>>> url = 'https://www.facebook.com/xxxxxx?test1q223'
>>> url = url.split('?')[:-1][0]
>>> url
'https://www.facebook.com/xxxxxx'
>>>
There are also ways to do it using the stdlib's
urllib.parse module:
>>> from urllib.parse import urlparse
>>> parsed = urlparse('https://www.facebook.com/xxxxxx?test1q223')
>>> parsed._replace(query='').geturl()
'https://www.facebook.com/xxxxxx'Note that
_replace is an undocumented "private" method, so its semantics might change in the future (although it's pretty unlikely).
You might also want to replace
params and
fragment, depending on your exact needs.
HI thanks.
if i wants to write in loop, is it possible be like this:
i put the url in the text file, and export it to a new file.
Example: 'orgginal.txt' would be like
https://www.facebook.com/xxxxxx?test1q223, and out.txt would be like
https://www.facebook.com/xxxxxx
with open('orgginal.txt') as f,open('out.txt', 'w') as f_out:
for line in f:
line = line.strip()
line=line.split('?')[:-1][0]
f_out.write('{}\n'.format(line))
i have figure it out
with open('orgginal.txt') as f,open('out.txt', 'w') as f_out:
for line in f:
line = line.strip()
print(line)
line=line.split('?')[:-1][0]
print(line)
f_out.write('{}\n'.format(line))
or
from urllib.parse import urlparse
with open('orgginal.txt') as f,open('out.txt', 'w') as f_out:
for line in f:
line = line.strip()
parsed = urlparse(line)
#print(line)
newline=parsed._replace(query='').geturl()
print(newline)
#f_out.write('{}\n'.format(line))
You really need to study up on slicing, see:
https://www.python-course.eu/python3_seq..._types.php
This will handle all cases:
url1 = 'https://www.facebook.com/xxxxxx/test1q223/'
url2 = 'https://www.facebook.com/xxxxxx/?test1q223'
url3 = 'https://www.facebook.com/xxxxxx/test1q223'
def change_url(url):
urlx = url.split('/')
if url[-1] == '/':
return url[:-1]
if urlx[-1].startswith('?'):
urlx[-1] = urlx[-1][1:]
return '/'.join(urlx)
return url
print(f'url1: {change_url(url1)}')
print(f'url2: {change_url(url2)}')
print(f'url3: {change_url(url3)}')results:
Output:
url1: https://www.facebook.com/xxxxxx/test1q223
url2: https://www.facebook.com/xxxxxx/test1q223
url3: https://www.facebook.com/xxxxxx/test1q223
hi, i have a question about this script.
Why does my first url1 didn't cut off the last string" /test1q223 "?
url1 = 'https://www.facebook.com/xxxxxx/test1q223/'
url2 = 'https://www.facebook.com/xxxxxx/?test1q223'
url3 = 'https://www.facebook.com/xxxxxx/test1q223'
url4 = 'https://www.facebook.com/xxxxxx/test1q223'
def change_url(url):
urlx = url.split('/')
#print (urlx)
#print(urlx[4])
# if url[-1] == '/':
# print("yes1")
# return ''.join(urlx[:-1])
if urlx[-1].startswith('?'):
urlx[-1] = urlx[-1][1:]
#print("yes2")
return '/'.join(urlx[:-1])
if urlx[2]!='':
urlx[-1] = urlx[:4][3]
#print(urlx[:3][2])
#print(urlx[2])
#print("yes3")
#print("ttt"+urlx[:3][1])
#print(urlx)
return '/'.join(urlx[:-1])
return url
print(f'url1: {change_url(url1)}')
print(f'url2: {change_url(url2)}')
print(f'url3: {change_url(url3)}')
print(f'url4: {change_url(url4)}')#output is :
url1:
https://www.facebook.com/xxxxxx/test1q223
url2:
https://www.facebook.com/xxxxxx
url3:
https://www.facebook.com/xxxxxx
url4:
https://www.facebook.com/xxxxxx
Quote:Why does my first url1 didn't cut off the last string" /test1q223 "?
Break it down step by step (uses f-string which requires python 3.6 or newer)
>>> url1 = 'https://www.facebook.com/xxxxxx/test1q223/'
>>> url2 = 'https://www.facebook.com/xxxxxx/?test1q223'
>>> url3 = 'https://www.facebook.com/xxxxxx/test1q223'
>>> def change_url(url):
... urlx = url.split('/')
... print(f'url: {url}, urlx: {urlx}')
... if url[-1] == '/':
... print(f'returning url[-1]: {url[-1]}')
... return url[:-1]
... if urlx[-1].startswith('?'):
... print(f'urlx[-1][1:]: {urlx[-1][1:]}')
... print(f"returning '/'.join(urlx): {'/'.join(urlx)}")
... return '/'.join(urlx)
... # No change needed
... return url
...
>>> print(f'url1: {change_url(url1)}')
url: https://www.facebook.com/xxxxxx/test1q223/, urlx: ['https:', '', 'www.facebook.com', 'xxxxxx', 'test1q223', '']
returning url[-1]: /
url1: https://www.facebook.com/xxxxxx/test1q223
>>> # ------------------------------------------
...
>>> print(f'url2: {change_url(url2)}')
url: https://www.facebook.com/xxxxxx/?test1q223, urlx: ['https:', '', 'www.facebook.com', 'xxxxxx', '?test1q223']
urlx[-1][1:]: test1q223
returning '/'.join(urlx): https://www.facebook.com/xxxxxx/?test1q223
url2: https://www.facebook.com/xxxxxx/?test1q223
>>> # ------------------------------------------
...
>>> print(f'url3: {change_url(url3)}')
url: https://www.facebook.com/xxxxxx/test1q223, urlx: ['https:', '', 'www.facebook.com', 'xxxxxx', 'test1q223']
url3: https://www.facebook.com/xxxxxx/test1q223
>>>