# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"<div id=\"pageContent\">[\s\S]*<div id=\"pageContent\">"
test_str = (" \"HTML Tidy for Mac OS X (vers 31 October 2006 - Apple Inc. build 15.15), see www.w3.org\">\n\n"
" <title>02.00: Page 1</title>\n"
" <meta charset=\"utf-8\">\n"
" <script type=\"text/javascript\">\n"
"var pg_csslibs = []; // CSS Libs for this Page\n"
" var pg_jslibs = []; // JS Libs for this Page\n"
" </script>\n"
" <script src=\"../../global/js/settings.js\" id=\"settingJS\" type=\n"
" \"text/javascript\">\n"
"</script>\n"
"</head>\n\n"
"<body>\n"
" <div id=\"pageContent\">\n"
" <!-- CONTENT GOES HERE -->\n\n"
" <div id=\"pageContent\">\n"
" <div>\n"
" <p><a href=\"pop/02_00_01/02_00_01_pop01.htm\" class=\n"
" \"modal-pop\"><strong>Print</strong></a> the Carousel of Progress\n"
" Checklist provided below to keep track of your progress\n"
" through the <span class=\"lang\" data-term=\n"
" \"module_name\">module</span>. It is important that you read\n"
" each page and complete all practice activities in every\n"
" <span class=\"lang\" data-term=\"lesson_name")
matches = re.search(regex, test_str)
if matches:
print ("Match was found at {start}-{end}: {match}".format(start = matches.start(), end = matches.end(), match = matches.group()))
for groupNum in range(0, len(matches.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = matches.start(groupNum), end = matches.end(groupNum), group = matches.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