# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<![[:punct:]].|\>|\w)\<\/[p]\>"
test_str = (" <p class=\"calibre_\">John Wiley & Sons Ltd, The Atrium, Southern Gate, Chichester, West Sussex, PO19 8SQ, United Kingdom. </p>\n\n"
" <p class=\"calibre_\">For details of our global editorial offices, for customer services and for information about how to apply for permis-</p>\n\n"
" <p class=\"calibre_\"><a href=\"http://www.wiley.com\">sion to reuse the copyright material in this book please see our website at www.wiley.com. </a></p>\n\n"
" <p class=\"calibre_\">The right of the author to be identified as the author of this work has been asserted in accordance with the </p>")
subst = " "
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0, re.MULTILINE | re.IGNORECASE)
if result:
print (result)
# 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