import re
Str1= "This is a test string.. 123123123 "
Str2= "<HTML> THis is a sample string having 1232123, %$%^$%$, ABCDE, asdfhg12312$ </HTML> "
# reg= re.compile("\d*")
matches= re.match(r"\w+", Str1, 0)
if matches:
print (matches.group())
else:
print ("No match found")
print (type(matches))
print ("\n+++++++++++++++find all the matches using re.finditer--Group method+++++++++++++++\n")
searches= re.finditer(r"\d{4,}", Str1)
for sea in searches:
print (sea)
print ("Each match: ", sea.group())
print ("\n+++++++++++++++find all the matches using re.finditer method+++++++++++++++\n")
searches= re.finditer(r"\d{4,}", Str1)
for sea in searches:
print ("Item found using FindIter: ", sea)
findAl= re.findall(r"\w+", Str2)
if findAl:
print (findAl)
for each in findAl:
print ("Match Found: ", each)
#print ("Match Found: ", each.group()) #each.group() is invalid with findall method..
'''the above commented line throws an error.. '''
print ("\n+++++++++++++++find all the matches using re.findall method+++++++++++++++\n")
Str2= "<HTML> THis is a sample string having 1232123, %$%^$%$, ABCDE, asdfhg12312$ </HTML> "
se1= re.findall(r"[A-Z]{2,}", Str2)
print (se1) # Print all the upper case ones having more than two characters in a word..
#output: ['HTML', 'TH', 'ABCDE', 'HTML']
se1= re.findall(r"[A-Z]{3,}", Str2)
print (se1) # Print all the upper case ones having more than 3 characters in a word..
#output: ['HTML', 'ABCDE', 'HTML']
print ("++++++++++++++++++++++++++++++++++++++++++++++++++")
Str1= "This is a test string.. 123123123 "
Str2= "<HTML> THis is a sample string having 1232123, %$%^$%$, ABCDE, asdfhg12312$ </HTML> "
# reg= re.compile("\d*")
matches= re.match(r"\w+", Str1, 0)
if matches:
print (matches.group())
else:
print ("No match found")
print (type(matches))
print ("\n+++++++++++++++find all the matches using re.finditer--Group method+++++++++++++++\n")
searches= re.finditer(r"\d{4,}", Str1)
for sea in searches:
print (sea)
print ("Each match: ", sea.group())
print ("\n+++++++++++++++find all the matches using re.finditer method+++++++++++++++\n")
searches= re.finditer(r"\d{4,}", Str1)
for sea in searches:
print ("Item found using FindIter: ", sea)
findAl= re.findall(r"\w+", Str2)
if findAl:
print (findAl)
for each in findAl:
print ("Match Found: ", each)
#print ("Match Found: ", each.group()) #each.group() is invalid with findall method..
'''the above commented line throws an error.. '''
print ("\n+++++++++++++++find all the matches using re.findall method+++++++++++++++\n")
Str2= "<HTML> THis is a sample string having 1232123, %$%^$%$, ABCDE, asdfhg12312$ </HTML> "
se1= re.findall(r"[A-Z]{2,}", Str2)
print (se1) # Print all the upper case ones having more than two characters in a word..
#output: ['HTML', 'TH', 'ABCDE', 'HTML']
se1= re.findall(r"[A-Z]{3,}", Str2)
print (se1) # Print all the upper case ones having more than 3 characters in a word..
#output: ['HTML', 'ABCDE', 'HTML']
print ("++++++++++++++++++++++++++++++++++++++++++++++++++")
Output:
This
<class '_sre.SRE_Match'>
+++++++++++++++find all the matches using re.finditer--Group method+++++++++++++++
<_sre.SRE_Match object; span=(24, 33), match='123123123'>
Each match: 123123123
+++++++++++++++find all the matches using re.finditer method+++++++++++++++
Item found using FindIter: <_sre.SRE_Match object; span=(24, 33), match='123123123'>
['HTML', 'THis', 'is', 'a', 'sample', 'string', 'having', '1232123', 'ABCDE', 'asdfhg12312', 'HTML']
Match Found: HTML
Match Found: THis
Match Found: is
Match Found: a
Match Found: sample
Match Found: string
Match Found: having
Match Found: 1232123
Match Found: ABCDE
Match Found: asdfhg12312
Match Found: HTML
+++++++++++++++find all the matches using re.findall method+++++++++++++++
['HTML', 'TH', 'ABCDE', 'HTML']
['HTML', 'ABCDE', 'HTML']
++++++++++++++++++++++++++++++++++++++++++++++++++
No comments:
Post a Comment