python - 通过查看某些字符并判断在何处分隔来尝试分隔行

Question

使用 Python 3。

基本上我有一段代码试图查看文本文件并查找小于号。如果它在它后面找到一个大于号，然后是一个大写字母，它就知道这是一个新行的开头，所以它会放置一个 \n。那里。我遇到了“局部变量”错误，但我不知道为什么。它不应该发生，因为我在函数内部使用变量而不使用任何全局变量。奇怪的是，该代码适用于“单独”函数的前三个调用，但不适用于第四个。我唯一的解释是 while (example[x] != "<"):无论出于何种原因，循环在第四次调用“单独”函数时根本没有执行。

example = "Tags for HTML: <!--...--> Defines a comment <!DOCTYPE> Defines the document
type <a> Defines a hyperlink <abbr> Defines an abbreviation or an acronym <acronym> Not
supported in HTML5. Use <abbr> instead. Defines an acronym <address> Defines contact 
information for the author/owner of a document <applet> Not supported in HTML5. Use
<embed> or <object> instead. Defines an embedded applet <area> Defines an area inside
an image-map <article> Defines an article <aside> Defines content aside from the page 
content <audio> Defines sound content <b> Defines bold text"

x = 0
def separate(x, example):
    f=open('format_output.txt','w')

    #looking for the first less than sign
    while (example[x] != "<"):
        x+=1
        #advancing and storing the lineholder so it can enter a newline when done
        lineholder = x

    #looking for the first greater than sign
    while (example[x] != ">"):
        #advancing the cursor
        x+=1

    #checking if the position two characters from the cursor is an uppercase letter
    this = example[x+2:x+3]
    if(this.isupper()):
        #if it is, print "it's upper"
        print("its upper")
        #putting everything before lineholder into a variable
        temp_file_string = example[:lineholder]
        #adding a newline to it
        temp_file_string = temp_file_string + "\r\n"
        #putting everything after linholder into another variable
        rest_of_string = example[lineholder:]
        #writing them combined into the output file
        f.write(temp_file_string + rest_of_string)
        #rewinding the file cursor so the file can be read and printed to the shell 
        f.seek(0)
        f=open('format_output.txt','r')
        example = f.read()
        print("\n\nprinting contents:\n\n" + example)
        f.close
        return (x, example)            
    else:
        #else say 'Isn't Uppper'
        lineholder = x
        print("Isn't Upper")
        return (x , example)

(x, example) = separate(x, example)
(x, example) = separate(x, example)
(x, example) = separate(x, example)
(x, example) = separate(x, example)


print('\n'+str(x))

错误信息指出:

local variable 'lineholder' referenced before assignment

在线:

temp_file_string = example[:lineholder]

我连续四次使用该函数只是为了测试代码。我希望能够简单地循环该函数并自动处理“示例”，在每个标记完成描述后放置一个换行符。

输出应该是:

Tags for HTML: 
<!--...--> Defines a comment 
<!DOCTYPE> Defines the document type 
<a> Defines a hyperlink 
<abbr> Defines an abbreviation or an acronym 
<acronym> Not supported in HTML5. Use <abbr> instead. Defines an acronym 
<address> Defines contact information for the author/owner of a document 
<applet> Not supported in HTML5. Use <embed> or <object> instead. Defines an embedded applet 
<area> Defines an area inside an image-map 
<article> Defines an article 
<aside> Defines content aside from the page content 
<audio> Defines sound content 
<b> Defines bold text

我对 Python 和一般编码还很陌生，所以我知道我的代码非常糟糕和困惑。我知道我在这里做的事情严重错误，所以请纠正我。

Answer 1

问题出现在第一个条件while (example[x] != "<")为 false 并且循环永远不会运行，则 lineholder = x不执行。

所以你应该初始化lineholder = x之前的某个地方。

example = """Tags for HTML: <!--...--> Defines a comment <!DOCTYPE> Defines the document
type <a> Defines a hyperlink <abbr> Defines an abbreviation or an acronym <acronym> Not
supported in HTML5. Use <abbr> instead. Defines an acronym <address> Defines contact 
information for the author/owner of a document <applet> Not supported in HTML5. Use
<embed> or <object> instead. Defines an embedded applet <area> Defines an area inside
an image-map <article> Defines an article <aside> Defines content aside from the page 
content <audio> Defines sound content <b> Defines bold text"""

x = 0
def separate(x, example):
    lineholder = x
    f=open('format_output.txt','w')

    #looking for the first less than sign
    while (example[x] != "<"):
        x+=1
        #advancing and storing the lineholder so it can enter a newline when done
        lineholder = x

    #looking for the first greater than sign
    while (example[x] != ">"):
        #advancing the cursor
        x+=1

    #checking if the position two characters from the cursor is an uppercase letter
    this = example[x+2:x+3]
    if(this.isupper()):
        #if it is, print "it's upper"
        print("its upper")
        #putting everything before lineholder into a variable
        temp_file_string = example[:lineholder]
        #adding a newline to it
        temp_file_string = temp_file_string + "\r\n"
        #putting everything after linholder into another variable
        rest_of_string = example[lineholder:]
        #writing them combined into the output file
        f.write(temp_file_string + rest_of_string)
        #rewinding the file cursor so the file can be read and printed to the shell 
        f.seek(0)
        f=open('format_output.txt','r')
        example = f.read()
        print("\n\nprinting contents:\n\n" + example)
        f.close
        return (x, example)            
    else:
        #else say 'Isn't Uppper'
        lineholder = x
        print("Isn't Upper")
        return (x , example)

(x, example) = separate(x, example)
(x, example) = separate(x, example)
(x, example) = separate(x, example)
(x, example) = separate(x, example)


print('\n'+str(x))