siat 3.7.7__py3-none-any.whl → 3.7.9__py3-none-any.whl

siat/allin.py

@@ -41,6 +41,9 @@ from siat.financials import *
 # 财务分析：雅虎源
 from siat.financials2 import *
 
+# 财务报表：雅虎源
+from siat.fin_stmt2_yahoo import *
+
 # 财务分析：中国
 from siat.financials_china import *
 

siat/common.py

@@ -4171,6 +4171,77 @@ def firstLetterUpper(text):
 
     return utext
 
+
+#==============================================================================
+if __name__ == '__main__':
+    long_text = "Hello, this is a test string."
+    short_text = "test strng"
+     
+    similar_substring, similarity = find_similar_substring(long_text, short_text)
+    if similarity:
+        print(f"Similar substring found: {similar_substring}, Similarity: {similarity}")
+    else:
+        print("No similar substring found.")
+
+ 
+def find_similar_substring(long_string, short_string, threshold=0.7):
+    """
+    
+    功能：判断一个字符串中是否存在与另一个字符串相似度较高的子串
+    注意：尚未测试
+    """
+    
+    import difflib
+    
+    # 使用SequenceMatcher比较字符串
+    matcher = difflib.SequenceMatcher(None, long_string, short_string)
+    
+    # 遍历所有可能的子串长度
+    for size in range(len(short_string), len(long_string) + 1):
+        for start in range(0, len(long_string) - size + 1):
+            # 获取子串并计算相似度
+            substring = long_string[start:start + size]
+            similarity = matcher.ratio()
+            
+            # 如果相似度超过阈值，返回子串
+            if similarity > threshold:
+                return substring, similarity
+    
+    # 如果没有找到相似度较高的子串，返回None
+    return None, None   
+
+    
+#==============================================================================
+if __name__ == '__main__':
+    str1 = "kitten"
+    str2 = "sitting"
+    
+    string_similarity(str1,str2)
+    
+
+def string_similarity(str1,str2,ignore_cases=True):
+    """
+    
+    功能：计算两个字符串的文本相似度
+    """
+    import difflib
+    
+    if ignore_cases:
+        string1=str1.lower()
+        string2=str2.lower()
+    else:
+        string1=str1
+        string2=str2
+    
+    # 创建SequenceMatcher对象
+    matcher = difflib.SequenceMatcher(None, string1, string2)
+    
+    # 计算相似度
+    similarity = matcher.ratio()
+    #print(f"SequenceMatcher Similarity: {similarity:.2f}")
+
+    return similarity
+
 #==============================================================================
 if __name__ == '__main__':
     string = "HeLLo, Welcome to this New WorLd!"
@@ -4181,7 +4252,7 @@ if __name__ == '__main__':
 def contains_any(string, words):
     """
     
-    功能：测试字符串string中是否含有字符串列表words中的任意一个元素
+    功能：测试字符串string中是否含有字符串列表words中的任意一个元素，忽略字母大小写
     参数：
     string：字符串，大小写不限
     words：字符串列表，大小写不限
@@ -4208,6 +4279,183 @@ def contains_any(string, words):
     #检查字符串new_string是否包含列表new_words_list中的任何元素
     return any((word in new_string) for word in new_words_list)    
 
