def folder(url, dirname):
location = url + dirname
msg = (htmlconv.h3(('>-- ' + dirname)))
try:
f = urllib.request.urlopen(location).getcode()
except urllib.error.HTTPError as err:
return (msg + htmlconv.perror(dirname + ' ' + str(err)))
return (msg + htmlconv.p('found at ' + location))
def file(url, filename):
location = (url + filename)
msg = (htmlconv.h3('>-- ' + filename + ' File'))
try:
f = urllib.request.urlopen(location).getcode()
except urllib.error.HTTPError as err:
return (msg + htmlconv.perror(filename + ' ' + str(err)))
return (msg + htmlconv.p('found at ' + url))
def file(url, filename):
location = (url + filename)
msg = (htmlconv.h3('>-- ' + filename + ' File'))
try:
f = urllib.request.urlopen(location).getcode()
except urllib.error.HTTPError as err:
return (msg + htmlconv.perror(filename + ' ' + str(err)))
return (msg + htmlconv.p('found at ' + url))
def folder(url, dirname):
location = url + dirname
msg = (htmlconv.h3(('>-- ' + dirname)))
try:
f = urllib.request.urlopen(location).getcode()
except urllib.error.HTTPError as err:
return (msg + htmlconv.perror(dirname + ' ' + str(err)))
return (msg + htmlconv.p('found at ' + location))
output.append(htmlconv.h1(('Scanning URL ' + str(urls[0]))))
urls.pop(0)
# DO NOT MESS WITH THIS FOR LOOP; IF YOU GET IT WRONG IT CAN ESCAPE YOUR URL AND
# GO INTO THE WILD. YOU ARE WARNED..
for tag in soup.findAll('a', href=True):
tag['href'] = urljoin(url, tag['href'])
if url in tag['href'] and tag['href'] not in visited:
urls.append(tag['href'])
visited.append(tag['href'])
output.append(htmlconv.h2('HTML Structure'))
if len(soup.findAll('head')) == 0:
output.append(htmlconv.perror('You should have a <code><head></code> section in your HTML5'))
elif len(soup.findAll('head')) == 1:
output.append(htmlconv.psuccess('Single <code><head></code> section found for page; ✔'))
else:
output.append(htmlconv.perror('You should only have a single <code><head></code> section per page. You have used more than one on this page'))
output.append(htmlconv.p(('Meta:' + str(len(soup.findAll('meta'))))))
output.append(htmlconv.p(('Links:' + str(len(soup.findAll('link', href=True))))))
if len(soup.findAll('nav')) == 0:
output.append(htmlconv.perror('You should have a nav section in your HTML5'))
elif len(soup.findAll('nav')) == 1:
output.append(htmlconv.psuccess('Single <code><nav></code> section found for page; ✔'))
else:
output.append(htmlconv.perror('You should only have a single <code><nav></code> tag per page. You have used more than one on this page') )
