>>> s = '<b>cfgghjkjlsdfghj</b>'
>>> help(s.strip)
Help on built-in function strip:
strip(...) method of builtins.str instance
S.strip([chars]) -> str
Return a copy of the string S with leading and trailing
whitespace removed.
If chars is given and not None, remove characters in chars instead.
>>> s.strip('</b>')
'cfgghjkjlsdfghj'
>>> s.rstrip('</b>')
'<b>cfgghjkjlsdfghj'
>>> s.lstrip('</b>')
'cfgghjkjlsdfghj</b>'
re.sub
>>> import re
>>> help(re.sub)
Help on function sub in module re:
sub(pattern, repl, string, count=0, flags=0)
Return the string obtained by replacing the leftmost
non-overlapping occurrences of the pattern in string by the
replacement repl. repl can be either a string or a callable;
if a string, backslash escapes in it are processed. If it is
a callable, it's passed the match object and must return
a replacement string to be used.
>>> s = 'aaa'
>>> re.sub('a','b',s)
'bbb'
>>> pattern = re.compile(r'\w')
>>> s
'aaa'
>>> pattern.sub('b',s)
'bbb'
def urlretrieve(url, filename=None, reporthook=None, data=None):
"""
Retrieve a URL into a temporary location on disk.
Requires a URL argument. If a filename is passed, it is used as
the temporary file location. The reporthook argument should be
a callable that accepts a block number, a read size, and the
total file size of the URL target. The data argument should be
valid URL encoded data.
If a filename is passed and the URL points to a local resource,
the result is a copy from local file to new file.
Returns a tuple containing the path to the newly created
data file as well as the resulting HTTPMessage object.
"""
url_type, path = splittype(url)
with contextlib.closing(urlopen(url, data)) as fp:
headers = fp.info()
# Just return the local path and the "headers" for file://
# URLs. No sense in performing a copy unless requested.
if url_type == "file" and not filename:
return os.path.normpath(path), headers
# Handle temporary file setup.
if filename:
tfp = open(filename, 'wb')
else:
tfp = tempfile.NamedTemporaryFile(delete=False)
filename = tfp.name
_url_tempfiles.append(filename)
with tfp:
result = filename, headers
bs = 1024*8
size = -1
read = 0
blocknum = 0
if "content-length" in headers:
size = int(headers["Content-Length"])
if reporthook:
reporthook(blocknum, bs, size)
while True:
block = fp.read(bs)
if not block:
break
read += len(block)
tfp.write(block)
blocknum += 1
if reporthook:
reporthook(blocknum, bs, size)
if size >= 0 and read < size:
raise ContentTooShortError(
"retrieval incomplete: got only %i out of %i bytes"
% (read, size), result)
return result