# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"""
(?s:
<ins
(?:(?!</ins>).)*?
"adsbygoogle"
.*?
</ins>)
"""
test_str = (" 0\n"
"down vote\n"
"favorite\n"
" \n\n"
"I have a thousand html pages (without admin panel) with codes of adsense. And I want to remove all of them from html. One code looks like:\n\n"
"<ins class=\"adsbygoogle\"\n"
" style=\"display:inline-block;width:160px;height:600px\"\n"
" data-ad-client=\"ca-pub-7165746718333100\"\n"
" data-ad-slot=\"9087512399\"></ins>\n\n"
"Another:\n\n"
"<ins class=\"adsbygoogle\"\n"
" style=\"display:inline-block;width:160px;height:600px\"\n"
" data-ad-client=\"ca-pub-7163746711373100\"\n"
" data-ad-slot=\"7467236139\"></ins>\n\n"
"All of them are similar but not equal. A tried to write regex to find and replace it with empty string, but unsuccessfully.\n\n"
"Any suggetion how to do it automatically?\n")
matches = re.finditer(regex, test_str, re.VERBOSE)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html