emlyn · April 16, 2021 22:14
diff --git a/code.py b/code.py
 # Requires: pip install unidecode

 import gzip
 import re
 import unidecode

 # From https://sciencenotes.org/list-elements-atomic-number/, contains:
 # - Atomic number
 # - Symbol
 # - Name
 with open('elementlist.csv', 'rt') as f:
    elems = []
    for line in f:
        elems.append(line.split(',')[1])

 any_element = re.compile('|'.join(elems).lower())
 alpha = re.compile('[a-z]')

 # From https://datasets.imdbws.com/, contains:
 # - nconst (string) - alphanumeric unique identifier of the name/person
 # - primaryName (string)– name by which the person is most often credited
 # - birthYear – in YYYY format
 # - deathYear – in YYYY format if applicable, else '\N'
 # - primaryProfession (array of strings)– the top-3 professions of the person
 # - knownForTitles (array of tconsts) – titles the person is known for
 with gzip.open('name.basics.tsv.gz', 'rt') as f:
    seen = set()
    people = []
    for line in f:
        id, nm, by, dy, pr, kt = line.split('\t')
        plain_nm = unidecode.unidecode(nm).lower()
        plain_nm = re.sub('^[^a-z0-9]*', '', plain_nm)
        plain_nm = re.sub('[^a-z0-9]{1,}', ' ', plain_nm)
        if (nm not in seen) and alpha.search(plain_nm) and (not any_element.search(plain_nm)):
            people.append([plain_nm, nm, id, pr])
            seen.add(nm)

 print("Found {} different names".format(len(people)))
 print()

 for _, nm, id, pr in sorted(people):
    extra = ""
    if pr:
        extra = " ({})".format(pr.replace(',', ', '))
    escaped = re.sub('[][{}()\\`*_#.!+-]', lambda s: '\\' + s[0], nm)
    print('- [{}](https://www.imdb.com/{}/){}'.format(escaped, id, extra))
diff --git a/result.md b/result.md
	# Requires: pip install unidecode

	import gzip
	import re
	import unidecode

	# From https://sciencenotes.org/list-elements-atomic-number/, contains:
	# - Atomic number
	# - Symbol
	# - Name
	with open('elementlist.csv', 'rt') as f:
	elems = []
	for line in f:
	elems.append(line.split(',')[1])

	any_element = re.compile('\|'.join(elems).lower())
	alpha = re.compile('[a-z]')

	# From https://datasets.imdbws.com/, contains:
	# - nconst (string) - alphanumeric unique identifier of the name/person
	# - primaryName (string)– name by which the person is most often credited
	# - birthYear – in YYYY format
	# - deathYear – in YYYY format if applicable, else '\N'
	# - primaryProfession (array of strings)– the top-3 professions of the person
	# - knownForTitles (array of tconsts) – titles the person is known for
	with gzip.open('name.basics.tsv.gz', 'rt') as f:
	seen = set()
	people = []
	for line in f:
	id, nm, by, dy, pr, kt = line.split('\t')
	plain_nm = unidecode.unidecode(nm).lower()
	plain_nm = re.sub('^[^a-z0-9]*', '', plain_nm)
	plain_nm = re.sub('[^a-z0-9]{1,}', ' ', plain_nm)
	if (nm not in seen) and alpha.search(plain_nm) and (not any_element.search(plain_nm)):
	people.append([plain_nm, nm, id, pr])
	seen.add(nm)

	print("Found {} different names".format(len(people)))
	print()

	for _, nm, id, pr in sorted(people):
	extra = ""
	if pr:
	extra = " ({})".format(pr.replace(',', ', '))
	escaped = re.sub('[][{}()\\`*_#.!+-]', lambda s: '\\' + s[0], nm)
	print('- [{}](https://www.imdb.com/{}/){}'.format(escaped, id, extra))
No results found