def get_clean_keywords_list(self, unique=True):
"""
@summary: 获取规则化的关键词列表, 由于用户输入关键词可能含有中文标点等情况.
#统一为半角,小写,用户输入关键词按照1.自然分词 2.用户本身的输入间隔进行
#返回这两种分割非重复的关键词列表.
"""
uniform_keywords = uniform(self.keywords)
# uniform_keywords = replace_punctuation(uniform_keywords)
seg_keywords = jieba.cut(uniform_keywords)
seg_keywords = [
keyword.lower() for keyword in seg_keywords
if not is_other(keyword)
]
user_seg_keywords = uniform_keywords.split()
user_seg_keywords = [
keyword.lower() for keyword in user_seg_keywords
if not is_other(keyword)
]
if unique:
seg_keywords = get_ordered_unique(seg_keywords)
user_seg_keywords = get_ordered_unique(user_seg_keywords)
if seg_keywords == user_seg_keywords:
return [seg_keywords]
else:
return [seg_keywords, user_seg_keywords]
def get_clean_keywords_list(self, unique=True):
"""
@summary: 获取规则化的关键词列表, 由于用户输入关键词可能含有中文标点等情况.
#统一为半角,小写,用户输入关键词按照1.自然分词 2.用户本身的输入间隔进行
#返回这两种分割非重复的关键词列表.
"""
uniform_keywords = uniform(self.keywords)
# uniform_keywords = replace_punctuation(uniform_keywords)
seg_keywords = jieba.cut(uniform_keywords)
seg_keywords = [ keyword.lower() for keyword in seg_keywords if not is_other(keyword) ]
user_seg_keywords = uniform_keywords.split()
user_seg_keywords = [ keyword.lower() for keyword in user_seg_keywords if not is_other(keyword)]
if unique:
seg_keywords = get_ordered_unique(seg_keywords)
user_seg_keywords = get_ordered_unique(user_seg_keywords)
if seg_keywords == user_seg_keywords:
return [seg_keywords]
else:
return [seg_keywords, user_seg_keywords]
def get_all_eng_words(self, unique=True):
"""
@summary: 获取关键词和职位描述中的所有单词或者单词+数字类型 ,如cocos2d
"""
desc = uniform(self.keywords + ' ' + self.job_desc)
words = jieba.cut(desc)
eng_words = [word for word in words if is_num_word(word)]
if unique:
eng_words = get_ordered_unique(eng_words)
return eng_words
def get_all_eng_words(self, unique=True):
"""
@summary: 获取关键词和职位描述中的所有单词或者单词+数字类型 ,如cocos2d
"""
desc = uniform(self.keywords + ' ' + self.job_desc)
words = jieba.cut(desc)
eng_words = [word for word in words if is_num_word(word)]
if unique:
eng_words = get_ordered_unique(eng_words)
return eng_words