|
|
@@ -72,41 +72,4 @@ def get_book_data(isbn): |
|
|
|
book.update(book_cover) |
|
|
|
return book |
|
|
|
except: |
|
|
|
pass |
|
|
|
|
|
|
|
# function to get full metadata for a book and combine into one object |
|
|
|
# TO BE DELETED |
|
|
|
def get_book(resource_id): |
|
|
|
book = get_resource(resource_id) |
|
|
|
book_data = get_book_data(book.isbn) |
|
|
|
book.__dict__.update(book_data) |
|
|
|
return book |
|
|
|
|
|
|
|
# function to replace embedded URL strings with href links |
|
|
|
def replace_urls(input): |
|
|
|
# Compile a regular expression to match URLs. |
|
|
|
# This regular expression is not exhaustive and may not match all possible URLs. |
|
|
|
# It is intended to be a starting point and can be refined and expanded as needed. |
|
|
|
url_regex = re.compile(r'((?:https?:(?:/{1,3}|[a-z0-9%])|[a-z0-9.\-]+[.](?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)/)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:\'\".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)\b/?(?!@)))') |
|
|
|
|
|
|
|
# Find all URLs in the input string using the regular expression. |
|
|
|
# This will return a list of Match objects, each of which represents a single URL in the string. |
|
|
|
matches = url_regex.finditer(input) |
|
|
|
|
|
|
|
# Iterate over the list of matches and replace each URL with an HTML link. |
|
|
|
for match in matches: |
|
|
|
# Get the full URL from the Match object. |
|
|
|
url = match.group(0) |
|
|
|
|
|
|
|
# Create the HTML link by wrapping the URL in an <a> tag. |
|
|
|
# If the URL does not include a protocol (e.g. "http://" or "https://"), |
|
|
|
# then add "http://" as the default protocol. |
|
|
|
if not url.startswith('http'): |
|
|
|
link = f'<a href="http://{url}">{url}</a>' |
|
|
|
else: |
|
|
|
link = f'<a href="{url}">{url}</a>' |
|
|
|
|
|
|
|
# Replace the URL in the original string with the HTML link. |
|
|
|
input = input.replace(url, link) |
|
|
|
|
|
|
|
return input |
|
|
|
pass |