"""
pointer = 0
for p in positions:
content += escape(source[pointer:p])
content += start_css
pointer = source.find('',p) + 4
content += escape(source[p:pointer]) # lenght of is 4
content += end_css
content += escape(source[pointer:])
content += """
"""
return content
def get_source_code(url):
req = urllib2.Request(url, headers={"Accept" : "*/*"})
try:
usock = urllib2.urlopen(req, timeout = 120)
source = usock.read()
usock.close()
return source.decode('utf-8','ignore')
except urllib2.HTTPError as httperr:
print "HTTP Error : %s : %s" % (httperr.code, httperr.reason)
return 'Error'
def clear_source (source):
''' Removes certain code from a HTML source
Given a HTML source, it clear certain code that is of no interest, i.e.
comments, and returns that string. Can be extended to exclude any code that
should not be parsed for URLs, as desired.
'''
while source.find("", pos)
#if epos > source.find(""):]
return source
def get_position(pointers):
url = pointers.split('|')
url.pop() #last element is empty string so to remove it
positions = []
for u in url:
positions.append(int(u.split(';')[1]))
positions.sort()
return positions