附加列表后的空输出

Question

r = ","
x = ""
output = list()
import string

def find_word(filepath,keyword):
    doc = open(filepath, 'r')

    for line in doc:
        #Remove all the unneccessary characters
        line = line.replace("'", r)
        line = line.replace('`', r)
        line = line.replace('[', r)
        line = line.replace(']', r)
        line = line.replace('{', r)
        line = line.replace('}', r)
        line = line.replace('(', r)
        line = line.replace(')', r)
        line = line.replace(':', r)
        line = line.replace('.', r)
        line = line.replace('!', r)
        line = line.replace('?', r)
        line = line.replace('"', r)
        line = line.replace(';', r)
        line = line.replace(' ', r)
        line = line.replace(',,', r)
        line = line.replace(',,,', r)
        line = line.replace(',,,,', r)
        line = line.replace(',,,,,', r)
        line = line.replace(',,,,,,', r)
        line = line.replace(',,,,,,,', r)
        line = line.replace('#', r)
        line = line.replace('*', r)
        line = line.replace('**', r)
        line = line.replace('***', r)

        #Make the line lowercase
        line = line.lower()

        #Split the line after every r (comma) and name the result "word"
        words = line.split(r)

        #if the keyword (also in lowercase form) appears in the before created words list
        #then append the list output by the whole line in which the keyword appears

        if keyword.lower() in words:
            output.append(line)

    return output

print find_word("pg844.txt","and")

这段代码的目标是在一个文本文件中搜索某个关键字，比如“and”，然后将找到该关键字的整行放入一个类型为 (int,string) 的列表中。 int 应该是行号，字符串是上面提到的其余整行。

我仍在处理行号问题 - 所以对此没有任何疑问。但问题是：输出为空。即使我附加一个随机字符串而不是行，我也没有得到任何结果。

如果我使用

if keyword.lower() in words:
        print line

我得到了所有需要的行，其中出现了关键字。但我就是无法将它放入输出列表中。

我试图搜索的文本文件：http://www.gutenberg.org/cache/epub/844/pg844.txt

Answer 1

请使用正则表达式。请参阅Regex in Python 的一些文档。替换每个字符/字符集是令人困惑的。列表和 .append() 的使用看起来是正确的，但也许可以考虑在 for 循环中调试您的 line 变量，偶尔打印它以确保它的值是您想要的。

pyInProgress 的回答很好地说明了全局变量，尽管没有对其进行测试，如果使用 output 返回变量而不是全局 output 变量，我不相信它是必需的。如果您需要有关全局变量的更多信息，请参阅this StackOverflow post。

Answer 2

遍历string.punctuation 以在遍历行之前删除所有内容

import string, re

r = ','

def find_word(filepath, keyword):

    output = []
    with open(filepath, 'rb') as f:
        data = f.read()
        for x in list(string.punctuation):
            if x != r:
                data = data.replace(x, '')
        data = re.sub(r',{2,}', r, data, re.M).splitlines()

    for i, line in enumerate(data):
        if keyword.lower() in line.lower().split(r):
            output.append((i, line))
    return output

print find_word('pg844.txt', 'and')

Answer 3

由于output = list() 位于代码的顶层并且不在函数内部，因此它被视为全局变量。 要在函数中编辑全局变量，必须首先使用 global 关键字。

例子：

gVar = 10

def editVar():
    global gVar
    gVar += 5

因此，要在函数find_word() 中编辑变量output，您必须在为其赋值之前输入global output。

应该是这样的：

r = ","
x = ""
output = list()
import string

def find_word(filepath,keyword):
    doc = open(filepath, 'r')

    for line in doc:
        #Remove all the unneccessary characters
        line = line.replace("'", r)
        line = line.replace('`', r)
        line = line.replace('[', r)
        line = line.replace(']', r)
        line = line.replace('{', r)
        line = line.replace('}', r)
        line = line.replace('(', r)
        line = line.replace(')', r)
        line = line.replace(':', r)
        line = line.replace('.', r)
        line = line.replace('!', r)
        line = line.replace('?', r)
        line = line.replace('"', r)
        line = line.replace(';', r)
        line = line.replace(' ', r)
        line = line.replace(',,', r)
        line = line.replace(',,,', r)
        line = line.replace(',,,,', r)
        line = line.replace(',,,,,', r)
        line = line.replace(',,,,,,', r)
        line = line.replace(',,,,,,,', r)
        line = line.replace('#', r)
        line = line.replace('*', r)
        line = line.replace('**', r)
        line = line.replace('***', r)

        #Make the line lowercase
        line = line.lower()

        #Split the line after every r (comma) and name the result "word"
        words = line.split(r)

        #if the keyword (also in lowercase form) appears in the before created words list
        #then append the list output by the whole line in which the keyword appears

        global output
        if keyword.lower() in words:
            output.append(line)

    return output

以后尽量远离全局变量，除非你绝对需要它们。他们可能会变得一团糟！