Python 类型错误 : 'str' object is not callable when calling type function

Question

我正在尝试根据由关键字分隔的标题将一堵文本墙拆分为文本 block 和文本列表。我认为最好的方法是递归。不幸的是，我在尝试检查给定变量的类型时遇到以下错误 *** TypeError: 'str' object is not callable。当我直接调用 type(var) 时，我在 PDB 中遇到了同样的错误。这似乎没有意义，所以我担心这是我没有看到的东西。

我认为这是代码的相关部分。如果您觉得需要查看更多内容，请告诉我

def separate(text,boundary = None):
    pdb.set_trace()
    if boundary == None:
        m = re.findall(r'(?<=boundary=).*',text)
        i = 0
        textList = [text]
        while i < len(m): #have all levels of Boundary/headers named
            boundary = m[i]
            textList = recursiveSplit(textList,boundary)
            i += 1

    return textList

def recursiveSplit(chunk,boundary):
    if type(chunk) is types.ListType: #error occurs here
        for object in chunk:
            recursiveSplit(object,boundary)
    if type(chunk) is types.StringType:
        list = re.split(r'(?P<boundary>)(?!--)',chunk)
        return list
    return None

完整代码。需要一个文本文件。您可以使用任何 MIME 电子邮件。我还将上传我用于测试的电子邮件

    #Textbasics email parser
#based on a "show original" file converted into text

from sys import argv
import re, os, pdb, types

script, filename = argv
text = open(filename).read()
type = "text only" #Set the default type of email

#cut the email up by sections
#--A section is defined as any time there are two line breaks in a row
textList = re.split(r"\n\n", text)
header = textList[0]
if re.search(r'MIME-Version',header):
    type = "MIME"

# If mail has no attachments, parse as a text-only email
class Parser(object):

    def __init__(self,textList):
        a = 1
        self.body = ""
        self.textList = textList
        self.header = textList[0]
        while a < len(textList):
            self.body = self.body + textList[a] + '\n\n'
            a += 1

        m = re.search(r'(?<=Subject: ).*', self.header)
        self.subject = m.group(0)

        m = re.search(r'(?<=From: ).*', self.header)
        self.fromVar = m.group(0)

        m = re.search(r'(?<=To: ).*', self.header)
        self.toVar = m.group(0)

        m = re.search(r'(?<=Date: )\w+\s\w+\s\w+', self.header)
        self.date = m.group(0)

    def returnParsed(self,descriptor = "all"):
        if descriptor == "all":
            retv = "Subject: " + self.subject + "\n" + "From: " + self.fromVar + "\n" + "To: " + self.toVar + "\n" + "Date: " + self.date + "\n" + "\n" + self.body
            return retv

        if descriptor == "subject":
            return self.subject
        if descriptor == "fromVar":
            return self.fromVar
        if descriptor == "toVar":
            return self.toVar
        if descriptor == "date":
            return self.date
        if descriptor == "body":
            return self.body

class MIMEParser(Parser):

    class MIMEDataDecoder(object):
        def __init__(self,decodeString,type):
            pass    


    def __init__(self,textList):
        self.textList = textList
        self.nestedItems = []
        newItem = NestedItem(self)
        newItem.setContentType("Header")
        newItem.setValue(self.textList[0])
        self.nestedItems.append(newItem)
        if re.search(r'(boundary=)',newItem.value):
            helperItem = NestedItem(self)
            helperItem.value = (self.textList[0])
            m = re.search(r'(?<=Content-Type: ).+(?=;)',newItem.value)
            helperItem.setContentType(m.group(0))
            self.nestedItems.append(helperItem)

        self.organizeData()   
        """i = 0
        while i < len(self.textList):
            newItem = NestedItem(self)
            ct = self.nextContentType
            newItem.setContentType(ct)
            newItem.setValue(self.textList[i])
            self.nestedItems.append(newItem)
            m = re.search(r'(?<=Content-Type: ).+(?=;)',self.textList[i])
            if m:
                self.nextContentType = m.group(0)
            i += 1
            """

    def nestItem (self,item):
        self.nestedItems.append(item)

