我试图运行下面的代码来清理txt文件中的一组推文
我也在命令行中定义了参数,但似乎没有输出
知道我可能做错了吗?
以下是代码:
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:USAID为人道主义合作伙伴(不是GOH)提供400,000美元的初步援助,以迅速提供重要的救济。 \ U2026""截断":假,"实体" {"#标签":[],"符号":[] ," user_mentions":[{" screen_name":" Jacquiecharles"," name":" Jacqueline Charles",& #34; ID":15360434," ID_STR":" 15360434""指数":[3,18]}],"网址& #34;:[]},"元数据" {" iso_language_code":"恩"" result_type的":"最近& #34;},"来源":" Twitter for iPhone< \ / a>"," in_reply_to_status_id":null," in_reply_to_status_id_str" :空," in_reply_to_user_id":空," in_reply_to_user_id_str":空," in_reply_to_screen_name":空,"使用者" {&#3 4; id":635031678," id_str":" 635031678"," name":" Tracie Hamilton"," screen_name":" TracieHamilton8"," location":""," description":" Leaning&每天取决于他"," url":null," entity":{" description":{" urls":[] }},"保护":假," FOLLOWERS_COUNT":1929," FRIENDS_COUNT":715," listed_count":63,#34& ; created_at":" Fri Jul 13 23:39:46 +0000 2012"," favourites_count":27603," utc_offset":null,&#34 ;的time_zone":空," geo_enabled":真,"验证":假," statuses_count":17433"朗&#34 ;: "恩"" contributors_enabled":假," is_translator":假," is_translation_enabled":假," profile_background_color" :" C0DEED"" profile_background_image_url":" HTTP:\ / \ / abs.twimg.com \ /图像\ /主题\ / THEME1 \ /bg.png" ;," profile_background_image_url_https":" HTTPS:\ / \ / abs.twimg.com \ /图像\ /主题\ / THEME1 \ /bg.png"," profile_background_tile&# 34;:假," profile_image_url":" HTTP:\ / \ / pbs.twimg.com \ / profile_images \ / 575645183288610817 \ / 5vJNgPld_norm al.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&#34 ;, " profile_text_color":" 333333"" profile_use_background_image":真," has_extended_profile":假," DEFAULT_PROFILE":真" default_profile_image":假,"以下":假," follow_request_sent":假,"通知":假}"地理":空,"坐标":空,"地方":空,"贡献者":空," retweeted_status":{ " created_at":" Tue Oct 04 01:27:02 +0000 2016"," id":783116185726357504," id_str":&# 34; 783116185726357504"
=============================================== =========================
答案 0 :(得分:3)
这是一个完全正常的版本:
#!/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)
您可以通过以下方式调用它:
python clean.py inputDirectory outputFileName
答案 1 :(得分:1)
您的代码存在一些问题:
您正在传递文件名,但是尝试根据该文件名遍历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,我得到了正确的输出:
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