# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?<URL>\/upload(.+?)pdf).+?(?P<DATE>\d{2}\.\d{2}\.\d{4})"
test_str = ("<div class=\"rasschetSredstv\">\n"
"<table class=\"tab td_tac\" border=\"0\" cellpadding=\"10\" cellspacing=\"0\">\n"
" <tbody><tr>\n"
" <th width=\"17%\">Январь</th>\n"
" <th width=\"17%\">Февраль</th>\n"
" <th width=\"17%\">Март</th>\n"
" <th width=\"17%\">Апрель</th>\n"
" <th width=\"17%\">Май</th>\n"
" <th width=\"17%\">Июнь</th>\n"
" </tr>\n"
" <tr>\n"
" <td>\n"
" \n"
" <a target=\"_blanc\" href=\"/upload/iblock/2da/otchet_ss_310117.pdf\">Скачать</a><br>\n"
" pdf(201 кБ)<br> (14.02.2017 12:44:00) </td>\n"
" <td>\n"
" \n"
" <a target=\"_blanc\" href=\"/upload/iblock/aa8/otchet_rss_na_sayt.pdf\">Скачать</a><br>\n"
" pdf(196 кБ)<br> (15.03.2017 18:49:00) </td>\n"
" <td>\n"
" \n"
" <a target=\"_blanc\" href=\"/upload/iblock/71e/raschet_ss_na_sayt.pdf\">Скачать</a><br>\n"
" pdf(197 кБ)<br> (14.04.2017 18:23:00) </td>\n"
" <td>\n"
" \n"
" ----\n"
" </td>\n"
" <td>\n"
" \n"
" ----\n"
" </td>\n"
" <td>\n"
" \n"
" ----\n"
" </td>\n"
" </tr>\n"
" <tr>\n"
" <th>Июль</th>\n"
" <th>Август</th>\n"
" <th>Сентябрь</th>\n"
" <th>Октябрь</th>\n"
" <th>Ноябрь</th>\n"
" <th>Декабрь</th>\n"
" </tr>\n"
" <tr>\n"
" <td>\n"
" \n"
" \n"
" ----\n"
" </td>\n"
" <td>\n"
" \n"
" \n"
" ----\n"
" </td>\n"
" <td>\n"
" \n"
" \n"
" ----\n"
" </td>\n"
" <td>\n"
" \n"
" \n"
" ----\n"
" </td>\n"
" <td>\n"
" \n"
" \n"
" ----\n"
" </td>\n"
" <td>\n"
" \n"
" \n"
" ----\n"
" </td>\n"
" </tr>\n"
"</tbody></table>\n"
"</div>")
matches = re.finditer(regex, test_str, 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