    def organizeData(self):
        self.nestLevel = 1
        self.currentSuper = self
        m = re.search(r'(?<=boundary=).*',self.textList[0])
        self.currentBoundary = m.group(0)
        self.currentList = self.textList
        self.currentList.remove(self.textList[0])
        self.formerObjectDatabase = {}
        pdb.set_trace()
        while self.nestLevel > 0:
            i = 0
            while i < len(self.currentList):

                boundary = self.currentBoundary
                #If block is a "normal block", containing a current boundary identifier
                p = re.search(r'--(?P<boundary>)(?!--)', text)
                if p:
                    newItem = NestedItem(self.currentSuper)
                    newItem.setValue(self.currentList[i])
                    r = re.search(r'(?<=Content-Type: ).+(?=;)',newItem.value)
                    if r:
                        newItem.setContentType(r.group(0))
                    self.currentObject = newItem
                    self.currentSuper.nestItem(self.currentObject)
                #If the block contains a new block boundary
                m = re.search(r'(?<=boundary=).*',self.currentList[i])
                if m:
                    #begin new layer of recursive commands
                    newFormerObject = self.FormerCurrentObject(self.currentList,self.currentSuper,self.currentBoundary)
                    self.formerObjectDatabase[self.nestLevel] = newFormerObject
                    self.currentSuper = self.currentObject
                    self.nestLevel += 1
                    self.currentBoundary = m.group(0)
                    boundary = self.currentBoundary
                    #self.currentList = re.split(r'--(?P<boundary>)(?!--)', self.currentList[i])
                boundary = self.currentBoundary
                #If block contains an "end of boundary" marker
                q = re.search(r'(?P<boundary>)--', text)
                if q:
                    self.nestLevel -= 1
                    currentObject = self.formerObjectDatabase[self.nestLevel]
                    self.currentList = currentObject.formerList
                    self.currentSuper = currentObject.formerSuper
                    self.currentBoundary = currentObject.formerBoundary
                i += 1                    


    class FormerCurrentObject:
        def __init__(self,formerList,formerSuper,formerBoundary):
            self.formerList = formerList
            self.formerSuper = formerSuper
            self.formerBoundary = formerBoundary




    def printAll(self):
        print "printing all: %d" % len(self.nestedItems)
        i = 0
        while i < len(self.nestedItems):
            print "printing out item %d" % i
            self.nestedItems[i].printOut()
            i += 1

class NestedItem(object):
    def __init__(self,superObject,contentType=" ",value = " "):
        self.superObject = superObject
        self.contentType = contentType
        self.value = value
        self.nestedItems = []

    def nestItem(self,item):
        self.nestedItems.append(item)

    def printOut(self,printBuffer = ""):
        print printBuffer + '++%s' % self.contentType
        print printBuffer + self.value
        a = 0
        printBuffer = printBuffer + "  "
        while a < len(self.nestedItems):
            self.nestedItems[a].printOut(printBuffer)

    def setContentType(self,contentType):
        self.contentType = contentType

    def setValue(self,value):
        self.value = value



if type == "text only":
    p = Parser(textList)
    print p.returnParsed()

def separate(text,boundary = None):
    pdb.set_trace()
    if boundary == None:
        m = re.findall(r'(?<=boundary=).*',text)
        i = 0
        textList = [text]
        while i < len(m): #have all levels of Boundary/headers named
            boundary = m[i]
            textList = recursiveSplit(textList,boundary)
            i += 1

    return textList

def recursiveSplit(chunk,boundary):
    if type(chunk) is types.ListType: #<<--error occurs here
        for obj in chunk:
            recursiveSplit(obj,boundary)
    if type(chunk) is types.StringType:
        list = re.split(r'(?P<boundary>)(?!--)',chunk)
        return list
    return None


if type == "MIME":
    #separate the text file instead by its boundary identifier
    p = MIMEParser(separate(text))
    p.printAll()

Answer 1

您正在分配一个字符串以键入:

type = "text only"

然后调用它

if type(chunk)...

引发异常:

*** TypeError: 'str' object is not callable