清理推文，什么都不显示

Question

我正在尝试运行下面的代码来清理 txt 文件中的一组推文

我也在命令行上定义了参数，但似乎没有输出任何内容

知道我做错了什么吗？

下面是代码：

代码：

#!/usr/bin/python
# -*- coding: utf-8 -*-

import sys
import os
import re
import string
from nltk.corpus import stopwords
from nltk import word_tokenize
from nltk import pos_tag


def clean(path, filename):

    # print("Cleaning "+path)

    filename = CLEANED_DATA + filename.strip()
    WRITE_HANDLER = open(filename, 'wb')
    tweets = dict()
    for line in open('/Users/Mustafa/Desktop/nexalogy/project3.txt',
                 'rb'):
        line = re.sub(r'[.,"!]+', '', line, flags=re.MULTILINE)  # removes the characters specified
        line = re.sub(r'^RT[\s]+', '', line, flags=re.MULTILINE)  # removes RT
        line = re.sub(r'https?:\/\/.*[\r\n]*', '', line,
                  flags=re.MULTILINE)  # remove link
        line = re.sub(r'[:]+', '', line, flags=re.MULTILINE)
        line = filter(lambda x: x in string.printable, line)  # filter non-ascii characers

        new_line = ''
        for i in line.split():  # remove @ and #words, punctuataion
            if not i.startswith('@') and not i.startswith('#') and i \
                not in string.punctuation:
                new_line += i + ' '
        line = new_line

        # # Do sentence correction

        if new_line in tweets:
            continue
        else:
            tweets[new_line] = 1
        if len(new_line.strip()) > 0:
           WRITE_HANDLER.write(new_line + '''

''')
    return filename


DATA_FOLDER = sys.argv[1]
CLEANED_DATA = sys.argv[2]
for (root, dirs, files) in os.walk(DATA_FOLDER):  # gets all the files from 
subfolders recrsively
    for name in files:
        absolute_path = os.path.join(root, name)
        if os.path.isfile(absolute_path) and name != '.DS_Store':
        filename = clean(absolute_path, name)

文件：Project3.txt

{"created_at":"Tue Oct 04 17:16:30 +0000 2016","id":783355126945722368,"id_str":"783355126945722368","text":"RT @Jacquiecharles：美国国际开发署提供为人道主义合作伙伴（非 GOH）提供 400,000 美元的初始援助，以迅速提供关键救济。\u2026","truncated":false,"entities":{"hashtags":[],"symbols":[],"user_mentions": [{"screen_name":"Jacquiecharles","name":"Jacqueline Charles","id":15360434,"id_str":"15360434","indices":[3,18]}],"urls":[ ]},"metadata":{"iso_language_code":"en","re​​sult_type":"recent"},"source":"Twitter for iPhone","in_reply_to_status_id":null,"in_reply_to_status_id_str": null,"in_reply_to_user_id":null,"in_reply_to_user_id_str":null,"in_reply_to_screen_name":null,"user":{"id":635031678,"id_str":"635031678","name":"Tracie Hamilton","screen_name ":"TracieHamilton8","location":"","description":"每天依靠他","url":null,"entities":{"description":{"urls":[]}} ,"受保护":false,"followers_count":1929,"friends_count":715,"listed_cou nt":63,"created_at":"Fri Jul 13 23:39:46 +0000 2012","favourites_count":27603,"utc_offset":null,"time_zone":null,"geo_enabled":true,"verified" :false,"statuses_count":17433,"lang":"en","contributors_enabled":false,"is_translator":false,"is_translation_enabled":false,"profile_background_color":"C0DEED","profile_background_image_url":"http: \/\/abs.twimg.com\/images\/themes\/theme1\/bg.png","profile_background_image_url_https":"https:\/\/abs.twimg.com\/images\/themes\/theme1 \/bg.png","profile_background_tile":false,"profile_image_url":"http:\/\/pbs.twimg.com\/profile_images\/575645183288610817\/5vJNgPld_normal.jpeg","profile_image_url_https":"https:\ //pbs.twimg.com\/profile_images\/575645183288610817\/5vJNgPld_normal.jpeg","profile_link_color":"0084B4","profile_sidebar_border_color":"C0DEED","profile_sidebar_fill_color":"DDEEF6","profile_text_color":" 333333","profile_use_background_image":true,"has_extended_profile":false,"default_profile":true,"default_profile_image":false,"following":fa lse,"follow_request_sent":false,"notifications":false},"geo":null,"coordinates":null,"place":null,"contributors":null,"retweeted_status":{"created_at":"Tue 10 月 4 日 01:27:02 +0000 2016","id":783116185726357504,"id_str":"783116185726357504"

