def weblinksIn(text, withoutBracketed=False, onlyBracketed=False):
text = pywikibot.removeDisabledParts(text)
# MediaWiki parses templates before parsing external links. Thus, there
# might be a | or a } directly after a URL which does not belong to
# the URL itself.
# First, remove the curly braces of inner templates:
nestedTemplateR = re.compile(r'{{([^}]*?){{(.*?)}}(.*?)}}')
while nestedTemplateR.search(text):
text = nestedTemplateR.sub(r'{{\1 \2 \3}}', text)
# Then blow up the templates with spaces so that the | and }} will not
# be regarded as part of the link:.
templateWithParamsR = re.compile(r'{{([^}]*?[^ ])\|([^ ][^}]*?)}}',
re.DOTALL)
while templateWithParamsR.search(text):
text = templateWithParamsR.sub(r'{{ \1 | \2 }}', text)
# Add <blank> at the end of a template
# URL as last param of multiline template would not be correct
text = text.replace('}}', ' }}')
# Remove HTML comments in URLs as well as URLs in HTML comments.
# Also remove text inside nowiki links etc.
text = pywikibot.removeDisabledParts(text)
linkR = pywikibot.compileLinkR(withoutBracketed, onlyBracketed)
for m in linkR.finditer(text):
if m.group('url'):
yield m.group('url')
else:
yield m.group('urlb')
def weblinksIn(text, withoutBracketed = False, onlyBracketed = False):
text = pywikibot.removeDisabledParts(text)
# MediaWiki parses templates before parsing external links. Thus, there
# might be a | or a } directly after a URL which does not belong to
# the URL itself.
# First, remove the curly braces of inner templates:
nestedTemplateR = re.compile(r'{{([^}]*?){{(.*?)}}(.*?)}}')
while nestedTemplateR.search(text):
text = nestedTemplateR.sub(r'{{\1 \2 \3}}', text)
# Then blow up the templates with spaces so that the | and }} will not be regarded as part of the link:.
templateWithParamsR = re.compile(r'{{([^}]*?[^ ])\|([^ ][^}]*?)}}',
re.DOTALL)
while templateWithParamsR.search(text):
text = templateWithParamsR.sub(r'{{ \1 | \2 }}', text)
linkR = pywikibot.compileLinkR(withoutBracketed, onlyBracketed)
# Remove HTML comments in URLs as well as URLs in HTML comments.
# Also remove text inside nowiki links etc.
text = pywikibot.removeDisabledParts(text)
for m in linkR.finditer(text):
if m.group('url'):
yield m.group('url')
else:
yield m.group('urlb')