# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"<h4>В главных ролях:<\/h4>\s*<ul>(.*)<\/ul>"
test_str = ("<div id=\"actorList\" class=\"clearfix actorListbg\">\n"
" \n"
" \n"
" \n"
" <h4>В главных ролях:</h4>\n"
" <ul><li itemprop=\"actors\"><a href=\"/name/27959/\">Альберт Брукс</a></li><li itemprop=\"actors\"><a href=\"/name/20162/\">Эллен ДеДженерес</a></li><li itemprop=\"actors\"><a href=\"/name/14715/\">Александр Гоулд</a></li><li itemprop=\"actors\"><a href=\"/name/9274/\">Уиллем Дефо</a></li><li itemprop=\"actors\"><a href=\"/name/6754/\">Эллисон Дженни</a></li><li itemprop=\"actors\"><a href=\"/name/23960/\">Джо Рэнфт</a></li><li itemprop=\"actors\"><a href=\"/name/24683/\">Джеффри Раш</a></li><li itemprop=\"actors\"><a href=\"/name/10781/\">Элизабет Перкинс</a></li><li itemprop=\"actors\"><a href=\"/name/11215/\">Эрик Бана</a></li><li itemprop=\"actors\"><a href=\"/name/23951/\">Эндрю Стэнтон</a></li><li itemprop=\"actors\"><a href=\"/film/7908/cast/\">...</a></li></ul>\n"
" \n"
" \n"
" <h4>Роли дублировали:</h4>\n"
" <ul><li itemprop=\"actors\"><a href=\"/name/298467/\">Ян Цапник</a></li><li itemprop=\"actors\"><a href=\"/name/477449/\">Елена Шульман</a></li><li itemprop=\"actors\"><a href=\"/name/1660135/\">Федор Машанов</a></li><li itemprop=\"actors\"><a href=\"/name/273210/\">Виктор Костецкий</a></li><li itemprop=\"actors\"><a href=\"/name/37388/\">Мария Кузнецова</a></li><li itemprop=\"actors\"><a href=\"/film/7908/cast/\">...</a></li></ul>\n"
" \n"
" <h4><a href=\"/film/7908/cast/\">показать всех</a> »</h4>\n"
" </div>")
matches = re.search(regex, test_str)
if matches:
print ("Match was found at {start}-{end}: {match}".format(start = matches.start(), end = matches.end(), match = matches.group()))
for groupNum in range(0, len(matches.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = matches.start(groupNum), end = matches.end(groupNum), group = matches.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