# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"\[(?<tag>[^\]]+)]\s*(?<content>[\w\W]+?)\s*\[\/\1]"
test_str = ("[SLUG]ghana-cocoa-supply-shortfall-impacts-traders[/SLUG]\n\n"
"[TITLE]Sweet Trouble: Ghana's Cocoa Shortfall Leaves Traders in a Bitter Spot[/TITLE]\n\n"
"[EXCERPT]Ghana's cocoa bean delivery hiccup has traders facing a whopping $1 billion loss. Here's what happened and why it matters for your morning mocha.[/EXCERPT]\n\n"
"[BODY]\n"
"<p>Hey there, chocolate lovers and market watchers! Grab your favorite cocoa-based snack because we've got some news that might make your wallet feel a little lighter (but hopefully not your candy bar).</p>\n"
"[/BODY]\n\n"
"[CATEGORIES]Finance,Commodities,Global Trade[/CATEGORIES]\n\n"
"[TAGS]cocoa,Ghana,commodities,trading,supplychain,chocolate[/TAGS]")
matches = re.finditer(regex, test_str)
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