Question

到目前为止，我有以下代码：

import sys
from Tkinter import *
import tkFileDialog
from tkFileDialog import askopenfile # Open dialog box


fen1 = Tk()                              # Create window
fen1.title("Optimisation")               # Window title

menu1 = Menu(fen1)

def open():
    filename = askopenfile(filetypes=[("Text files","*.txt")], mode='r')

filename.seek(0)
    numligne = 0
    line     = []
    ok       = 0
    k        = -1

    while (ok == 0)  &  (k == -1):
    line = filename.readline()
    k    = line.find( "*load" )
    if k == 0 :
        l = filename.readlines()

fen1.mainloop()

我搜索的文本文件格式如下：

*test
1 2 3 4

*load
2 7 200
3 7 150

*stiffness
2 9 8 7

etc..

到目前为止，我设法找到以“* load”开头的行，但我希望将'* load'和'* stiffness'之间的值分配给变量，例如a，b，c。我的问题是，在这个加载部分，可能有几行，我需要每次检测每一行，拆分行中的值并给它们一个名称。如果有人可以请求帮助解释一个循环或类似的东西，只会伎俩，我将非常感激！谢谢！

更新：我遇到的问题是我现在想在同一个文本文件中找到SEVERAL单独的部分。我如何创建一个循环来进一步查找'* geo'和'* house'之间的行，还有'* name'和'* surname'？我试图创建一个完全独立的定义，但希望最小化我使用的代码行...谢谢！代码我一直在使用类似的结构（正如我原来的问题所提供的，感谢mgilson！），因此我想编辑这些类型的代码。

def parse_file(ff):     
    out=[]     
    append=False     
    for line in ff:         
        if(append and line.strip()):
            out.append(line)          
            if(line.startswith('*load')): 
                append=True
            elif(line.startswith('*stiffness')):  
                return [map(int,x.split()) for x in out[:-1] ]

Answer 1

我们假设代码的“块”由标题分隔（例如*header）。在每个块中存储数据的最直观方式是列表列表。例如[ row1, row2, ...]（其中row1=[elem1,elem2,elem3,...]）。然后，您可以将块存储在字典中，以便通过block=dictionary['headername']访问块。

这将执行您想要的操作（此版本未经测试）。

import sys

def convert_type(ss):
    try:
        return int(ss)
    except ValueError:
        try:
            return float(ss)
        except ValueError:
            return ss

def parse_file(ff):
    out={}
    block=None
    for i,line in enumerate(ff):
        #Allow for comments to start with '#'.  We break off anything after a '#'
        #and ignore it.  After that, we 
        data=line.split('#',1)
        line=data[0]  #comments (if in line) are in data[1] ... ignore those.
        line=line.strip() #remove whitespace from front and back of line.
        if(line.startswith('*')):
            #python supports multiple assignment.  
            #e.g. out['header'] is the same object as block.  
            #     changing block also changes out['header']
            block=out[line.strip()[1:]]=[]
        elif (block is not None) and line: #checks to make sure there is an active block and the line wasn't empty.
            #If the file could also have floats, you should use float instead of int
            #We also put the parsing in a try/except block.  If parsing fails (e.g. a
            #element can't be converted to a float, you'll know it and you'll know the
            #line which caused the problem.)
            try:
                #block.append(map(int,line.split()))
                block.append(map(convert_type,line.split()))  
            except Exception:
                sys.stderr.write("Parsing datafile choked on line %d '%s'\n"%(i+1,line.rstrip()))
                raise
    return out

with open('textfile.txt','r') as f:
    data_dict=parse_file(f)

#get information from '*load' block:
info=data_dict['load']
for row in info:
    a,b,c=row
    ##same as:
    #a=row[0]
    #b=row[1]
    #c=row[2]
    ##as long as row only has 3 elements.

    #Do something with that particular row. 
    #(each row in the 'load' block will be visited once in this loop)

#get info from stiffness block:
info=data_dict['stiffness']
for row in info:
    pass #Do something with this particular row.

