# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"<a[^>]*?href=([\"\'])?((?:.(?!\1|>))*.?)\1?"
test_str = ("<li class=\"navItem \"><a href=\"/services/\" lang=\"de\" hreflang=\"de\">Services</a></li>\n"
"<a class=\"iMacLink\" href=\"/portfolio/\" ><div class=\"iMacOverlay\"></div><div class=\"\">Super</div></a></div>\n"
"<div class=\"addthis_toolbox addthis_default_style\">\n"
"<a itemprop=\"url\" target=\"_blank\" href=\"https://www.facebook.com/any-profile\" title=\"facebook\" class=\"facebookSite\"><span class=\"icon-facebook\"></span></a>\n"
"<a itemprop=\"url\" target=\"_blank\" href=\"https://twitter.com/any-profile\" title=\"twitter\" class=\"twitterSite\"><span class=\"icon-twitter\"></span></a>\n"
"<a itemprop=\"url\" target=\"_blank\" href=\"https://pinterest.com/any-profile\" title=\"pinterest\" class=\"pinterestSite\"><span class=\"icon-pinterest\"></span></a>\n"
"<a itemprop=\"url\" target=\"_blank\" href=\"//feeds.feedburner.comany-profile?format=xml\" title=\"rss\" class=\"rss\"><span class=\"icon-rss\"></span></a>\n"
"</div>\n\n\n"
"<a class=\"social facebookProfil\" href=\"http://www.facebook.com/any-profile\">Facebook</a>\n"
"<a class=\"social facebookProfil\" href='https://www.facebook.com/single-quotes'>Facebook</a>\n"
"<a class=\"social facebookProfil\" href=https://www.facebook.com/no-quotes>Facebook</a>\n"
"<a class=\"social youtubeProfil\" href=\"http://www.youtube.com/user/any-profile\">Youtube</a>\n\n"
"<a class=\"social vimeoProfil\" href=\"http://vimeo.com/any-profile\">Vimeo</a>\n"
"<a class=\"social xingProfil\" href=\"https://www.xing.com/companies/any-profile\">XING</a>\n"
"<a class=\"social twitterProfil\" href=\"https://twitter.com/any-profile\">Folge bei Twitter</a>\n\n"
"<a href=\"https://www.instagram.com/p/CN-Kx40nOW0/\">Instagram Beitrag</a>\n"
"<a href=\"http://instagram.com/quellenhofaachen\">Instagram Profil</a>\n"
"<a href=\"https://www.instagram.com/explore/tags/url\">Instagram Tag-Url</a>\n"
"<A href=\"https://www.Instagram.com/uppercase-link\">Upercase-link</A>\n\n"
"<a href=\"http://instagram.com/unique\">Unique-test http</a>\n"
"<a href=\"//instagram.com/unique\">Unique-test protocol relative</a>\n"
"<a href=\"https://instagram.com/unique\">Unique-test https</a>\n"
"<a href=\"http://www.instagram.com/unique\">Unique-test www</a>\n\n\n")
matches = re.finditer(regex, test_str, 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