def getShortLink(link):
if matchKey(link, ['weibo.', 'twitter.', 't.me/']):
return
raw_link = getRawLink(link)
if isCN(export_to_telegraph.getTitle(raw_link)):
return shorter(raw_link, link)
if isCN(export_to_telegraph.getTitle(link)):
return link
def containCN(text):
if not text:
return False
for c in text:
if isCN(c):
return True
return False
def isCNIndex(key):
text = index.get(key)
if not text:
return False
for c in text:
if isCN(c):
return True
return False
def calculateToSimplified(toSimplified, noAutoConvert, title):
if toSimplified:
return True
if noAutoConvert:
return False
for c in title:
if isCN(c) and not hanzidentifier.is_simplified(c):
return True
return False
def suspiciousUser(user):
display = getDisplayUser(user)
if isCN(display):
return False
if len(''.join(display.split())) <= 2:
return True
if display.lower() == 'deleted account':
return True
return False
def en2zhPiece(text):
if not text.strip() or text.startswith('['):
return text
if isCN(text) or len(text) < 3:
return text
print('translating', text)
result = translator.translate(text)
l_char_len = len(text) - len(text.lstrip())
l_char = text[:l_char_len]
r_char_len = len(text) - len(text.rstrip())
if not r_char_len:
r_char = ''
else:
r_char = text[-r_char_len:]
return l_char + result + r_char
def shouldDelay(channel):
key = channel + '/0'
if timestamp.get(key) < time.time() - 60 * 24 * 60 * 60:
return True
if channel not in suspect._db.items:
return False
for ch in index.get(key, ''):
if isCN(ch):
return False
for ch in index.get(key, ''):
try:
if matchKey(unicodedata.name(ch), ['arabic', 'cyrillic']):
return True
except Exception as e:
...
return False
def videoFilter(title, v_len, author, _, raw):
if matchKey(title, ['镇魂', '白宇', '朱一龙']) and v_len > 60 * 20:
return False
if matchKey(title, ['丁毅', '聰明的一休', '準提咒']):
return False
if matchKey(author, ['sunfirekiss', '丁毅', 'YaleUniversity']):
return False
if matchKey(raw, ['Human Behavioral Biology']):
return False
if matchKey(author, ['bach', 'piano']) or matchKey(title,
['bach', 'piano']):
return False
if v_len > 10 * 60:
return False
if isCN(title):
return False
return True
def en2zh(text):
soup = BeautifulSoup(text, 'html.parser')
final_result = []
for item in soup:
if item.name == 'a':
final_result.append(str(item))
continue
for line in str(item).split('\n'):
if not line.strip():
continue
if isCN(line):
final_result.append(line)
continue
try:
line_result = [trans_microsoft.translate(line)]
except:
line_result = []
line_result.append(trans_google.translate(line, dest='zh-CN').text)
line_result = [
line.strip() for line in line_result if isValid(line)
]
final_result += line_result
return '\n\n'.join(final_result)
def tooShort(text): if isCN(text): return len(text) <= 1 return len(text) <= 4
def isSimplified(text):
cn = sum([isCN(c) + hanzidentifier.is_simplified(c) for c in text])
for c in text:
if isCN(c) and not hanzidentifier.is_simplified(c):
return False
return cn * 2 >= len(text)
def matchLanguage(channel, status_text):
if not credential['channels'][channel].get('chinese_only'):
return True
return isCN(status_text)