python 正则表达式错误：TypeError：预期的字符串或类似字节的对象

Question

我有以下代码。

import datetime
import re


class Entry:
    task_name = None
    minutes = None
    notes = None
    created_at = None

    def __init__(self, task_name=None, minutes=None,
                 created_at=None, notes=None):
        if task_name:
            self.task_name = task_name
            self.minutes = int(minutes)
            self.created_at = datetime.datetime.strptime(
                                                    created_at,
                                                    "%Y-%m-%d %H:%M:%S.%f")
            self.notes = notes
        else:
            self.get_task_details()

    # get task name, num of minutes and notes if required
    def get_task_details(self):
        self.task_name = input("Enter the name of the task: ")
        self.minutes = self.get_minutes()
        self.notes = self.get_notes()
        self.created_at = datetime.datetime.now()

    # get num of minutes and verify it
    # the user should enter a valid input
    def get_minutes(self):
        while True:
            minutes = input("Enter the number of minutes spent on the task: ")
            if minutes:
                try:
                    minutes = int(minutes)
                    return minutes
                except ValueError:
                    print("Please Enter a valid num of minutes")
            else:
                print("Please enter a valid input. ex 12")

    # print task info
    def get_task_info(self):
        print("You created your task at")
        created_at_formatted = self.created_at.strftime("%m/%d/%Y %H:%M")
        print("{}".format(created_at_formatted))

    # get notes if the user wants to
    # else: leave it with a value of None
    def get_notes(self):
        answer = input("Do you want to write any note on this task ? N/y >>> ")
        if answer.lower() == "y":
            note = input("Enter your note >>> ")
            return note
        else:
            self.notes = None
            print("Alright. No notes are added")

    def __str__(self):
        return """
        Task Name: {}
        Created At: {}
        Minutes Spend: {}
        Notes: {}
        """.format(self.task_name, self.created_at, self.minutes, self.notes)

class Log:
    e = Entry()
    entries = []
    entries.append(e)

    def find_by_pattern(self):
        """find by regex pattern"""
        regex = input("Enter your regex >>> ")
        try:
            regex = re.compile(r'{}'.format(regex), re.X)
        except sre_constants.error:
            print("Invalid regex")
            regex = None
        entries_found = []
        # check if the user entered a regex
        if regex:
            for entry in self.entries:
                if (re.findall(regex, entry.task_name) or
                        re.findall(regex, entry.notes)):
                        entries_found.append(entry)
        else:
            print("Please enter a  valid regex")

        if entries_found:
            if entries_found:
                print("We found the following entries")
                for entry in entries_found:
                    print("{}".format(entry))
        else:
            print("No entries were found based on your pattern")

if __name__ == "__main__":
    l = Log()
    l.find_by_pattern()

当我运行程序并输入正则表达式时：'\w{4}';它崩溃了 但是，如果我运行程序并输入相同的正则表达式但不带引号：\w{r}，它不会崩溃。 这是我正在尝试做的更清晰的图片：

Answer 1

这不是因为正则表达式而崩溃，而是因为entry.notes 是None 而findall 需要一个字符串。

它在第一个示例中有效，因为正则表达式匹配 entry.task_name，因此条件行 88-89 的其他部分被跳过。
但是，当输入引号时，正则表达式与第一部分不匹配（它需要引号）并在后者为 None 时崩溃。

您可以通过输入注释来验证这一点，它不会崩溃，尽管将这些属性初始化为空字符串可能更明智。

PS：请注意，在get_notes 中，如果有任何注释，您将返回该注释，但在其他情况下，您可能希望返回实际值（或者当函数返回并在第 27 行设置 None 时该值将被删除） )

这是一个快速/修复不佳的版本：

import datetime
import re


class Entry:
    task_name = ""
    minutes = None
    notes = ""
    created_at = None

    def __init__(self, task_name=None, minutes=None,
                 created_at=None, notes=""):
        if task_name:
            self.task_name = task_name
            self.minutes = int(minutes)
            self.created_at = datetime.datetime.strptime(
                                                    created_at,
                                                    "%Y-%m-%d %H:%M:%S.%f")
            self.notes = notes
        else:
            self.get_task_details()

    # get task name, num of minutes and notes if required
    def get_task_details(self):
        self.task_name = input("Enter the name of the task: ")
        self.minutes = self.get_minutes()
        self.notes = self.get_notes()
        self.created_at = datetime.datetime.now()

    # get num of minutes and verify it
    # the user should enter a valid input
    def get_minutes(self):
        while True:
            minutes = input("Enter the number of minutes spent on the task: ")
            if minutes:
                try:
                    minutes = int(minutes)
                    return minutes
                except ValueError:
                    print("Please Enter a valid num of minutes")
            else:
                print("Please enter a valid input. ex 12")

    # print task info
    def get_task_info(self):
        print("You created your task at")
        created_at_formatted = self.created_at.strftime("%m/%d/%Y %H:%M")
        print("{}".format(created_at_formatted))

    # get notes if the user wants to
    # else: leave it with a value of None
    def get_notes(self):
        answer = input("Do you want to write any note on this task ? N/y >>> ")
        if answer.lower() == "y":
            note = input("Enter your note >>> ")
            return note
        else:
            return ""
            print("Alright. No notes are added")

    def __str__(self):
        return """
        Task Name: {}
        Created At: {}
        Minutes Spend: {}
        Notes: {}
        """.format(self.task_name, self.created_at, self.minutes, self.notes)

class Log:
    e = Entry()
    entries = []
    entries.append(e)

    def find_by_pattern(self):
        """find by regex pattern"""
        regex = input("Enter your regex >>> ")
        try:
            regex = re.compile(r'{}'.format(regex), re.X)
        except sre_constants.error:
            print("Invalid regex")
            regex = None
        entries_found = []
        # check if the user entered a regex
        if regex:
            for entry in self.entries:
                if (re.findall(regex, entry.task_name) or
                        re.findall(regex, entry.notes)):
                        entries_found.append(entry)
        else:
            print("Please enter a  valid regex")

        if entries_found:
            if entries_found:
                print("We found the following entries")
                for entry in entries_found:
                    print("{}".format(entry))
        else:
            print("No entries were found based on your pattern")

if __name__ == "__main__":
    l = Log()
    l.find_by_pattern()

Answer 2

根据错误：

expected string or bytes-like object

您只需要使用 str() 将后面的部分作为字符串类型的数据传输：

if (re.findall(regex, str(entry.task_name)) or
                        re.findall(regex, str(entry.notes))):
                        entries_found.append(entry)

或者你可以尝试在findall函数的第二个参数前面加上b'xxx'。不是变量，是原始字符串。