path: root/bin/sniff

#!/usr/bin/python3

import argparse
import code
import signal
import sys
import re
from requests import get
from requests.exceptions import RequestException
from contextlib import closing
from bs4 import BeautifulSoup


def SigHandler_SIGINT(signum, frame):
    print()
    sys.exit(0)


def simple_get(url):
    try:
        with closing(get(url, stream=True)) as resp:
            if is_good_response(resp):
                return resp.content
            else:
                return None
    except RequestException as e:
        log_error("Error during requests to {0} : {1}".format(url, str(e)))
        return None


def is_good_response(resp):
    content_type = resp.headers['Content-Type'].lower()
    return (resp.status_code == 200 and content_type is not None and content_type.find("html") > -1)


def log_error(e):
    print(e)


class Argparser(object):
    def __init__(self):
        parser = argparse.ArgumentParser()
        parser.add_argument("--src", type=str, help="url")
        parser.add_argument("--str", type=str, help="what string to look for")
        parser.add_argument("--vid", action="store_true",
                            help="video", default=False)
        parser.add_argument("--dbg", action="store_true",
                            help="debug", default=False)
        parser.add_argument("--url", action="store_true",
                            help="url", default=False)
        self.args = parser.parse_args()


VID_FMT = ["webm", "mpg", "mp2", "mpeg", "mpe", "mpv", "ogg",
           "mp4", "m4p", "m4v", "flv", "avi", "wmv", "mkv", "svi"]
# write code here


def premain(argparser):
    signal.signal(signal.SIGINT, SigHandler_SIGINT)
    # here
    raw_ml = simple_get(argparser.args.src)
    # print("raw html length is " + repr(len(raw_ml)))
    ml = BeautifulSoup(raw_ml, "lxml")
    ml_str = repr(ml)
    tmp = open("/tmp/riecher", "w")
    tmp.write(ml_str)
    tmp.close()
    tmp = open("/tmp/riecher", "r")
    if argparser.args.src:
        if argparser.args.vid:
            for line in tmp:
                # hit = False
                for elem in VID_FMT:
                    if line.find("."+elem) > -1:
                        print(line)
                        # hit = True
    if argparser.args.url:
        dump_list = []
        for line in tmp:
            dummy = re.findall(
                'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', line)
            dump_list += dummy
        for elem in dump_list:
            print(elem)

    tmp.close()


def main():
    argparser = Argparser()
    if argparser.args.dbg:
        try:
            premain(argparser)
        except:
            variables = globals().copy()
            variables.update(locals())
            shell = code.InteractiveConsole(variables)
            shell.interact(banner="DEBUG REPL")
    else:
        premain(argparser)


if __name__ == "__main__":
    main()