I Want To Extract A Certain Number Of Words Surrounding A Given Word In A Long String(paragraph) In Python 2.7

I am trying to extract a selected number of words surrounding a given word. I will give example to make it clear: string = 'Education shall be directed to the full development of t

Solution 1:

This will extract all occurrences of the target word in your text, with context:

import re

text = ("Education shall be directed to the full development of the human personality ""and to the strengthening of respect for human rights and fundamental freedoms.")

def search(target, text, context=6):
    # It's easier to use re.findall to split the string, 
    # as we get rid of the punctuation
    words = re.findall(r'\w+', text)

    matches = (i for (i,w) inenumerate(words) if w.lower() == target)
    forindexin matches:
        if index < context //2:yield words[0:context+1]
        elif index > len(words) - context//2 - 1:yield words[-(context+1):]
        else:
            yield words[index - context//2:index + context//2 + 1]print(list(search('the', text)))
# [['be', 'directed', 'to', 'the', 'full', 'development', 'of'], 
#  ['full', 'development', 'of', 'the', 'human', 'personality', 'and'], 
#  ['personality', 'and', 'to', 'the', 'strengthening', 'of', 'respect']]

print(list(search('shall', text)))
# [['Education', 'shall', 'be', 'directed', 'to', 'the', 'full']]

print(list(search('freedoms', text)))
# [['respect', 'for', 'human', 'rights', 'and', 'fundamental', 'freedoms']]

Solution 2:

Tricky with potential for off-by-one errors but I think this meets your spec. I have left removal of punctuation, probably best to remove it before sending the string for analysis. I assumed case was not important.

test_str = "Education shall be directed to the full development of the human personality and to the strengthening of respect for human rights and fundamental freedoms."

def get_surrounding_words(search_word, s, n_words):
    words = s.lower().split(' ')
    try:
        i = words.index(search_word)
    except ValueError:
        return []
    # Word is near startif i < n_words/2:
        words.pop(i)
        return words[:n_words]
    # Word is near endelif i >= len(words) - n_words/2:
        words.pop(i)
        return words[-n_words:]
    # Word is in middleelse:
        words.pop(i)
        return words[i-n_words/2:i+n_words/2]

def test(word):
    print('{}: {}'.format(word, get_surrounding_words(word, test_str, 6)))

test('notfound')
test('development')
test('shall')
test('education')
test('fundamental')
test('for')
test('freedoms')

Solution 3:

import sys, os

args = sys.argv[1:]
if len(args) !=2:
   os.exit("Use with <string> <query>")
text = args[0]
query = args[1]
words = text.split()
op = []
left=3right=3
try:
    index = words.index(query)
    if index <=left:
        start=0else:
        start= index -left

    if start+left+right+1> len(words):
        start= len(words) -left-right-1
        if start<0:
            start=0

    while len(op) <left+rightandstart< len(words):
        if start!= index:
            op.append(words[start])
        start+=1except ValueError:
    pass
print op

• How do this work?
  1. find the word in the string
  2. See if we can make left+right words from the index the
  3. Take left+right number of words and save them in op
  4. print op

Solution 4:

A simple approach to your problem. First separates all the words and then selects words from left and right.

def custom_search(sentence, word, n):     
    given_string = sentencegiven_word=wordtotal_required=nword_list= given_string.strip().split(" ")
    length_of_words = len(word_list)

    output_list = []
    given_word_position = word_list.index(given_word)
    word_from_left = 0
    word_from_right = 0if given_word_position + 1 > total_required / 2:
        word_from_left = total_required / 2if given_word_position + 1 + (total_required / 2) <= length_of_words:
            word_from_right = total_required / 2else:
            word_from_right = length_of_words - (given_word_position + 1)
            remaining_words = (total_required / 2) - word_from_right
            word_from_left += remaining_words

    else:
        word_from_right = total_required / 2
        word_from_left = given_word_position
        if word_from_left + word_from_right < total_required:
            remaining_words = (total_required / 2) - word_from_left
            word_from_right += remaining_wordsrequired_words= []
    for i in range(given_word_position - word_from_left, word_from_right + 
    given_word_position + 1):
        if i != given_word_position:
            required_words.append(word_list[i])
    returnrequired_wordssentence="Education shall be directed to the full development of the human personality and to the strengthening of respect for human rights and fundamental freedoms."
custom_search(sentence, "shall", 6)

>>[Education, be, directed, to , the , full] 


custom_search(sentence, "development", 6)

>>['to', 'the', 'full', 'of', 'the', 'human'] 

Solution 5:

I don't think regular expressions are necessary here. Assuming the text is well-constructed, just split it up into an array of words, and write a couple if-else statements to make sure it retrieves the necessary amount of surrounding words:

def search(text, word, n):
    # text is the string you are searching# word is the word you are looking for# n is the TOTAL number of words you want surrounding the word

    words    = text.split(" ")  # Create an array of words from the string
    position = words.index(word)   # Find the position of the desired word

    distance_from_end = len(words) - position  # How many words are after the word in the textif position < n // 2 + n % 2:  # If there aren't enough words before...return words[:position], words[position + 1:n + 1]

    elif distance_from_end < n // 2 + n % 2:  # If there aren't enough words after...return words[position - n + distance_from_end:position], words[position + 1:]

    else:  # Otherwise, extract an equal number of words from both sides (take from the right if odd)return words[position - n // 2 - n % 2:position], words[position + 1:position + 1 + n//2]string = "Education shall be directed to the full development of the human personality and to the \
strengthening of respect for human rights and fundamental freedoms."print search(string, "shall", 6)
# >> (['Education'], ['be', 'directed', 'to', 'the', 'full'])print search(string, "human", 5)
# >> (['development', 'of', 'the'], ['personality', 'and'])

In your example you didn't have the target word included in the output, so I kept it out as well. If you'd like the target word included simply combine the two arrays the function returns (join them at position).

Hope this helped!