Question

这个小脚本将关键字写入文件，但在每个关键字之间添加了一个额外的换行符。我怎么让它停下来？即而不是

Apple

Banana

Crayon

我想要

Apple
Banana
Crayon

我试过谷歌搜索＆＃34; listwrite＆＃34;但没有帮助。

我确信这是一件非常简单的事情，但我无法弄清楚。

#!/usr/local/bin/python
###################################################
# nerv3.py
# Goal: Named entity recognition script to pull names/place from text
# called as python nerv3.py text_path_or_file 
#
# Inputs:
# path - text file or directory containing text files
# output - output file name 
# uuid
# Outputs:
# Output file written
# People, Places, Others files
#
###################################################

#gonna need to install AlchemyAPI
import AlchemyAPI
import argparse
import xml.etree.ElementTree as ET
import collections
import codecs
import os
#from IPython import embed 
#=================================================
def listwrite(output_file,thelist):
    for item in thelist:
        item.encode('utf-8')
        output_file.write("%s\n\n" % item)

#=================================================

def main():

    tmpdir = "/tmp/pagekicker"

    #personal api key saved as api_key.txt
    parser = argparse.ArgumentParser()
    parser.add_argument('path', help = "target file or directory for NER")
    parser.add_argument('output', help = "target file for output")
    parser.add_argument('uuid', help = "uuid")
    args = parser.parse_args()

    in_file = args.path
    out_file = args.output
    uuid = args.uuid
    folder = os.path.join(tmpdir, uuid)
    print folder    
    cwd = os.getcwd()
    apikey_location = os.path.join(cwd, "api_key.txt")

    with open(in_file) as f:
        text = f.read()

    alchemyObj = AlchemyAPI.AlchemyAPI()
    alchemyObj.loadAPIKey(apikey_location)

    result = alchemyObj.TextGetRankedNamedEntities(text)

    root = ET.fromstring(result)

    place_list = ['City', 'Continent', 'Country', 'Facility', 'GeographicFeature',\
    'Region', 'StateOrCounty']
    People = {}
    Places = {}
    Other = {}

    for entity in root.getiterator('entity'):
        if entity[0].text == 'Person':
            People[entity[3].text]=[entity[1].text, entity[2].text]
        elif entity[0].text in place_list:
            Places[entity[3].text] = [entity[1].text, entity[2].text]
        else:
            Other[entity[3].text] = [entity[1].text, entity[2].text]

    #print lists ordered by relevance
    Places_s = sorted(Places, key = Places.get, reverse = True)
    People_s = sorted(People, key = People.get, reverse = True)
    Other_s = sorted(Other, key = Other.get, reverse = True)

# here is where things seem to go awry
    with codecs.open(out_file, mode = 'w', encoding='utf-8') as o:
        listwrite(o, People_s)
        listwrite(o, Places_s)
        listwrite(o, Other_s)
    out_file = os.path.join(folder, 'People')
    with codecs.open(out_file, mode= 'w', encoding='utf-8') as o:
          listwrite(o, People_s)
    out_file = os.path.join(folder, 'Places')
        with codecs.open(out_file, mode= 'w', encoding='utf-8') as o:
         listwrite(o, Places_s)
    out_file = os.path.join(folder, 'Other')
    with codecs.open(out_file, mode= 'w', encoding='utf-8') as o:
          listwrite(o, Other_s)
#=================================================
if __name__ == '__main__':
    main()

Answer 1

self.__nodes

在代码中，listwrite被定义为一个函数。对于def listwrite(output_file,thelist): for item in thelist: item.encode('utf-8') output_file.write("%s\n\n" % item)中的每个item，它会写入thelist，后跟两个换行符。要删除额外的行，只需删除其中一个item。

\n

写入文件时删除额外的换行符

1 个答案: