diff options
Diffstat (limited to '')
| -rwxr-xr-x | bin/sniff | 97 |
1 files changed, 52 insertions, 45 deletions
@@ -1,33 +1,37 @@ -#!/usr/bin/python3 +#!/usr/bin/env python +"""Sniffs different file types in a given URL.""" import argparse -import signal -import sys import re -from requests import get -from requests.exceptions import RequestException -from contextlib import closing -from bs4 import BeautifulSoup +import typing +import contextlib +import requests # type:ignore +import bs4 # type:ignore -def SigHandler_SIGINT(signum, frame): - print() - sys.exit(0) +def log_error(error): + """A logger wrapper.""" + print(error) -def simple_get(url): +def simple_get(url) -> typing.Optional[typing.ByteString]: + """A simple get wrapper.""" try: - with closing(get(url, stream=True)) as resp: + with contextlib.closing( + requests.get(url, stream=True, timeout=10) + ) 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 + except requests.exceptions.RequestException as error: + log_error( + f"Error during requests to {0} : {1}".format(url, str(error)) + ) return None def is_good_response(resp): + """Checks if the response we get is a good response.""" content_type = resp.headers["Content-Type"].lower() return ( resp.status_code == 200 @@ -36,11 +40,10 @@ def is_good_response(resp): ) -def log_error(e): - print(e) - +# pylint: disable=too-few-public-methods +class Argparser: + """Argparser""" -class Argparser(object): def __init__(self): parser = argparse.ArgumentParser() parser.add_argument("--src", type=str, help="url") @@ -49,7 +52,7 @@ class Argparser(object): "--vid", action="store_true", help="video", default=False ) parser.add_argument( - "--dbg", action="store_true", help="debug", default=False + "--img", action="store_true", help="sniff images", default=False ) parser.add_argument( "--url", action="store_true", help="url", default=False @@ -57,7 +60,7 @@ class Argparser(object): self.args = parser.parse_args() -VID_FMT = [ +VID_FMTS = [ "webm", "mpg", "mp2", @@ -74,28 +77,43 @@ VID_FMT = [ "mkv", "svi", ] -# write code here -def premain(argparser): - signal.signal(signal.SIGINT, SigHandler_SIGINT) - # here +def image_finder(url: str) -> None: + """Sniffs images.""" + # raw_url_content = simple_get(url) + response = requests.get(url, timeout=10, allow_redirects=True) + # print(response.content) + if response.content is None: + return None + + soup = bs4.BeautifulSoup(response.content, "lxml") + search_results = soup.findAll("img") + for result in search_results: + print(result["src"]) + # img_response = requests.get( + # result["src"], timeout=10, allow_redirects=True + # ) + return None + + +def main() -> None: + """Entry point.""" + argparser = Argparser() + if argparser.args.img: + image_finder(argparser.args.src) 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") + ml_str = repr(bs4.BeautifulSoup(raw_ml, "lxml")) + tmp = open("/tmp/riecher", "w", encoding="utf-8") tmp.write(ml_str) tmp.close() - tmp = open("/tmp/riecher", "r") + tmp = open("/tmp/riecher", "r", encoding="utf-8") if argparser.args.src: if argparser.args.vid: for line in tmp: - # hit = False - for elem in VID_FMT: + for elem in VID_FMTS: if line.find("." + elem) > -1: print(line) - # hit = True if argparser.args.url: dump_list = [] for line in tmp: @@ -111,16 +129,5 @@ def premain(argparser): tmp.close() -def main(): - argparser = Argparser() - if argparser.args.dbg: - try: - premain(argparser) - except Exception as e: - print(e) - else: - premain(argparser) - - if __name__ == "__main__": main() |