def extractFirstName(name, order):
'''Split on dots'''
name = ' '.join(name.split('.'))
'''Split on - '''
name = ' '.join(name.split('-'))
'''Replace numbers by whitespace'''
oldname = name
name = re.sub("\d+", "", name)
if not len(name):
name = re.sub("\d+", "_", oldname)
oldname = name
'''Replace ? by whitespace'''
name = re.sub("\?", "", name)
if not len(name):
name = re.sub("\?", "_", oldname)
name = ' '.join(name.split('_'))
'''Use the Python name parser'''
try:
firstName = getFirstNameFromHumanName(HumanName(name), order)
except:
firstName = getFirstNameFromSplitName(name.split(), order)
'''If fail, use heuristics'''
if firstName.strip() == name.strip():
'''firstName('Ben Voigt') = 'Ben Voigt'!!!'''
if len(name.split()) == 2:
firstName = getFirstNameFromSplitName(name.split(), order)
else:
'''Try CamelCase'''
uncamel = ' '.join(splitCamelCase(name).split('_'))
if uncamel != name:
try:
firstName = HumanName(uncamel).first
if len(firstName.split()) == 2:
firstName = getFirstNameFromSplitName(firstName.split(), order)
except:
firstName = getFirstNameFromSplitName(uncamel.split(), order)
if firstName == 'Mc':
firstName = ''
if len(firstName) == 1:
firstName = ''
return firstName.lower()
def GetNameLink(name):
# Finds and returns formatted name and wikilinks for given name.
name = HumanName(name)
name.capitalize(force=True)
name = str(name)
soup = GetSoup("https://en.wikipedia.org/wiki/" + name.replace(" ", "_"),
False).text
wikitext = name
tennis = [
"International Tennis Federation", "Prize money", "Grand Slam",
"tennis career", "Wikipedia does not have", "may refer to", "WTA",
"ITF", "ATP"
]
pipe = False
if soup != None:
if any([f in soup for f in tennis
]): # player article exists, or no article exists
if "Redirected from" in soup:
soup = GetSoup(soup, True)
title = str(soup.title.string).replace(" - Wikipedia",
"").strip()
wikitext = title
pipe = True # if name is redirect, pipes wikilink to avoid anachronist names, e.g. using "Margaret Court" instead of "Margaret Smith" before she married.
else: # article exists for name but for different person
wikitext = name + " (tennis)"
pipe = True
wikilink = "[[" + wikitext + ("|" + name if pipe else "") + "]]"
split_name = name.split(" ")
abbr_name = "-".join(
f[0] for f in split_name[0].split("-")) + " " + " ".join(
split_name[1:]
) # reduce name to first name initials + last name, e.g. "J-L Struff"
abbr_wikilink = "[[" + wikitext + "|" + abbr_name + "]]"
return [name, wikilink, abbr_wikilink]
def extractFirstName(name, order):
'''Split on dots'''
name = ' '.join(name.split('.'))
'''Split on - '''
name = ' '.join(name.split('-'))
'''Replace numbers by whitespace'''
oldname = name
name = re.sub("\d+", "", name)
if not len(name):
name = re.sub("\d+", "_", oldname)
oldname = name
'''Replace ? by whitespace'''
name = re.sub("\?", "", name)
if not len(name):
name = re.sub("\?", "_", oldname)
name = ' '.join(name.split('_'))
'''Use the Python name parser'''
try:
firstName = getFirstNameFromHumanName(HumanName(name), order)
except:
firstName = getFirstNameFromSplitName(name.split(), order)
'''If fail, use heuristics'''
if firstName.strip() == name.strip():
'''firstName('Ben Voigt') = 'Ben Voigt'!!!'''
if len(name.split()) == 2:
firstName = getFirstNameFromSplitName(name.split(), order)
else:
'''Try CamelCase'''
uncamel = ' '.join(splitCamelCase(name).split('_'))
if uncamel != name:
try:
firstName = HumanName(uncamel).first
if len(firstName.split()) == 2:
firstName = getFirstNameFromSplitName(
firstName.split(), order)
except:
firstName = getFirstNameFromSplitName(
uncamel.split(), order)
if firstName == 'Mc':
firstName = ''
if len(firstName) == 1:
firstName = ''
return firstName.lower()
def get_last_name(author):
author = HumanName(author.split("and")[0])
return author.last
