2021-01-08 21:08:47 +01:00
|
|
|
import re
|
2021-04-12 19:47:21 +02:00
|
|
|
from typing import (
|
|
|
|
AsyncIterable,
|
|
|
|
Callable,
|
|
|
|
)
|
2021-01-08 21:08:47 +01:00
|
|
|
|
|
|
|
from library.logging import error_log
|
|
|
|
from nexus.pylon.exceptions import RegexNotFoundError
|
|
|
|
|
|
|
|
from .base import (
|
|
|
|
DoiSource,
|
|
|
|
PreparedRequest,
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
class LibgenDoiSource(DoiSource):
|
|
|
|
base_url = 'http://libgen.gs'
|
|
|
|
resolve_timeout = 10
|
|
|
|
|
2021-04-12 19:47:21 +02:00
|
|
|
async def resolve(self, error_log_func: Callable = error_log) -> AsyncIterable[PreparedRequest]:
|
2021-01-08 21:08:47 +01:00
|
|
|
async with self.get_resolve_session() as session:
|
|
|
|
url = f'{self.base_url}/scimag/ads.php?doi={self.doi}'
|
2021-04-12 19:47:21 +02:00
|
|
|
async with PreparedRequest(
|
|
|
|
method='get',
|
|
|
|
url=url,
|
|
|
|
timeout=self.resolve_timeout,
|
|
|
|
).execute_with(session=session) as resp:
|
2021-01-08 21:08:47 +01:00
|
|
|
downloaded_page_bytes = await resp.read()
|
|
|
|
downloaded_page = downloaded_page_bytes.decode('utf-8', 'backslashreplace')
|
|
|
|
match = re.search(
|
|
|
|
'https?://.*/scimag/get\\.php\\?doi=.*&key=[A-Za-z0-9]+',
|
|
|
|
downloaded_page,
|
|
|
|
re.IGNORECASE,
|
|
|
|
)
|
|
|
|
if match:
|
2021-04-12 19:47:21 +02:00
|
|
|
yield PreparedRequest(method='get', url=match.group(), timeout=self.timeout)
|
2021-01-08 21:08:47 +01:00
|
|
|
else:
|
2021-04-12 19:47:21 +02:00
|
|
|
error_log_func(RegexNotFoundError(url=url))
|