+#==============================================================================
+if __name__ == '__main__':
+    string = "HeLLo, Welcome to this New WorLd!"
+    words = ["Hello", "World"]
+    words = ["Hello", "World","the"]
+
+    contains_all(string, words)
+
+def contains_all(string, words):
+    """
+    
+    功能：测试字符串string中是否含有字符串列表words中的全部元素，忽略字母大小写
+    参数：
+    string：字符串，大小写不限
+    words：字符串列表，大小写不限
+    注意：为避免大小写字母的影响，比较前需要先将两边的字母全部小写化
+    """
+    
+    result=True
+    for w in words:
+        if not contains_any(string,w):
+            result=False
+            break
+        
+    return result
+
+
+#==============================================================================
+if __name__ == '__main__':
+    alist = ["CurrentDebt",
+            "CurrentDebtAndCapitalLeaseObligation",
+            "CurrentDeferredLiabilities",
+            "CurrentLiabilities",
+            "OtherCurrentBorrowings",
+            "OtherCurrentLiabilities",
+            "OtherNonCurrentLiabilities",
+            "TotalNonCurrentLiabilitiesNetMinorityInterest"]
+
+    alist = [
+            "CurrentDebtAndCapitalLeaseObligation",
+            "CurrentDeferredLiabilities",
+            "CurrentLiabilities",
+            "OtherCurrentBorrowings",
+            "OtherCurrentLiabilities",
+            "OtherNonCurrentLiabilities",
+            "TotalNonCurrentLiabilitiesNetMinorityInterest"]
+    
+    item_words = ["Current", "Debt"]
+    item_words = ["Current", "Liabilities"]
+    
+    perfect_match=True
+
+    list_contains_all(alist, item_words)
+
+def list_contains_all(alist, item_words,perfect_match=True):
+    """
+    
+    功能：测试列表alist中是否有元素含有字符串列表item_words中的全部元素，忽略字母大小写
+    参数：
+    alist：字符串列表，大小写不限
+    item_words：字符串列表，大小写不限
+    注意：为避免大小写字母的影响，比较前需要先将两边的字母全部小写化
+    返回值：
+        若列表alist中有多个元素含有字符串列表item_words中的全部元素，返回相似度最高的元素
+        若无则返回False
+    """
+    DEBUG=False
+    
+    #将item_words合成为一个字符串，以便比较相似度
+    words=''
+    for w in item_words:
+        words=words+w
+    if DEBUG:
+        print(f"  DEBUG: item_words={item_words}, words={words}")
+    
+    result=False
+    best_similarity=0
+    for e in alist:
+        similarity=0
+        
+        if DEBUG:
+            print(f"  DEBUG: e={e}")
+            
+        if perfect_match: #要求e精确含有item_words中的每个元素
+            if contains_all(e,item_words):
+                similarity=string_similarity(e,words)
+        else:
+            similarity=string_similarity(e,words)
+            
+        if DEBUG:
+            print(f"  DEBUG: item_words={item_words}, e={e}, similarity={similarity}")
+        
+        if similarity > best_similarity:
+            best_similarity=similarity
+            result=e
+                
+        
+    return result,best_similarity
+
+if __name__ == '__main__':
+    alist = ["CurrentDebt",
+            "CurrentDebtAndCapitalLeaseObligation",
+            "CurrentDeferredLiabilities",
+            "CurrentLiabilities",
+            "OtherCurrentBorrowings",
+            "OtherCurrentLiabilities",
+            "OtherNonCurrentLiabilities",
+            "TotalNonCurrentLiabilitiesNetMinorityInterest"]
+
+    alist = [
+            "CurrentDebtAndCapitalLeaseObligation",
+            "CurrentDeferredLiabilities",
+            "CurrentLiabilities",
+            "OtherCurrentBorrowings",
+            "OtherCurrentLiabilities",
+            "OtherNonCurrentLiabilities",
+            "TotalNonCurrentLiabilitiesNetMinorityInterest"]
+    
+    item_words_list=[["Current","Debt"],["Current","Liabilities"]]
+    item_words_list=[["Current","Liabilibities"],["Current","Debt"]]
+    
+    list_contains_all_list(alist, item_words_list)
+    
+def list_contains_all_list(alist, item_words_list):
+    """
+    
+    功能：测试列表alist中是否有元素含有字符串列表组中item_words_list各个item_words中的全部元素，忽略字母大小写
+    参数：
+    alist：字符串列表，大小写不限
+    item_words_list：字符串列表组，大小写不限。第1个为最佳字符串列表，后面可跟多个替代最佳字符串列表
+    注意：为避免大小写字母的影响，比较前需要先将两边的字母全部小写化
+    返回值：
+        若列表alist中有多个元素含有字符串列表item_words中的全部元素，返回相似度最高的元素
+        若出现多个最高相似度相同的，则返回第一个
+        若无则返回False
+    """
+    DEBUG=False
+    
+    best_result=False
+    best_similarity=0
+    
+    for iwords in item_words_list:
+        result,similarity=list_contains_all(alist, iwords,perfect_match=False)
+        if DEBUG:
+            print("  DEBUG: iwords={0}, alist={1}".format(iwords,alist))
+            #print("  DEBUG: result={0}, similarity={1}".format(result,similarity))
+            print('')
+            print(f"  DEBUG: result={result}, similarity={similarity:.2f}")
+        
+        if similarity > best_similarity:
+            best_similarity=similarity
+            best_result=result
+        
+    return best_result
+
+
+#==============================================================================
+if __name__ == '__main__':
+    max_sleep=30
+
+    sleep_random(max_sleep)
+
+def sleep_random(max_sleep=30):
+    """
+    
+    功能：随机挂起秒数，以防被数据源封堵IP地址，适用于连续抓取同种信息时。
+    参数：
+    max_sleep：最大挂起秒数，默认30秒。随机挂起1-30秒。
+    """
+    
+    import time; import random
+    
+    random_int=random.randint(1,max_sleep)
+    time.sleep(random_int)
+
+    return
+    
 #==============================================================================
 if __name__ == '__main__':
     s = "Hello, 世界! This is a test string with symbols #$%^&*()."