# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?:(?:drill|suc+k|lic+k|bang+|stuf+|(?:mother)?fuc*k|fis+t)(?:(?:ing|e[dr])?(?:e?[sz])?)?(?:|\b.{0,80}?\b)(?:pis+|pus+(?:y|ies)|boo+b+|tit+(?:ies)?|coc?k|dick|ass(?:hole)?|penis|phallus|cunt|vag(?:ina)?|genital|ball|rectum|dog+ystyle|blowjob|bitch|bastard|slut+(?:ish)?|harlot|whore|lesbian|queer|homo(?:sexual)?|retard|jew(?:ish)?|nig+(?:er|a)|nic+a|fag(?:g?[eio]t)?|her[ei]tic|idiot|sin+ers|raghead|muslim|hindu|(?:your|him|her|them)\W*sel(?:f|ves))(?:(?:ing|e[dr]|e?)[sz]?)?|(?:pis+|pus+(?:y|ies)|boo+b+|tit+(?:ies)?|coc?k|dick|ass(?:hole)?|penis|phallus|cunt|vag(?:ina)?|genital|ball|rectum|dog+ystyle|blowjob|bitch|bastard|slut+(?:ish)?|harlot|whore|lesbian|queer|homo(?:sexual)?|retard|jew(?:ish)?|nig+(?:er|a)|nic+a|fag(?:g?[eio]t)?|her[ei]tic|idiot|sin+ers|raghead|muslim|hindu|(?:your|him|her|them)\W*sel(?:f|ves))(?:(?:ing|e[dr]|e?)[sz]?)?(?:|\b.{0,80}?\b)(?:drill|suc+k|lic+k|bang+|stuf+(?:ing|ed)|(?:mother)?fuc*k|fis+t)(?:(?:ing|e[dr])?(?:e?[sz])?)?)"
test_str = ("<p>I am afraid this is not easily doable, as modern browsers will block non-HTTPS requests if you are on https website.</p>\n\n"
"<p>I think your best option would be to create your own form, with <code>fromStation</code> and <code>toStation</code> fields, collect this information from user yourself on your website, and then hit the railways website similar way you are doing, but instead of hardcoded URLs, there would be variables provided by the user</p>\n\n"
"<pre><code>$fromStation = $_GET['fromStation']; // this should be sanitized and validated first\n"
"$toStation = $_GET['toStation'];\n\n"
"$content = file_get_contents(\"http://razpisanie.bdz.bg/mobile/search.jsp?fromstation={$fromStation}&tostation={$toStation}\");\n"
"echo $content;\n"
"</code></pre>\n\n"
"<p>This is just a very simple prototype, and you will lose stuff like autocomplete (unless you write it yourself). But unless the Bulgarian railways move their website on https, I am afraid you don't have too many options.</p>")
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