import re
regex = re.compile(r"href=[^>]+\.pdf\"", flags=re.DOTALL)
test_str = "<li>Your browser may be missing a required plug-in contained in <a href=\"http://get.adobe.com/reader/\">Adobe Acrobat Reader</a>. Please reload this page after installing the missing component.<br />If this error persists, you can also save a copy of <a href=\"http://www.police.vt.edu/VTPD_v2.1/crime_stats/crime_logs/data/VT_2011-01_Crime_Log.pdf\">"
matches = regex.finditer(test_str)
for match_num, match in enumerate(matches, start=1):
print(f"Match {match_num} was found at {match.start()}-{match.end()}: {match.group()}")
for group_num, group in enumerate(match.groups(), start=1):
print(f"Group {group_num} found at {match.start(group_num)}-{match.end(group_num)}: {group}")
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