def checkHTML(self, html, url):
"""Parses html content or any arbitrary text for links and returns result of `checkURLs`
:param html: html source
:return:
"""
urls = []
if html:
urls += [x[0] for x in urlmatcher.findall(html)]
if url:
page = getURL(url)
urls += [x[0] for x in urlmatcher.findall(page)]
return self.checkLinks(uniqify(urls))
def checkHTML(self, html, url):
"""Parses html content or any arbitrary text for links and returns result of `checkURLs`
:param html: html source
:return:
"""
urls = []
if html:
urls += [x[0] for x in urlmatcher.findall(html)]
if url:
page = getURL(url)
urls += [x[0] for x in urlmatcher.findall(page)]
return self.checkLinks(uniqify(urls))
def parseURLs(self, html=None, url=None):
"""Parses html content or any arbitrary text for links and returns result of `checkURLs`
:param html: html source
:return:
"""
urls = []
if html:
urls += [x[0] for x in urlmatcher.findall(html)]
if url:
page = getURL(url)
urls += [x[0] for x in urlmatcher.findall(page)]
# remove duplicates
return self.checkURLs(set(urls))
def parseURLs(self, html=None, url=None):
"""Parses html content or any arbitrary text for links and returns result of `checkURLs`
:param html: html source
:return:
"""
urls = []
if html:
urls += [x[0] for x in urlmatcher.findall(html)]
if url:
page = getURL(url)
urls += [x[0] for x in urlmatcher.findall(page)]
# remove duplicates
return self.checkURLs(set(urls))
