# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"<div[^>]*>\d{6}<\/div>"
test_str = ("<div dir=\"ltr\"><br><br><div class=\"gmail_quote\"><div dir=\"ltr\" class=\"gmail_attr\"><br></div><u></u>\n"
" <div>\n"
" <center id=\"m_-2051398760120817894wrapper\">\n"
" <table id=\"m_-2051398760120817894main\" width=\"100%\">\n"
" <tbody><tr id=\"m_-2051398760120817894logo\">\n"
" <td>\n"
" <table width=\"100%\">\n"
" <tbody><tr>\n"
" <td>\n"
" <img src=\"test.com/logo.png\" width=\"140px\" alt=\"xxxxx Logo\" style=\"padding:0 10px\">\n"
" </td>\n"
" </tr>\n"
" </tbody></table>\n"
" </td>\n"
" </tr>\n"
" <tr>\n"
" <td height=\"18px\"></td>\n"
" </tr>\n"
" <tr id=\"m_-2051398760120817894header\">\n"
" <td>\n"
" <table width=\"100%\">\n"
" <tbody><tr>\n"
" <td height=\"64px\" style=\"background-color:#10069f;color:#fff;padding-left:24px;font-weight:700\">Reset your password</td>\n"
" </tr>\n"
" </tbody></table>\n"
" </td>\n"
" </tr>\n"
" <tr id=\"m_-2051398760120817894content\">\n"
" <td>\n"
" <table width=\"100%\">\n"
" <tbody><tr>\n"
" <td style=\"background-color:#f6f5ff;padding:24px 24px 16px 24px\">\n"
" <p style=\"margin-top:0\">The following is the verification code required to complete your password reset.</p>\n"
" <p style=\"margin-bottom:24px\">Enter the following verification code on the screen during the registration, and proceed to the next step.</p>\n"
" <div style=\"display:block;text-align:center;margin-bottom:8px;background-color:#fff;height:92px;font-weight:600;font-size:36px;line-height:92px\">191418</div>\n"
" <span style=\"display:block;font-size:12px;color:#5d5d5d\">*The verification code is valid only for 24 hours.</span>\n"
" </td>\n"
" </tr>\n"
" </tbody></table>\n"
" </td>\n"
" </tr>\n"
" <tr>\n"
" <td height=\"24px\"></td>\n"
" </tr>\n"
" <tr id=\"m_-2051398760120817894footer\">\n"
" <td>\n"
" <table width=\"100%\">\n"
" <tbody><tr>\n"
" <td style=\"background-color:#6d7777;padding:16px 24px;font-size:12px;color:#fff\">\n"
" <table width=\"100%\">\n"
" <tbody><tr>\n"
" <td id=\"m_-2051398760120817894footer-left\">\n"
" <span style=\"display:block\">amnimo Inc.</span>\n"
" <span style=\"display:block\">0-3-30 usaa-fso, xxxxxxxx-shi, Tokyo, 180-8750, Japan</span>\n"
" <span style=\"display:block\">Phone: +81-422-52-6779</span>\n"
" <span id=\"m_-2051398760120817894copyright-mb\" style=\"margin-top:16px\">© 2020 <div dir=\"ltr\"><br><br><div class=\"gmail_quote\"><div dir=\"ltr\" class=\"gmail_attr\"><br></div><u></u>\n"
"<div>\n"
" <center id=\"m_-2051398760120817894wrapper\">\n"
" <table id=\"m_-2051398760120817894main\" width=\"100%\">\n"
" <tbody><tr id=\"m_-2051398760120817894logo\">\n"
" <td>\n"
" <table width=\"100%\">\n"
" <tbody><tr>\n"
" <td>\n"
" <img src=\"https://test.com/logo.png\" width=\"140px\" alt=\"Amnimo Logo\" style=\"padding:0 10px\">\n"
" </td>\n"
" </tr>\n"
" </tbody></table>\n"
" </td>\n"
" </tr>\n"
" <tr>\n"
" <td height=\"18px\"></td>\n"
" </tr>\n"
" <tr id=\"m_-2051398760120817894header\">\n"
" <td>\n"
" <table width=\"100%\">\n"
" <tbody><tr>\n"
" <td height=\"64px\" style=\"background-color:#10069f;color:#fff;padding-left:24px;font-weight:700\">Reset your password</td>\n"
" </tr>\n"
" </tbody></table>\n"
" </td>\n"
" </tr>\n"
" <tr id=\"m_-2051398760120817894content\">\n"
" <td>\n"
" <table width=\"100%\">\n"
" <tbody><tr>\n"
" <td style=\"background-color:#f6f5ff;padding:24px 24px 16px 24px\">\n"
" <p style=\"margin-top:0\">The following is the verification code required to complete your password reset.</p>\n"
" <p style=\"margin-bottom:24px\">Enter the following verification code on the screen during the registration, and proceed to the next step.</p>\n"
" <div style=\"display:block;text-align:center;margin-bottom:8px;background-color:#fff;height:92px;font-weight:600;font-size:36px;line-height:92px\">191418</div>\n"
" <span style=\"display:block;font-size:12px;color:#5d5d5d\">*The verification code is valid only for 24 hours.</span>\n"
" </td>\n"
" </tr>\n"
" </tbody></table>\n"
" </td>\n"
" </tr>\n"
" <tr>\n"
" <td height=\"24px\"></td>\n"
" </tr>\n"
" <tr id=\"m_-2051398760120817894footer\">\n"
" <td>\n"
" <table width=\"100%\">\n"
" <tbody><tr>\n"
" <td style=\"background-color:#6d7777;padding:16px 24px;font-size:12px;color:#fff\">\n"
" <table width=\"100%\">\n"
" <tbody><tr>\n"
" <td id=\"m_-2051398760120817894footer-left\">\n"
" <span style=\"display:block\">test Inc.</span>\n"
" <span style=\"display:block\">2-9-32 ssdsa-sss, puakano-shi, Tokyo, 000-8000, Japan</span>\n"
" <span style=\"display:block\">Phone: +81-000-00-652</span>\n"
" <span id=\"m_-2051398760120817894copyright-mb\" style=\"margin-top:16px\">© 2020 amnimo Inc.</span>\n"
" </td>\n"
" <td id=\"m_-2051398760120817894footer-right\">\n"
" <span style=\"display:block\">© 2020 amnimo Inc.</span>\n"
" </td>\n"
" </tr>\n"
" </tbody></table>\n"
" </td>\n"
" </tr>\n"
" </tbody></table>\n"
" </td>\n"
" </tr>\n"
" </tbody></table>\n"
" </center>\n"
"</div>\n"
"</div></div> Inc.</span>\n"
" </td>\n"
" <td id=\"m_-2051398760120817894footer-right\">\n"
" <span style=\"display:block\">© 2020 test Inc.</span>\n"
" </td>\n"
" </tr>\n"
" </tbody></table>\n"
" </td>\n"
" </tr>\n"
" </tbody></table>\n"
" </td>\n"
" </tr>\n"
" </tbody></table>\n"
" </center>\n"
" </div>\n"
" </div></div>")
matches = re.finditer(regex, test_str, re.DOTALL | re.IGNORECASE)
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