From d99e8ddb10add0e200b27609c8446915b41822ab Mon Sep 17 00:00:00 2001 From: terminaldweller Date: Sat, 13 Mar 2021 21:01:56 +0330 Subject: added an anime scraper. was wasting too much time checking them manually --- kaminokumo | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/kaminokumo b/kaminokumo index d6d7f4d..c14ae89 100755 --- a/kaminokumo +++ b/kaminokumo @@ -30,6 +30,8 @@ class Argparser(object): help="run as daemon", default=False) parser.add_argument("--manga", action="store_true", help="run manga scraper", default=False) + parser.add_argument("--anime", action="store_true", + help="run anime scraper", default=False) parser.add_argument("--cb", action="store_true", help="run cb scraper", default=False) parser.add_argument("--slumber", type=int, @@ -90,6 +92,28 @@ def manga_scrape(): print(result, end="") +def anime_scrape(): + path = str() + if Path(sys.argv[0]).is_symlink(): + path = os.readlink(sys.argv[0]) + else: + path = sys.argv[0] + + urls = json.load(open(os.path.dirname(path)+"/anime.json")) + requests.packages.urllib3.disable_warnings() + result = str() + for name, url in urls.items(): + resp = requests.get(url, verify=False) + soup = BeautifulSoup(resp.text, "lxml") + search = soup.find_all("a", href=True) + re_res = [] + for thing in search: + re_res.append(re.findall("Episode [0-9]*$", thing.text)) + # print(name+":"+repr(max(re_res))) + result += name+":"+repr(max(re_res)) + "\n" + print(result, end="") + + def vocalize(sound): subprocess.call([os.path.expanduser("~")+"/scripts/voice.sh", sound]) ############################################################################### @@ -101,6 +125,8 @@ def premain(argparser): run_cb_scrape() elif argparser.args.manga: manga_scrape() + elif argparser.args.anime: + anime_scrape() else: pass -- cgit v1.2.3