# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"<a[^>]*href=\"(?<url>[^\"]*(?<=\?|&)o=(?<number>\d+)[^\"]*)\"[^>]*>\s*last"
test_str = ("<div class=\"listing_thumbs_resultcontainer\">\n"
" \n"
" <span class=\"FloatLeft nav-next-btn\">\n"
" \n"
" \n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=1&q=nike air&th=1\" title=\"Go to first page\">« First</a>\n"
" \n\n"
" \n"
" <span class=\"nav-next-btn nohistory marginLeft\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=18&q=nike air&th=1\" title=\"Go to previous page\">\n"
" ‹ Previous\n"
" </a>\n"
" </span>\n"
" \n"
" \n"
" \n\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=1&q=nike air&th=1\" title=\"Page 1 of 29\">1</a>\n"
" </span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=2&q=nike air&th=1\" title=\"Page 2 of 29\">2</a>\n"
" </span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=3&q=nike air&th=1\" title=\"Page 3 of 29\">3</a>\n"
" </span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=4&q=nike air&th=1\" title=\"Page 4 of 29\">4</a>\n"
" </span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=5&q=nike air&th=1\" title=\"Page 5 of 29\">5</a>\n"
" </span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=6&q=nike air&th=1\" title=\"Page 6 of 29\">6</a>\n"
" </span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=7&q=nike air&th=1\" title=\"Page 7 of 29\">7</a>\n"
" </span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=8&q=nike air&th=1\" title=\"Page 8 of 29\">8</a>\n"
" </span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=9&q=nike air&th=1\" title=\"Page 9 of 29\">9</a>\n"
" </span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=10&q=nike air&th=1\" title=\"Page 10 of 29\">10</a>\n"
" </span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=11&q=nike air&th=1\" title=\"Page 11 of 29\">11</a>\n"
" </span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=12&q=nike air&th=1\" title=\"Page 12 of 29\">12</a>\n"
" </span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=13&q=nike air&th=1\" title=\"Page 13 of 29\">13</a>\n"
" </span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=14&q=nike air&th=1\" title=\"Page 14 of 29\">14</a>\n"
" </span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=15&q=nike air&th=1\" title=\"Page 15 of 29\">15</a>\n"
" </span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=16&q=nike air&th=1\" title=\"Page 16 of 29\">16</a>\n"
" </span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=17&q=nike air&th=1\" title=\"Page 17 of 29\">17</a>\n"
" </span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=18&q=nike air&th=1\" title=\"Page 18 of 29\">18</a>\n"
" </span>\n"
" \n"
" <span class=\"nav-active\"><strong>19</strong></span>\n"
" <span class=\"non-active nohistory\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=20&q=nike air&th=1\" title=\"Page 20 of 29\">20</a>\n"
" </span\n"
" \n"
" \n"
" </span>\n"
" \n"
" <span class=\"nav-next-btn nohistory FloatRight\">\n"
" \n"
" <span class=\"nav-next-btn nohistory marginRight\">\n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=20&q=nike air&th=1\" title=\"Go to next page\">\n"
" Next ›\n"
" </a>\n"
" </span>\n"
" \n"
" \n"
" \n"
" \n"
" <a href=\"http://www.mudah.my/Malaysia/nike+air-for-sale?o=29&q=nike air&th=1\" title=\"Go to last page\">\n"
" Last »\n"
" </a>\n"
" \n"
" \n"
" </span> \n"
" \n"
" </div>")
matches = re.finditer(regex, test_str, re.MULTILINE | re.IGNORECASE | re.DOTALL)
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