# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"<img.+?class=[\"'].*?hero-class.*?[\"'].*?src=[\"'](.+?)[\"'].*?>"
test_str = ("// it should match but it didn't\n"
"<img src=\"image.jpg\" class=\"hero-class\">\n\n"
"// it shouldn't match class 'nohero-class-dont-match'\n"
"<img class=\"nohero-class-dont-match\" src=\"image.jpg\">\n\n"
"// it shouldn't match custom tag 'imgs-tag'\n"
"<imgs-tag class=\"hero-class\" src=\"image.jpg\">\n\n"
"// it shouldn't match two tags and text between them\n"
"<img src=\"foo.jpg\" class=\"hero-class\"> any text <img src=\"image.jpg\">\n\n"
"// it should match whole src attribute, not just part\n"
"<img class=\"hero-class\" src=\"mcdonald's.jpg\">\n\n"
"// it shouldn't match custom attribute 'data-src'\n"
"<img class=\"hero-class\" data-src=\"custom info\" src=\"image.jpg\">\n\n\n")
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