# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\b(https?://\S*?/documents/)en(/\S*)\.pdf\b"
test_str = ("The problem is, if the page contains a PDF linked to another page (not my own website), example https://othersite.example.com/whatever.pdf, it becomes https://othersite.example.com/whatever_SPANISH.pdf which isn't valid on other people's sites. I want to ignore offsite links and only change URLs on my site.\n\n"
"So what I would like to do is look for the string: https://example.com/documents/en/whateverfilename.pdf and pull that file name out and change it to https://example.com/documents/es/whateverfilename_SPANISH.pdf (Switching the en to es and also appending the _SPANISH to the end of the PDF filename.\n\n")
subst = "$1es$2_SPANISH.pdf"
# You can manually specify the number of replacements by changing the 4th argument
result = re.sub(regex, subst, test_str, 0)
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