# parse_html_attribute.py
# Great help from http://bytes.com/topic/python/answers/660853-simpleprograms-challenge
# http://stackoverflow.com/questions/1335507/keyboard-input-with-timeout-in-python
# http://code.activestate.com/recipes/59892/
# https://github.com/collective/collective.xmpp.core/blob/master/collective/xmpp/core/browser/transforms.py
# ... thanks
# RJM Programming
# R. Metcalfe
# January, 2015
#
# Examples of usage:
# echo "My link" | python parse_html_attribute.py title
# ... results in ...
# My title
#
# python parse_html_attribute.py x.html
# ... results in list of href (which is default) attributes with HTML of x.html file in current directory ...
#
# python parse_html_attribute.py < x.html
# ... results in same list as above ...
#
# python parse_html_attribute.py http://localhost:8888/x.html
# ... results in list of href (which is default) attributes with HTML of URL http://localhost:8888/x.html ...
#
# python parse_html_attribute.py http://localhost:8888/x.html style
# ... results in list of style attributes with HTML of URL http://localhost:8888/x.html ...
#
# python parse_html_attribute.py
# ... results in nothing (after 5 seconds ... timeout) ...
from HTMLParser import HTMLParser
import sys
import urllib2
import socket
import ssl
from urlparse import urlparse
import signal
import os.path
TIMEOUT = 5 # number of seconds you want for timeout
def interrupted(signum, frame):
"called when read times out"
sys.exit()
class URLLister(HTMLParser):
def getUrlContent(self, url):
try:
return urllib2.urlopen(url, timeout=5).read()
except ssl.SSLError:
return None
except urllib2.URLError:
return None
except socket.timeout:
return None
except socket.error:
return None
except urllib2.URLError:
return None
def reset(self):
HTMLParser.reset(self)
self.urls = []
def handle_starttag(self, tag, attrs):
try:
# get handler for tag and call it e.g. self.start_a
getattr(self, "start_%s" % tag)(attrs)
except ssl.SSLError:
pass
except urllib2.URLError:
pass
except socket.timeout:
pass
except socket.error:
pass
except AttributeError:
pass
def start_a(self, attrs):
href = [v for k, v in attrs if k == atype]
if href:
self.urls.extend(href)
parser = URLLister()
url = ""
hfound = 0
dfound = 0
one = 1
atype = "href"
try:
# Set URL to that defined on the command line
url = sys.argv[1]
try:
dfound = url.lower().index(".")
except ValueError:
atype = url
url = ""
if (dfound >= 0):
one = 2
except IndexError:
url = ""
try:
# Set attribute type to look for
atype = sys.argv[one]
except IndexError:
pass
try:
if (url == ""):
# Get URL (or file) contents piped in, or from stdin redirected via input file
signal.signal(signal.SIGALRM, interrupted)
signal.alarm(TIMEOUT)
try:
parser.feed(sys.stdin.read())
except:
pass
else:
try:
hfound = url.lower().index("http://")
except ValueError:
try:
hfound = url.lower().index("https://")
except ValueError:
try:
hfound = url.lower().index("file://")
except ValueError:
try:
hfound = -999
if (os.path.isfile(url)):
hfound = -1
except:
pass
if (hfound >= 0):
# Get URL contents from URL defined on the command line
content = parser.getUrlContent(url)
elif (hfound == -1):
# Open a file whose name was a parameter on command line
fo = open(url, "r+")
# Get URL contents from contents of this file
content = fo.read();
# Close opened file
fo.close()
else:
content = ""
parser.feed(content)
signal.alarm(0)
parser.close()
for url in parser.urls:
print url
except urllib2.URLError as e:
print type(e)
except socket.timeout as e:
print type(e)