python笔记：字符串

s=string.Template("This is ${name} big big pig")
print s.substitute(name="yzh")

s = "yzh is a big big pig"
if "pig" in s:
    print True
if "ppig" not in s:
    print True

s = "yzh is a big big pig"
for item in s:
    print item

for i,v in enumerate(s):
    print i,v

#从path提取目录名
s = u"D:\个人笔记\书籍"
index= s.rfind("\") #也可以用find
print s[index+1:]

s= u"hehe"# 这是一个unicode字符串
utf8S = s.encode("utf-8")
normalS = utf8S.decode("utf-8")
print normalS

def readable_or_empty(text):
    """
     传入参数必须是unicode字符
    尝试将b'\xd7\xeeŒ\xc5\xb5\xc4\xcf\xc2\xc2' 之类的字符串转为正常str
    """
    attr = repr(text.encode('raw_unicode_escape'))
    print(attr)
    temp_text = ""

    if u'\\x' in attr and u'\\\\u' not in attr:
        try:
            temp_text = text.encode('raw_unicode_escape').decode('gb18030')
        except:
            temp_text = ""
    else:
        temp_text = text.encode('raw_unicode_escape').decode('utf-8', 'ignore')
        temp_text = temp_text.encode('utf-8').decode('raw_unicode_escape')
    return temp_text

def CutStringSafe(strIn, length):
    if length > len(strIn):
        return strIn
    else:
        temp_length = length
        result = strIn[0:length]

        for i in range(len(result) - 1, -1, -1):
            if i < len(result) - 8:
                break
            char = result[i]
            if char == '>':
                break
            if char == '<':
                result = result[0:i]
        return result

str_test = "haha<hahahaaaaaaa>dafdsasdf"
print("test:", CutStringSafe(str_test,8))

def only_normal_str(input_str):
    result = ''
    for n in re.findall('[\u4e00-\u9fffa-zA-Z 0-9]+', input_str):
        result += n
    return result

test = 'Swallow'
print(only_normal_str(test))