# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"<td class=\"lineColumn\">(.*)<\/td>(.*)<td class=\"stationColumn\">(.*)<span(.*)<td class=\"inMinColumn\">(.*)<\/td>"
test_str = ("\n\n\n"
"<!DOCTYPE html PUBLIC \"-//W3C//DTD HTML 4.01 Transitional//EN\" \"http://www.w3.org/TR/html4/loose.dtd\">\n"
"<html>\n"
"<head>\n"
" \n"
" <meta http-equiv=\"Content-Type\" content=\"text/html; charset=ISO-8859-1\">\n"
" <meta name=\"viewport\" content=\"width=340px\">\n"
" <title>MVG-Live: Westkreuz Bf.</title>\n"
" <link type=\"text/css\" rel='stylesheet' href='css/size30/mvg/mvglive-mobile.css' media='all'>\n"
"</head>\n"
"<body>\n"
" <div class=\"departureTable header logo\">\n"
" <div class=\"logoLeft\">\n"
" <img class=\"logoImgLeft\" src=\"images/size30/grafik/mvg/mobile-logo-left.jpg\" alt=\"MVG live\">\n"
" </div>\n"
" <div class=\"logoRight\">\n"
" <img class=\"logoImgRight\" src=\"images/size30/grafik/mvg/mobile-logo-right.jpg\" alt=\"MVG live\">\n"
" </div>\n"
" </div>\n"
" \n"
" \n\n"
" \n"
" <table class=\"departureTable departureView\">\n"
" <tr>\n"
" <td colspan=\"2\" class=\"headerStationColumn\">Westkreuz Bf.</td>\n"
" <td colspan=\"2\" class=\"serverTimeColumn\">21:33</td>\n"
" </tr>\n"
" \n"
" \n"
" \n"
" <tr>\n"
" <td colspan=\"4\" class=\"sBahnHeader\">S-Bahn München (Daten DB Regio AG)</td>\n"
" </tr>\n"
" \n"
" <tr class=\"rowOdd\">\n"
" <td class=\"lineColumn\">S6</td> \n"
" <td class=\"stationColumn\">\n"
" Ebersberg(Oberbay)\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">1</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowEven\">\n"
" <td class=\"lineColumn\">S8</td> \n"
" <td class=\"stationColumn\">\n"
" Herrsching\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">5</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowOdd\">\n"
" <td class=\"lineColumn\">S8</td> \n"
" <td class=\"stationColumn\">\n"
" München Flughafen Terminal\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">6</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowEven\">\n"
" <td class=\"lineColumn\">S6</td> \n"
" <td class=\"stationColumn\">\n"
" Starnberg\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">11</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowOdd\">\n"
" <td class=\"lineColumn\">S6</td> \n"
" <td class=\"stationColumn\">\n"
" Ebersberg(Oberbay)\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">21</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowEven\">\n"
" <td class=\"lineColumn\">S8</td> \n"
" <td class=\"stationColumn\">\n"
" Weßling(Oberbay)\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">25</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowOdd\">\n"
" <td class=\"lineColumn\">S8</td> \n"
" <td class=\"stationColumn\">\n"
" München Flughafen Terminal\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">26</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowEven\">\n"
" <td class=\"lineColumn\">S6</td> \n"
" <td class=\"stationColumn\">\n"
" Tutzing\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">31</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowOdd\">\n"
" <td class=\"lineColumn\">S6</td> \n"
" <td class=\"stationColumn\">\n"
" Grafing Bahnhof\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">41</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowEven\">\n"
" <td class=\"lineColumn\">S8</td> \n"
" <td class=\"stationColumn\">\n"
" Herrsching\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">45</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowOdd\">\n"
" <td class=\"lineColumn\">S8</td> \n"
" <td class=\"stationColumn\">\n"
" München Flughafen Terminal\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">46</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowEven\">\n"
" <td class=\"lineColumn\">S6</td> \n"
" <td class=\"stationColumn\">\n"
" Tutzing\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">51</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowOdd\">\n"
" <td class=\"lineColumn\">S6</td> \n"
" <td class=\"stationColumn\">\n"
" Ebersberg(Oberbay)\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">61</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowEven\">\n"
" <td class=\"lineColumn\">S8</td> \n"
" <td class=\"stationColumn\">\n"
" Weßling(Oberbay)\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">65</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowOdd\">\n"
" <td class=\"lineColumn\">S8</td> \n"
" <td class=\"stationColumn\">\n"
" München Flughafen Terminal\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">66</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowEven\">\n"
" <td class=\"lineColumn\">S6</td> \n"
" <td class=\"stationColumn\">\n"
" Tutzing\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">71</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowOdd\">\n"
" <td class=\"lineColumn\">S6</td> \n"
" <td class=\"stationColumn\">\n"
" Ebersberg(Oberbay)\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">81</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowEven\">\n"
" <td class=\"lineColumn\">S8</td> \n"
" <td class=\"stationColumn\">\n"
" Herrsching\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">85</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowOdd\">\n"
" <td class=\"lineColumn\">S8</td> \n"
" <td class=\"stationColumn\">\n"
" München Flughafen Terminal\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">86</td>\n"
" \n"
" </tr>\n"
" \n"
" <tr class=\"rowEven\">\n"
" <td class=\"lineColumn\">S6</td> \n"
" <td class=\"stationColumn\">\n"
" Tutzing\n"
" <span class=\"spacer\"> </span>\n"
" </td> \n"
" <td class=\"inMinColumn\">91</td>\n"
" \n"
" </tr>\n"
" \n"
" \n"
" <tr> \n"
" <td colspan=\"4\" class=\"reloadLink\"> \n"
" <a href=\"/ims/dfiStaticAnzeige.svc?haltestelle=Westkreuz Bf.&ubahn=&bus=&tram=&sbahn=checked\">\n"
" Fahrten aktualisieren \n"
" </a>\n"
" </td>\n"
" </tr>\n"
" \n"
" </table>\n"
" <table class=\"departureTable footerTable\">\n"
" <tr>\n"
" <td class=\"footer\">\n"
" <a href=\"http://www.mvg-mobil.de/impressum.htm\" target=\"_blank\">Impressum</a> \n"
" </td>\n"
" </tr>\n"
" </table> \n"
"</body>\n"
"</html>")
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