, name))
# Generate VTK file for reconstructed surface
render3D(os.path.join(save_dir, name, name + '_normalized.pcd'),
show=False)
subprocess.check_call([
'./extract_pov',
os.path.join(save_dir, name, name + '_normalized_output.vtk'),
os.path.join(save_dir, name) + '/',
str(x[0]),
str(x[1]),
str(x[2]),
str(y[0]),
str(y[1]),
str(y[2]),
str(z[0]),
str(z[1]),
str(z[2])
])
print('Extracted PoV images to %s' % os.path.join(save_dir, name))
def look_up_book_in_resource(book_dict: Dict[str, str]) -> pd.DataFrame:
# Generate query string
# logger.info(f'Looking for {book_dict["Main Title"]} in Harvard LibraryCloud...')
query_author = normalize(f"{book_dict['Author 1 Given']} {book_dict['Author 1 Initial']} {book_dict['Author 1 Family']}")
# query_author = book_dict['authorLast']
query_author.replace("'", " ")
title_bool_and = create_title_bool_and(book_dict)
params = {
'title' : title_bool_and,
'name' : query_author,
'limit': 10,
'publisher' : book_dict['Publisher']
}
query_str = f'&'.join([k+'='+str(params[k]) for k in list(params.keys())])
# logger.debug(query_str)
records = {}
result = make_request_using_cache(BIB_BASE_URL, params)
if result:
records.update(parse_modsxml(result,book_dict))
if len(list(records.keys())) == 0:
params.pop('publisher')
result = make_request_using_cache(BIB_BASE_URL, params)
if result:
records.update(parse_modsxml(result,book_dict))
if book_dict['Publisher'] != book_dict['Copyright Holder']:
params['publisher'] = book_dict['Copyright Holder']
second_result = make_request_using_cache(BIB_BASE_URL, params)
if second_result:
second_records = parse_modsxml(second_result,book_dict)
if len(list(second_records.keys())) > 0:
records.update(second_records)
# print(records)
# records.update(use_isbnlib({book_dict['ID']:book_dict}))
categorized = False
for k in list(records.keys()):
r = records[k]
for col in ['ebook ISBN', 'paper ISBN','hardcover ISBN']:
if col in r:
if len(r[col]) > 0:
categorized = True
for k in list(records.keys()):
r = records[k]
if len(str(r['Uncategorized ISBN'])) > 40:
categorized = False
# if categorized == False:
# records.update(use_isbnlib(records))
if records == {}:
return pd.DataFrame({})
else:
# records.update(use_isbnlib(records))
records_df = pd.DataFrame.from_dict(records,orient='index')
# logger.info(f'Number of records found: {len(records_df)}')
# logger.debug(records_df.head(10))
return records_df