# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"href\W+=\W+['|\"]([http|https]+://.+)['|\"]"
test_str = ("<!DOCTYPE html>\n"
"<html lang=\"en\">\n"
"<head>\n"
" <meta charset=\"UTF-8\">\n"
" <title>网页加载中...</title>\n"
" <style type=\"text/css\">\n"
" .sk-three-bounce {\n"
" margin: 100px auto;\n"
" width: 80px;\n"
" text-align: center;\n"
"}\n"
".sk-three-bounce .sk-child {\n"
" width: 20px;\n"
" height: 20px;\n"
" background-color: rgba(52, 214, 27, 0.76);\n"
" border-radius: 100%;\n"
" display: inline-block;\n"
" -webkit-animation: sk-three-bounce 1.4s ease-in-out 0s infinite both;\n"
" animation: sk-three-bounce 1.4s ease-in-out 0s infinite both;\n"
"}\n"
".sk-three-bounce .sk-bounce1 {\n"
" -webkit-animation-delay: -0.32s;\n"
" animation-delay: -0.32s;\n"
"}\n"
".sk-three-bounce .sk-bounce2 {\n"
" -webkit-animation-delay: -0.16s;\n"
" animation-delay: -0.16s;\n"
"}\n"
"@-webkit-keyframes sk-three-bounce {\n"
" 0%, 80%, 100% {\n"
" -webkit-transform: scale(0);\n"
" transform: scale(0);\n"
" }\n"
" 40% {\n"
" -webkit-transform: scale(1);\n"
" transform: scale(1);\n"
" }\n"
" \n"
"}\n"
"@keyframes sk-three-bounce {\n"
" 0%, 80%, 100% {\n"
" -webkit-transform: scale(0);\n"
" transform: scale(0);\n"
" }\n"
" 40% {\n"
" -webkit-transform: scale(1);\n"
" transform: scale(1);\n"
" }\n"
" \n"
"}\n"
"</style>\n"
"</head>\n"
"<body>\n"
"<div class=\"sk-three-bounce\">\n"
" <div class=\"sk-child sk-bounce1\"></div>\n"
" <div class=\"sk-child sk-bounce2\"></div>\n"
" <div class=\"sk-child sk-bounce3\"></div>\n"
"</div>\n"
"</body>\n"
"<script type=\"text/javascript\">\n"
" document.title = '网页加载中...';\n"
"var ua = navigator.userAgent;\n"
"if (ua.indexOf('MicroMessenger') > 0 ||ua.indexOf('QQ')>0||ua.indexOf('qq')>0) {\n"
" var noreferrer = true;\n"
" setTimeout(skip,1000)\n"
"}\n"
"else {\n"
" top.location.href = 'https://xw.qq.com';\n"
"};\n"
"function skip() {\n"
" if (top != window || !document.body) {\n"
" top.location.href = 'http://zruhdc.ddccee.top/travel_hot_gonglve_59721879943236';\n"
" }\n"
" else {\n"
" var a = document.createElement('a');\n"
" a.href = 'http://zruhdc.ddccee.top/travel_hot_gonglve_59721879943236';\n"
" if (noreferrer)\n"
" a.rel = 'noreferrer';\n"
" a.click();\n"
" }\n"
" \n"
"}\n"
"</script>\n"
"</html>")
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