附加列表后为空输出

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文本文件中搜索某个关键字，比如"and"，然后将找到关键字的整行放入一个类型列表 (int,细绳）。 int 应该是行号，上面提到的字符串是整行。

我仍在研究行编号 - 所以目前还没有问题。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。但是我就是不能把它放到输出列表中。

我正在尝试搜索的文本文件：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 character/character 集是令人困惑的。列表和 .append() 的使用看起来是正确的，但或许可以考虑在 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 的回答对全局变量提出了一个很好的观点，尽管没有测试它，但我不相信如果使用 output return 变量而不是全局 output 变量。如果您需要有关全局变量的更多信息，请参阅 this Whosebug post。

Answer 2

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。要在函数内编辑全局变量，必须先使用 global 关键字。

示例：

gVar = 10

def editVar():
    global gVar
    gVar += 5

因此，要在您的函数 find_word() 中编辑变量 output，您必须在为其赋值之前键入 global output。

它应该是这样的：

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

以后除非绝对需要，否则尽量远离全局变量。它们会变得凌乱！

Answer 3

循环 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')

附加列表后为空输出

Empty output after appending a list

python

string

list

output