================================================ ==========================

Answer 1

这是一个完整的版本：

#!/usr/bin/python
# -*- coding: utf-8 -*-

import sys
import os
import re
import string

def clean(inputDir, outputFile):

    # print("Cleaning "+path)

    WRITE_HANDLER = open(outputFile, 'wb')
    tweets = dict()
    for line in open(inputDir + './project3.json','rb'):
        # print "Before" + line
        line = re.sub(r'[.,"!]+', '', line, flags=re.MULTILINE)  # removes the characters specified
        line = re.sub(r'^RT[\s]+', '', line, flags=re.MULTILINE)  # removes RT
        line = re.sub(r'https?:\/\/.*[\r\n]*', '', line, flags=re.MULTILINE)  # remove link
        line = re.sub(r'[:]+', '', line, flags=re.MULTILINE)
        line = filter(lambda x: x in string.printable, line)  # filter non-ascii characers

        new_line = ''
        for i in line.split():  # remove @ and #words, punctuataion
            if not i.startswith('@') and not i.startswith('#') and i not in string.punctuation:
                new_line += i + ' '
        line = new_line

        # # Do sentence correction

        if new_line in tweets:
            continue
        else:
            tweets[new_line] = 1
        if len(new_line.strip()) > 0:
            #print  "Writing new line"
            WRITE_HANDLER.write(new_line + '''''')
    return outputFile


DATA_FOLDER = sys.argv[1]
CLEANED_DATA = sys.argv[2]
clean(DATA_FOLDER, CLEANED_DATA)

您通过以下方式调用它：

python clean.py inputDirectory outputFileName

Answer 2

您的代码有几个问题：

1. 您在“for line in open”语句中对输入文件进行硬编码
2. 您的输出文件名不是 clean.txt。它将是 clean.txt，clean.txt...将为您目录中的每个文件创建一个
3. 有一些奇怪的缩进
4. 您发布的 JSON 都在一行中，因此被删除标点符号的语句删除了

5. 您正在传递一个文件名，但试图根据该文件名遍历 os 文件系统。你应该通过：

   python clean.py DIR_NAME CLEAN_FILE

修复缩进并美化 JSON 后，我得到正确的输出：

def clean(path, filename):

    # print("Cleaning "+path)

    filename = CLEANED_DATA + filename.strip()
    print filename
    WRITE_HANDLER = open(filename, 'wb')
    tweets = dict()
    for line in open('./project3.json','rb'):
        # print "Before" + line
        line = re.sub(r'[.,"!]+', '', line, flags=re.MULTILINE)  # removes the characters specified
        line = re.sub(r'^RT[\s]+', '', line, flags=re.MULTILINE)  # removes RT
        line = re.sub(r'https?:\/\/.*[\r\n]*', '', line, flags=re.MULTILINE)  # remove link
        line = re.sub(r'[:]+', '', line, flags=re.MULTILINE)
        line = filter(lambda x: x in string.printable, line)  # filter non-ascii characers

        new_line = ''
        for i in line.split():  # remove @ and #words, punctuataion
            if not i.startswith('@') and not i.startswith('#') and i not in string.punctuation:
                new_line += i + ' '
        line = new_line

        # # Do sentence correction

        if new_line in tweets:
            continue
        else:
            tweets[new_line] = 1
        if len(new_line.strip()) > 0:
            #print  "Writing new line"
            WRITE_HANDLER.write(new_line + '''''')
    return filename