import re
regex = re.compile(r"href\W+=\W+['|\"]([http|https]+://.+)['|\"]", flags=re.MULTILINE)
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 = regex.finditer(test_str)
for match_num, match in enumerate(matches, start=1):
print(f"Match {match_num} was found at {match.start()}-{match.end()}: {match.group()}")
for group_num, group in enumerate(match.groups(), start=1):
print(f"Group {group_num} found at {match.start(group_num)}-{match.end(group_num)}: {group}")
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