# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"href=\"([^\"]+)\""
test_str = (" <!DOCTYPE html>\n"
" <html lang=\"fr\">\n\n"
" <head></head>\n"
" <body>\n"
" <div id=\"wm-ipp\" class=\"\" lang=\"en\" style=\"display: block;\"></div>\n"
" <!--\n\n"
" BEGIN WAYBACK TOOLBAR INSERT \n\n"
" -->\n"
" <script src=\"/static/js/disclaim-element.js\" type=\"text/javascript\"></script>\n"
" <script src=\"/static/js/graph-calc.js\" type=\"text/javascript\"></script>\n"
" <script src=\"/static/jflot/jquery.min.js\" type=\"text/javascript\"></script>\n"
" <script type=\"text/javascript\"></script>\n"
" <style type=\"text/css\"></style>\n"
" <script type=\"text/javascript\"></script>\n"
" <!--\n\n"
" END WAYBACK TOOLBAR INSERT \n\n"
" -->\n"
" <header id=\"main_header\">\n"
" <div class=\"header_content\"></div>\n"
" </header>\n"
" <div id=\"main_content\">\n"
" <div id=\"under_top_event\"></div>\n"
" <div id=\"breadcrumbs\"></div>\n"
" <div id=\"main_search\"></div>\n"
" <div id=\"content\">\n"
" <div id=\"page_test\" class=\"home\">\n"
" <div id=\"topline\">\n"
" <h1>\n\n"
" TESTS\n\n"
" </h1>\n"
" </div>\n"
" <div class=\"large_column left_column\">\n"
" <a class=\"top\" title=\"Lire le test : The Final Fantasy\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-65-the-final-fantasy-3ds-page-opinion.html\"></a>\n"
" <div class=\"separation\" style=\"margin: 20px 0;\"></div>\n"
" <a class=\"high\" title=\"Lire le test : El Shaddai : Ascension of The Metatron\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-63-el-shaddai-ascension-of-the-metatron-ps3-page-opinion.html\"></a>\n"
" <a class=\"high\" title=\"Lire le test : Heroes of Ruin\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-62-heroes-of-ruin-3ds-page-opinion.html\"></a>\n"
" <a class=\"high\" title=\"Lire le test : Prototype 2\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-61-prototype-2-ps3-page-opinion.html\"></a>\n"
" <a class=\"high\" title=\"Lire le test : Rayman Origins\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-60-rayman-origins-ps3-page-opinion.html\"></a>\n"
" </div>\n"
" <div class=\"medium_column right_column\" style=\"padding-top: 70px;\">\n"
" <a class=\"medium\" title=\"Lire le test : Mass Effect 3\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-59-mass-effect-3-x360-page-opinion.html\">\n"
" <span class=\"small title\"></span>\n"
" <span class=\"put_score score\"></span>\n"
" <span class=\"description\"></span>\n"
" </a>\n"
" <div class=\"separation\" style=\"margin: 10px 0;\"></div>\n"
" <a class=\"medium\" title=\"Lire le test : Pandora's Tower\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-58-pandoras-tower-wii-page-opinion.html\">\n"
" <span class=\"small title\"></span>\n"
" <span class=\"put_score score\"></span>\n"
" <span class=\"description\"></span>\n"
" </a>\n"
" <div class=\"separation\" style=\"margin: 10px 0;\"></div>\n"
" <a class=\"medium\" title=\"Lire le test : I am alive\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-57-i-am-alive-x360-page-opinion.html\"></a>\n"
" <div class=\"separation\" style=\"margin: 10px 0;\"></div>\n"
" <a class=\"medium\" title=\"Lire le test : Silent hill downpour\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-56-silent-hill-downpour-ps3-page-opinion.html\"></a>\n"
" <div class=\"separation\" style=\"margin: 10px 0;\"></div>\n"
" <a class=\"medium\" title=\"Lire le test : Naruto Storm Generations\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-55-naruto-storm-generations-x360-page-opinion.html\"></a>\n"
" <div class=\"separation\" style=\"margin: 10px 0;\"></div>\n"
" <a class=\"medium\" title=\"Lire le test : Street Fighter x Tekken\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-54-street-fighter-x-tekken-ps3-page-opinion.html\"></a>\n"
" <div class=\"separation\" style=\"margin: 10px 0;\"></div>\n"
" <a class=\"medium\" title=\"Lire le test : Ninja Gaiden 3\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-53-ninja-gaiden-3-ps3-page-opinion.html\"></a>\n"
" <div class=\"separation\" style=\"margin: 10px 0;\"></div>\n"
" <a class=\"medium\" title=\"Lire le test : Asura's Wrath\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-52-asuras-wrath-ps3-page-opinion.html\"></a>\n"
" <div class=\"separation\" style=\"margin: 10px 0;\"></div>\n"
" <a class=\"medium\" title=\"Lire le test : The Last Story\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-51-the-last-story-wii-page-opinion.html\"></a>\n"
" <div class=\"separation\" style=\"margin: 10px 0;\"></div>\n"
" <a class=\"medium\" title=\"Lire le test : Xenoblade\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-50-xenoblade-wii-page-opinion.html\"></a>\n"
" <div class=\"separation\" style=\"margin: 10px 0;\"></div>\n"
" <a class=\"medium\" title=\"Lire le test : SSX\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-48-ssx-ps3-page-opinion.html\"></a>\n"
" <div class=\"separation\" style=\"margin: 10px 0;\"></div>\n"
" <a class=\"medium\" title=\"Lire le test : Syndicate\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-47-syndicate-pc-page-opinion.html\"></a>\n"
" <div class=\"separation\" style=\"margin: 10px 0;\"></div>\n"
" <a class=\"medium\" title=\"Lire le test : Resident Evil Revelations\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-46-resident-evil-revelations-3ds-page-opinion.html\"></a>\n"
" <div class=\"separation\" style=\"margin: 10px 0;\"></div>\n"
" <a class=\"medium\" title=\"Lire le test : Binary Domain\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-45-binary-domain-ps3-page-opinion.html\"></a>\n"
" <div class=\"separation\" style=\"margin: 10px 0;\"></div>\n"
" <a class=\"medium\" title=\"Lire le test : Catherine\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-43-catherine-x360-page-opinion.html\"></a>\n"
" <div class=\"separation\" style=\"margin: 10px 0;\"></div>\n"
" <a class=\"medium\" title=\"Lire le test : Soulcalibur V\" href=\"/web/20121023121603/http://www.gameweb.fr/articles/test-44-soulcalibur-v-ps3-page-opinion.html\"></a>\n"
" <div class=\"separation\" style=\"margin: 10px 0;\"></div>\n"
" </div>\n"
" </div>\n"
" </div>\n"
" </div>\n"
" <footer id=\"main_footer\"></footer>\n"
" </body>\n"
" </html>\n"
" <!--\n\n\n"
" FILE ARCHIVED ON 12:16:03 oct. 23, 2012 AND …\n\n"
" -->\n")
matches = re.finditer(regex, test_str)
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