# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r">[^<>]+<"
test_str = ("<html>\n\n"
"<head>\n"
"<meta http-equiv=\"Content-Type\" content=\"text/html; charset=windows-1252\">\n"
"<title>Suessgraeser</title>\n"
"<meta name=\"GENERATOR\" content=\"Microsoft FrontPage 4.0\">\n"
"<meta name=\"ProgId\" content=\"FrontPage.Editor.Document\">\n"
"<meta name=\"Microsoft Theme\" content=\"expeditn 011, default\">\n"
"<meta name=\"Microsoft Border\" content=\"none, default\">\n"
"</head>\n\n"
"<body background=\"../../_themes/expeditn/exptextb.jpg\" bgcolor=\"#FFFFFF\" text=\"#000000\" link=\"#993300\" vlink=\"#666600\" alink=\"#CC3300\"><!--mstheme--><font face=\"Book Antiqua, Times New Roman, Times\">\n"
"<p align=\"center\"><!--webbot bot=\"Navigation\" S-Type=\"top\"\n"
"S-Orientation=\"horizontal\" S-Rendering=\"graphics\" B-Include-Home=\"TRUE\"\n"
"B-Include-Up=\"TRUE\" U-Page S-Target startspan --><script language=\"JavaScript\"><!--\n"
"MSFPhover = \n"
" (((navigator.appName == \"Netscape\") && \n"
" (parseInt(navigator.appVersion) >= 3 )) || \n"
" ((navigator.appName == \"Microsoft Internet Explorer\") && \n"
" (parseInt(navigator.appVersion) >= 4 ))); \n"
"function MSFPpreload(img) \n"
"{\n"
" var a=new Image(); a.src=img; return a; \n"
"}\n"
"// --></script><script language=\"JavaScript\"><!--\n"
"if(MSFPhover) { MSFPnav1n=MSFPpreload(\"../../_derived/home_cmp_expeditn010_hbtn.gif\"); MSFPnav1h=MSFPpreload(\"../../_derived/home_cmp_expeditn010_hbtn_a.gif\"); }\n"
"// --></script><a href=\"../../index.htm\" language=\"JavaScript\" onmouseover=\"if(MSFPhover) document['MSFPnav1'].src=MSFPnav1h.src\" onmouseout=\"if(MSFPhover) document['MSFPnav1'].src=MSFPnav1n.src\"><img src=\"../../_derived/home_cmp_expeditn010_hbtn.gif\" width=\"140\" height=\"50\" border=\"0\" alt=\"Home\" align=\"middle\" name=\"MSFPnav1\"></a> <script language=\"JavaScript\"><!--\n"
"if(MSFPhover) { MSFPnav2n=MSFPpreload(\"../../_derived/up_cmp_expeditn010_hbtn.gif\"); MSFPnav2h=MSFPpreload(\"../../_derived/up_cmp_expeditn010_hbtn_a.gif\"); }\n"
"// --></script><a href=\"../monoco_gras.htm\" language=\"JavaScript\" onmouseover=\"if(MSFPhover) document['MSFPnav2'].src=MSFPnav2h.src\" onmouseout=\"if(MSFPhover) document['MSFPnav2'].src=MSFPnav2n.src\"><img src=\"../../_derived/up_cmp_expeditn010_hbtn.gif\" width=\"140\" height=\"50\" border=\"0\" alt=\"Nach oben\" align=\"middle\" name=\"MSFPnav2\"></a> <script language=\"JavaScript\"><!--\n"
"if(MSFPhover) { MSFPnav3n=MSFPpreload(\"../../Hauptgruppen/_derived/Systematik.htm_cmp_expeditn010_hbtn.gif\"); MSFPnav3h=MSFPpreload(\"../../Hauptgruppen/_derived/Systematik.htm_cmp_expeditn010_hbtn_a.gif\"); }\n"
"// --></script><a href=\"../../Hauptgruppen/Systematik.htm\" language=\"JavaScript\" onmouseover=\"if(MSFPhover) document['MSFPnav3'].src=MSFPnav3h.src\" onmouseout=\"if(MSFPhover) document['MSFPnav3'].src=MSFPnav3n.src\"><img src=\"../../Hauptgruppen/_derived/Systematik.htm_cmp_expeditn010_hbtn.gif\" width=\"140\" height=\"50\" border=\"0\" alt=\"Systematik\" align=\"middle\" name=\"MSFPnav3\"></a> <script language=\"JavaScript\"><!--\n"
"if(MSFPhover) { MSFPnav4n=MSFPpreload(\"../../Bestimmung/_derived/bestimmung.htm_cmp_expeditn010_hbtn.gif\"); MSFPnav4h=MSFPpreload(\"../../Bestimmung/_derived/bestimmung.htm_cmp_expeditn010_hbtn_a.gif\"); }\n"
"// --></script><a href=\"../../Bestimmung/bestimmung.htm\" language=\"JavaScript\" onmouseover=\"if(MSFPhover) document['MSFPnav4'].src=MSFPnav4h.src\" onmouseout=\"if(MSFPhover) document['MSFPnav4'].src=MSFPnav4n.src\"><img src=\"../../Bestimmung/_derived/bestimmung.htm_cmp_expeditn010_hbtn.gif\" width=\"140\" height=\"50\" border=\"0\" alt=\"Bestimmung\" align=\"middle\" name=\"MSFPnav4\"></a> <script language=\"JavaScript\"><!--\n"
"if(MSFPhover) { MSFPnav5n=MSFPpreload(\"../../_derived/bestimmungsschluessel.htm_cmp_expeditn010_hbtn.gif\"); MSFPnav5h=MSFPpreload(\"../../_derived/bestimmungsschluessel.htm_cmp_expeditn010_hbtn_a.gif\"); }\n"
"// --></script><a href=\"../../bestimmungsschluessel.htm\" language=\"JavaScript\" onmouseover=\"if(MSFPhover) document['MSFPnav5'].src=MSFPnav5h.src\" onmouseout=\"if(MSFPhover) document['MSFPnav5'].src=MSFPnav5n.src\"><img src=\"../../_derived/bestimmungsschluessel.htm_cmp_expeditn010_hbtn.gif\" width=\"140\" height=\"50\" border=\"0\" alt=\"Familien\" align=\"middle\" name=\"MSFPnav5\"></a> <script language=\"JavaScript\"><!--\n"
"if(MSFPhover) { MSFPnav6n=MSFPpreload(\"../../Fundorte/_derived/fundorte.htm_cmp_expeditn010_hbtn.gif\"); MSFPnav6h=MSFPpreload(\"../../Fundorte/_derived/fundorte.htm_cmp_expeditn010_hbtn_a.gif\"); }\n"
"// --></script><a href=\"../../Fundorte/fundorte.htm\" language=\"JavaScript\" onmouseover=\"if(MSFPhover) document['MSFPnav6'].src=MSFPnav6h.src\" onmouseout=\"if(MSFPhover) document['MSFPnav6'].src=MSFPnav6n.src\"><img src=\"../../Fundorte/_derived/fundorte.htm_cmp_expeditn010_hbtn.gif\" width=\"140\" height=\"50\" border=\"0\" alt=\"Fundorte\" align=\"middle\" name=\"MSFPnav6\"></a> <script language=\"JavaScript\"><!--\n"
"if(MSFPhover) { MSFPnav7n=MSFPpreload(\"../../Fachbegriffe/_derived/fachbegriffe.htm_cmp_expeditn010_hbtn.gif\"); MSFPnav7h=MSFPpreload(\"../../Fachbegriffe/_derived/fachbegriffe.htm_cmp_expeditn010_hbtn_a.gif\"); }\n"
"// --></script><a href=\"../../Fachbegriffe/fachbegriffe.htm\" language=\"JavaScript\" onmouseover=\"if(MSFPhover) document['MSFPnav7'].src=MSFPnav7h.src\" onmouseout=\"if(MSFPhover) document['MSFPnav7'].src=MSFPnav7n.src\"><img src=\"../../Fachbegriffe/_derived/fachbegriffe.htm_cmp_expeditn010_hbtn.gif\" width=\"140\" height=\"50\" border=\"0\" alt=\"Fachbegriffe\" align=\"middle\" name=\"MSFPnav7\"></a> <script language=\"JavaScript\"><!--\n"
"if(MSFPhover) { MSFPnav8n=MSFPpreload(\"../../_derived/artenverzeichnis1.htm_cmp_expeditn010_hbtn.gif\"); MSFPnav8h=MSFPpreload(\"../../_derived/artenverzeichnis1.htm_cmp_expeditn010_hbtn_a.gif\"); }\n"
"// --></script><a href=\"../../artenverzeichnis1.htm\" language=\"JavaScript\" onmouseover=\"if(MSFPhover) document['MSFPnav8'].src=MSFPnav8h.src\" onmouseout=\"if(MSFPhover) document['MSFPnav8'].src=MSFPnav8n.src\"><img src=\"../../_derived/artenverzeichnis1.htm_cmp_expeditn010_hbtn.gif\" width=\"140\" height=\"50\" border=\"0\" alt=\"Artenverzeichnis\" align=\"middle\" name=\"MSFPnav8\"></a> <script language=\"JavaScript\"><!--\n"
"if(MSFPhover) { MSFPnav9n=MSFPpreload(\"../../Hilfe/_derived/hilfe.htm_cmp_expeditn010_hbtn.gif\"); MSFPnav9h=MSFPpreload(\"../../Hilfe/_derived/hilfe.htm_cmp_expeditn010_hbtn_a.gif\"); }\n"
"// --></script><a href=\"../../Hilfe/hilfe.htm\" language=\"JavaScript\" onmouseover=\"if(MSFPhover) document['MSFPnav9'].src=MSFPnav9h.src\" onmouseout=\"if(MSFPhover) document['MSFPnav9'].src=MSFPnav9n.src\"><img src=\"../../Hilfe/_derived/hilfe.htm_cmp_expeditn010_hbtn.gif\" width=\"140\" height=\"50\" border=\"0\" alt=\"Hilfe\" align=\"middle\" name=\"MSFPnav9\"></a> <script language=\"JavaScript\"><!--\n"
"if(MSFPhover) { MSFPnav10n=MSFPpreload(\"../../_derived/saatblumen.htm_cmp_expeditn010_hbtn.gif\"); MSFPnav10h=MSFPpreload(\"../../_derived/saatblumen.htm_cmp_expeditn010_hbtn_a.gif\"); }\n"
"// --></script><a href=\"../../saatblumen.htm\" language=\"JavaScript\" onmouseover=\"if(MSFPhover) document['MSFPnav10'].src=MSFPnav10h.src\" onmouseout=\"if(MSFPhover) document['MSFPnav10'].src=MSFPnav10n.src\"><img src=\"../../_derived/saatblumen.htm_cmp_expeditn010_hbtn.gif\" width=\"140\" height=\"50\" border=\"0\" alt=\"Saatblumen\" align=\"middle\" name=\"MSFPnav10\"></a><!--webbot bot=\"Navigation\" endspan i-checksum=\"53857\" -->\n"
"</p>\n"
"<p align=\"center\"><b><font color=\"#FF0000\" size=\"6\">Familie: Süßgräser (Poaceae,\n"
"Graminaceae)</font></b></p>\n"
"<p align=\"center\"><b><font size=\"4\" color=\"#0000FF\">Zur Familie gehören 668\n"
"Gattungen mit ca. 1000 Arten.</font></b></p>\n"
"<p align=\"center\"><b><font color=\"#0000FF\" size=\"4\">Süßgräser sind gekennzeichnet durch einen runden, hohlen\n"
"rundlichen Halm. <br>\n"
"Viele <a href=\"getreide.htm\">Getreidearten</a> gehören zu den Süßgräsern.</font></b></p>\n"
"<p align=\"center\">\n"
"<font size=\"4\" color=\"#0000FF\"><b>> <a href=\"aufbau_suessgras.htm\">Zum\n"
"Aufbau eines Süßgrases</a></b></font></p>\n"
"<!--mstheme--></font><table border=\"1\" width=\"100%\" bordercolordark=\"#660000\" bordercolorlight=\"#CC9966\">\n"
" <tr>\n"
" <td width=\"50%\" align=\"center\" valign=\"top\"><!--mstheme--><font face=\"Book Antiqua, Times New Roman, Times\"><b><font size=\"3\"> Pflanze 1, 5 m -\n"
" 6 m groß<br>\n"
"Halm mindestens 1 cm dick<br>\n"
"> <a href=\"gras_gross.htm\">Große Gräser</a></font></b>\n"
" <p><b><img border=\"0\" src=\"P1530625.JPG_a.jpg\" width=\"272\" height=\"581\"></b><!--mstheme--></font></td>\n"
" <td width=\"50%\" align=\"center\" valign=\"top\"><!--mstheme--><font face=\"Book Antiqua, Times New Roman, Times\"><b><font size=\"3\">\n"
"Pflanzen kleiner<br>\n"
"Halm dünner als 1 cm<br>\n"
"> <a href=\"gras_klein.htm\">Kleine Gräser</a></font></b><!--mstheme--></font></td>\n"
" </tr>\n"
"</table><!--mstheme--><font face=\"Book Antiqua, Times New Roman, Times\">\n"
"<p align=\"left\"><b><font size=\"3\"> </font></b></p>\n"
"<p align=\"left\"> </p>\n"
"<!--mstheme--></font></body>\n\n"
"</html>\n")
matches = re.finditer(regex, test_str, re.MULTILINE)
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