# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"<div class=\"img-with-caption\".*url\((.*)\)"
test_str = ("<div class=\"article-text\">\n"
" <p>Some text with <a href=\"/www.example.com/articles/49135\" target=\"_blank\">link</a>. </p>\n"
" <p>Some other text</p>\n"
" <div class=\"post-slideshow js-slider\" style=\"overflow: hidden; visibility: visible;\">\n"
" <div style=\"list-style: none; margin: 0px; width: 1710px; transition: 0ms; -webkit-transition: 0ms; -webkit-transform: translate3d(0px, 0px, 0px);\">\n"
" <div style=\"display: table-cell; width: 285px; vertical-align: top;\">\n"
" <div class=\"img-with-caption\" style=\"background-image: url(/lamcdn.net/example.com/post_image-image/2T30WPIWIUV1OUokYrlIbQ-small.jpg)\"></div>\n"
" <div class=\"slide-caption\"><span class=\"text\"></span>\n"
" </div>\n"
" </div>\n"
" <div style=\"display: table-cell; width: 285px; vertical-align: top;\">\n"
" <div class=\"img-with-caption\" style=\"background-image: url(/lamcdn.net/example.com/post_image-image/oWdXjCe7bnoUtGyqnlggBA-small.jpg)\"></div>\n"
" <div class=\"slide-caption\"><span class=\"text\"></span>\n"
" </div>\n"
" </div>\n"
" <!-- more images here -->\n"
" <div class=\"custom_slide\" style=\"display: table-cell; width: 285px; vertical-align: top;\"></div>\n"
" </div>\n"
" <div class=\"slideshow-counter\"><span class=\"current\">1</span> / <span class=\"total\">5</span>\n"
" </div>\n"
" </div>\n"
" <p class=\"small sasha-text\"><strong>Images:</strong> «<a href=\"/www.example.com/\" target=\"_blank\">Example Studio</a>»</p>\n"
" <p>Some other text.</p>\n"
"</div>")
matches = re.finditer(regex, test_str)
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