请注意，如果您确保某个标题下的数据文件中的每一行都具有相同的条目数，您可以将变量info视为一个二维行，其索引为{{ 1}} - 但您也可以按element=info[row_number][column_number]

获取整行

Answer 2

也许是这样的：

line = filename.readline()
if line.find("*load") == 0:
    line = filename.readline()
    while line != "\n" and line != "":
        vars = line.split(" ")

vars只是存储此代码运行后['2', '7', '200']值的示例（因此您需要将它们转换为浮点数或整数）。然后，您可以将这些附加到数组或根据需要重命名它们。

编辑：源自上述的工作计划。

filename = open("fff.txt", 'r')
values = {}

line = filename.readline()
while line:
    while line.find("*") != 0:
        line = filename.readline()

    sectionheader = line.strip()[1:]
    values[sectionheader] = []
    line = filename.readline()
    while line != "\n" and line != "":
        vals = [float(i) for i in line.split(" ")]
        values[sectionheader].append(vals)
        line = filename.readline()

print values

Answer 3

虽然我无法帮助您解决语法问题，但最好使用自我调用。

编写一个检测所需行的函数并存储字节偏移量。接下来，使该函数调用自身以查找下一行（结束操作），同时存储其偏移量并将其与先前保存的值进行比较。

现在您有足够的数据来确定需要更改的字节数。

然而，自我调用函数在使用时非常有效，它们可以提高性能并且易于重用。

在php中，我构建了一个类似于.net中的编写器，它以这种方式工作。因此，我知道这个理论是有效的，但这似乎是蟒蛇。

遗憾的是，我对这种语言知之甚少。祝你的项目好运！

Answer 4

这是我对你的代码所做的：

import sys
from Tkinter import *
import tkFileDialog
from tkFileDialog import askopenfile # Open dialog box


fen1 = Tk()                              # Create window
fen1.title("Optimisation")               # Window title

menu1 = Menu(fen1)

def do_open(interesting_parts=[]):
    thefile = askopenfile(filetypes=[("Text files","*.txt")], mode='r')

    data = {} # Create a dictionary to store all the data stored per part name
    part = None
    for line in thefile:
        if line.startswith("*"):
            # A * in the beginning signals a new "part"
            # And another one means the end.
            part = line[1:] # Remove the * in the beginning via slicing to get the name without it.
            if part in interesting_parts:
                data[part] = [] # Create a list inside the dictionary, so that you can add data to it later.
                # Only do this if we are interested in storing anything for this part
        elif part in interesting_parts:
            # Add an a condition to check if the part name is in the list of "parts" you are interested in having.
            line_data = get_something_from_this(part, line) # just a function that returns something based on the line and the part
            if line_data is not None: # Ignore it if it's None (just an option, as there might be newlines that you want to ignore)
                data[part].append(line_data)

    # Here, we return the dictionary to act on it.
    return data

def get_something_from_this(part, line):
    try:
        ints = [int(p) for p in line.split()]
    except ValueError:
        print "Ignoring Line", repr(line), "in", part
        return None # We don't care about this line!
    else:
        print "in", part, ints
        return ints # Store this line's data

data = do_open(["test", "egg"]) # Pass as an argument a list of the interesting "parts"

print data # this is a dictionary

# How do you access it?
print data["test"] # to get all the lines' data in a list
print data["egg"][0] # to get the first line of the data

for part, datalines in data.iterkeys():
    print part, datalines # datalines is the list of all the data, part is the dictionary's key which is the part name
    # Remember data[part] = ... <- Here part is the key.

fen1.mainloop()

当变量filename不是“文件名”而是“文件”时，不要将其命名。
您可以使用for循环逐行循环。
使用拆分拆分字符串
使用startswith来了解字符串是否以另一个字符串开头
跟踪您是否在变量的“* load”部分。

<强>更新：不要使用open作为函数名，它已经在python的内置函数中了。另外，为了避免解析*load和*stiffness行，我修改了一些代码：每行的解析都是在elif语句中完成的。

更新2 ：

根据OP的需要更新代码。使用此文件进行测试：

*test
1 2 3

*load
2 7 200
3 7 150

*stiffness
2 9 8

*egg
1 2 3
2 4 6

*plant
23 45 78

更新3 ：重评：）

Answer 5

这样的事情应该做

data=[]
check=false
for i in fid:
    if line.find("*load"):
        check=true
    if check==true and not line.find("*stiffness"):
        line=split(i)
        data.append(map(lambda x: float(x), line))
    if line.find("*stiffness"):
        break

fid.close()
for i in data:
    a=i[0]
    b=i[1]
    c=i[2]

将此作为代码作为粗略的建议...（我认为异常现在已经修复，如果不是我也不在乎......）

在文本中查找某个代码块

5 个答案: