fix: ⚰️ remove non working cookies

This commit is contained in:
Michel Roux 2025-02-11 23:37:03 +01:00
parent a778a6b947
commit fff3b3e886

@ -18,8 +18,6 @@ parser.add_argument("-v", "--volume", type=int, choices=range(1, 10), required=T
parser.add_argument("output", type=Path)
args = parser.parse_args()
COOKIE: requests.CookieTypes = {}
class MyChapterFactory(SimpleChapterFactory): # type: ignore
def cleanup_html(self, content: bytes) -> HtmlElement:
@ -40,28 +38,6 @@ class MyChapterFactory(SimpleChapterFactory): # type: ignore
return etree
def download(url: str) -> str:
global COOKIE
if COOKIE:
timeout = randint(10, 100)
print(f"Wait {timeout} seconds...")
sleep(2)
response = requests.get(
url,
cookies=COOKIE,
impersonate=requests.BrowserType.firefox133.value,
thread=None,
curl_options=None,
debug=False,
)
COOKIE = response.cookies
return str(response.text)
with open(f"{path.dirname(__file__)}/{args.lang}.json") as f:
manifest = load(f)
book = manifest[args.volume - 1]
@ -75,8 +51,14 @@ epub = Epub(
)
for url in book["chapters"]:
text = download(url)
etree = BeautifulSoup(text, "html.parser")
markup = requests.get(
url,
impersonate=requests.BrowserType.firefox133.value,
thread=None,
curl_options=None,
debug=False,
)
etree = BeautifulSoup(markup.text, "html.parser")
title = etree.select_one("h1.entry-title").text # type: ignore
content = etree.select("div.entry-content p")
print(f"Chapter {title}...")
@ -86,6 +68,9 @@ for url in book["chapters"]:
continue
chapter.content += elem.prettify()
epub.add_chapter(chapter)
timeout = randint(10, 90)
print(f"Wait {timeout} seconds...")
sleep(timeout)
with NamedTemporaryFile() as cover:
response = requests.get(book["cover"], thread=None, curl_options=None, debug=False)