在python中查找字符串中多次出现的字符串

re.finditer

>>> import re
>>> text = 'Allowed Hello Hollow'
>>> for m in re.finditer('ll', text):
         print('ll found', m.start(), m.end())

ll found 1 3
ll found 10 12
ll found 16 18

str.find

>>> text = 'Allowed Hello Hollow'
>>> index = 0
>>> while index < len(text):
        index = text.find('ll', index)
        if index == -1:
            break
        print('ll found at', index)
        index += 2 # +2 because len('ll') == 2

ll found at  1
ll found at  10
ll found at  16

string.count

"Allowed Hello Hollow".count('ll')
>>> 3

>>> l = ['ll', 'xx', 'll']
>>> print [n for (n, e) in enumerate(l) if e == 'll']
[0, 2]

>>> text = "Allowed Hello Hollow"
>>> print [n for n in xrange(len(text)) if text.find('ll', n) == n]
[1, 10, 16]

>>> text = 'Alllowed Hello Holllow'
>>> print [n for n in xrange(len(text)) if text.find('ll', n) == n]
[1, 2, 11, 17, 18]

poke's solution

str.index ValueError

def findall(sub, string):
    """
    >>> text = "Allowed Hello Hollow"
    >>> tuple(findall('ll', text))
    (1, 10, 16)
    """
    index = 0 - len(sub)
    try:
        while True:
            index = string.index(sub, index + len(sub))
            yield index
    except ValueError:
        pass

str.find -1 iter

def findall_iter(sub, string):
    """
    >>> text = "Allowed Hello Hollow"
    >>> tuple(findall_iter('ll', text))
    (1, 10, 16)
    """
    def next_index(length):
        index = 0 - length
        while True:
            index = string.find(sub, index + length)
            yield index
    return iter(next_index(len(sub)).next, -1)

def findall_each(findall, sub, strings):
    """
    >>> texts = ("fail", "dolly the llama", "Hello", "Hollow", "not ok")
    >>> list(findall_each(findall, 'll', texts))
    [(), (2, 10), (2,), (2,), ()]
    >>> texts = ("parallellized", "illegally", "dillydallying", "hillbillies")
    >>> list(findall_each(findall_iter, 'll', texts))
    [(4, 7), (1, 6), (2, 7), (2, 6)]
    """
    return (tuple(findall(sub, string)) for string in strings)

In [1]: x = ['ll','ok','ll']

In [2]: for idx, value in enumerate(x):
   ...:     if value == 'll':
   ...:         print idx, value       
0 ll
2 ll

In [3]: x = ['Allowed','Hello','World','Hollow']

In [4]: for idx, value in enumerate(x):
   ...:     if 'll' in value:
   ...:         print idx, value
   ...:         
   ...:         
0 Allowed
1 Hello
3 Hollow

>>> for n,c in enumerate(text):
...   try:
...     if c+text[n+1] == "ll": print n
...   except: pass
...
1
10
16

needle = input()
haystack = input()
counter = 0
n=-1
for i in range (n+1,len(haystack)+1):
   for j in range(n+1,len(haystack)+1):
      n=-1
      if needle != haystack[i:j]:
         n = n+1
         continue
      if needle == haystack[i:j]:
         counter = counter + 1
print (counter)

def find_all(st, substr, start_pos=0, accum=[]):
    ix = st.find(substr, start_pos)
    if ix == -1:
        return accum
    return find_all(st, substr, start_pos=ix + 1, accum=accum + [ix])

findall_lc = lambda txt, substr: [n for n in xrange(len(txt))
                                   if txt.find(substr, n) == n]

import random, string; random.seed(0)
s = ''.join([random.choice(string.ascii_lowercase) for _ in range(100000)])

>>> find_all(s, 'th') == findall_lc(s, 'th')
True
>>> findall_lc(s, 'th')[:4]
[564, 818, 1872, 2470]

%timeit find_all(s, 'th')
1000 loops, best of 3: 282 µs per loop

%timeit findall_lc(s, 'th')    
10 loops, best of 3: 92.3 ms per loop

#!/usr/local/bin python3
#-*- coding: utf-8 -*-

main_string = input()
sub_string = input()

count = counter = 0

for i in range(len(main_string)):
    if main_string[i] == sub_string[0]:
        k = i + 1
        for j in range(1, len(sub_string)):
            if k != len(main_string) and main_string[k] == sub_string[j]:
                count += 1
                k += 1
        if count == (len(sub_string) - 1):
            counter += 1
        count = 0

print(counter) 

str.index

def all_substring_indexes(string, substring, start=0, end=None):
    result = []
    new_start = start
    while True:
        try:
            index = string.index(substring, new_start, end)
        except ValueError:
            return result
        else:
            result.append(index)
            new_start = index + len(substring)

        def allindices(string, sub):
           l=[]
           i = string.find(sub)
           while i >= 0:
              l.append(i)
              i = string.find(sub, i + 1)
           return l

>>> key = 'll'
>>> text = "Allowed Hello Hollow"
>>> x = [len(i) for i in text.split(key)[:-1]]
>>> [sum(x[:i+1]) + i*len(key) for i in range(len(x))]
[1, 10, 16]
>>> 

def retrieve_occurences(sequence, word, result, base_counter):
     indx = sequence.find(word)
     if indx == -1:
         return result
     result.append(indx + base_counter)
     base_counter += indx + len(word)
     return retrieve_occurences(sequence[indx + len(word):], word, result, base_counter)

link

Suffix trees

    >>> text = 'Allowed Hello Hollow'
    >>> place = 0
    >>> while text.find('ll', place) != -1:
            print('ll found at', text.find('ll', place))
            place = text.find('ll', place) + 2


    ll found at 1
    ll found at 10
    ll found at 16

string1= "Allowed Hello Hollow"
string2= "ll"
print [num for num in xrange(len(string1)-len(string2)+1) if string1[num:num+len(string2)]==string2]
# [1, 10, 16]

findin = "algorithm alma mater alison alternation alpines"
search = "al"
inx = 0
num_str = 0

while True:
    inx = findin.find(search)
    if inx == -1: #breaks before adding 1 to number of string
        break
    inx = inx + 1
    findin = findin[inx:] #to splice the 'unsearched' part of the string
    num_str = num_str + 1 #counts no. of string

if num_str != 0:
    print("There are ",num_str," ",search," in your string.")
else:
    print("There are no ",search," in your string.")