def semshift(search_term):
r = requests.get(
f'https://csd.clld.org/parameters?sEcho=9&iColumns=4&sColumns=more%2Cname%2Csemantic_domain%2Cpart_of_speech&sSearch_1={search_term}&bRegex_1=false&bSearchable_1=true',
headers={
'accept': 'application/json',
'x-requested-with': 'XMLHttpRequest'
})
meanings = []
try:
etyma = [
html.fromstring(item[1]).attrib['href'].split('/')[-1]
for item in json.loads(r.content)['aaData']
]
if len(etyma) == 0:
return []
urls = [
f'https://csd.clld.org/values?parameter={etym}&sEcho=1&iColumns=6&sColumns=language%2Cname%2Cphonetic%2Cdescription%2Ccomment%2Csources'
for etym in etyma
]
results = multi_request(urls,
headers={
'accept': 'application/json',
'x-requested-with': 'XMLHttpRequest'
})
for result in results:
meanings += [
item[-3] for item in json.loads(result.content)['aaData']
]
except json.decoder.JSONDecodeError:
pass
return list(set(meanings))
def semshift(search_term):
r = requests.get(
f'https://stedt.berkeley.edu/~stedt-cgi/rootcanal.pl/search/ajax?tbl=etyma&s={search_term}&f=&lg=&as_values_lg-auto=',
headers={'accept': 'application/json'})
meanings = []
try:
ids = [item[0] for item in json.loads(r.content)['data']]
if len(ids) == 0:
return []
urls = [
f'https://stedt.berkeley.edu/~stedt-cgi/rootcanal.pl/etymon/{id}'
for id in ids
]
results = multi_request(urls)
for r2 in results:
tree2 = html.fromstring(r2.content)
meanings += tree2.xpath(
'/html/body/table[2]/tbody/tr/td[5]/text()')
except json.decoder.JSONDecodeError:
pass
return list(set(meanings))
def reverse(search_term):
r = requests.get(
f'https://stedt.berkeley.edu/~stedt-cgi/rootcanal.pl/search/ajax?tbl=lexicon&s={search_term}&f=&lg=&as_values_lg-auto=',
headers={'accept': 'application/json'})
proto_nums = set([
first_numeric(elem[1]) for elem in json.loads(r.content)['data']
if elem[1] != None
])
proto_nums.discard(0)
if len(proto_nums) == 0:
return []
meanings = []
urls = [
f'https://stedt.berkeley.edu/~stedt-cgi/rootcanal.pl/etymon/{num}'
for num in proto_nums
]
results = multi_request(urls)
for r2 in results:
tree2 = html.fromstring(r2.content)
meanings.append(
trim(tree2.xpath('/html/body/table[1]/tr/td/h1/text()')[0]))
return meanings
def semshift(search_term):
r = requests.get(f'https://clics.clld.org/parameters?sEcho=9&iColumns=7&sColumns=%23%2Cname%2C%23%2Ccount_varieties%2Ccount_colexifications%2Cinfomap%2Csubgraph&iDisplayStart=0&iDisplayLength=100&mDataProp_1=1&sSearch_1={search_term}',
headers={'accept': 'application/json', 'x-requested-with': 'XMLHttpRequest'})
urls = [html.fromstring(item[1]).attrib['href'] for item in json.loads(r.content)['aaData']]
results = multi_request(urls)
meanings = []
for result in results:
tree = html.fromstring(result.content)
meanings += tree.xpath('//*[@class="Edge"]/text()')
return meanings
def reverse(self, search_term):
if len(self.target_phrases) == 0:
self.populate_targets()
urls = [
f'http://datsemshift.ru/search?target={quote(input)}'
for input in self.target_phrases if search_term in input
]
results = multi_request(urls)
meanings = [
item for sublist in [
html.fromstring(r.content).xpath(
'/html/body/main/div/table/tr/td[3]/text()')
for r in results
] for item in sublist if item != 'Meaning 1'
]
return meanings
def semshift(self, search_term):
if len(self.source_phrases) == 0:
self.populate_sources()
urls = [
f'http://datsemshift.ru/search?source={quote(source_phrase)}'
for source_phrase in self.source_phrases
if search_term in source_phrase
]
results = multi_request(urls)
meanings = [
item for sublist in [
html.fromstring(r.content).xpath(
'/html/body/main/div/table/tr/td[5]/text()')
for r in results
] for item in sublist if item != 'Meaning 2'
]
return meanings
