Fix mypy errors and add missing await

This commit is contained in:
Joscha 2022-04-27 22:50:06 +02:00
parent 31631fb409
commit 602044ff1b
2 changed files with 13 additions and 13 deletions

View File

@ -1,9 +1,10 @@
import asyncio import asyncio
import os import os
from abc import ABC, abstractmethod from abc import ABC, abstractmethod
from collections.abc import Awaitable, Coroutine
from datetime import datetime from datetime import datetime
from pathlib import Path, PurePath from pathlib import Path, PurePath
from typing import Any, Awaitable, Callable, Dict, List, Optional, Sequence, Set, Tuple, TypeVar from typing import Any, Callable, Dict, List, Optional, Sequence, Set, Tuple, TypeVar
from ..auth import Authenticator from ..auth import Authenticator
from ..config import Config, Section from ..config import Config, Section
@ -58,7 +59,7 @@ def noncritical(f: Wrapped) -> Wrapped:
return wrapper # type: ignore return wrapper # type: ignore
AWrapped = TypeVar("AWrapped", bound=Callable[..., Awaitable[Optional[Any]]]) AWrapped = TypeVar("AWrapped", bound=Callable[..., Coroutine[Any, Any, Optional[Any]]])
def anoncritical(f: AWrapped) -> AWrapped: def anoncritical(f: AWrapped) -> AWrapped:

View File

@ -1,7 +1,8 @@
import asyncio import asyncio
import re import re
from collections.abc import Awaitable, Coroutine
from pathlib import PurePath from pathlib import PurePath
from typing import Any, Awaitable, Callable, Dict, List, Optional, Set, TypeVar, Union, cast from typing import Any, Callable, Dict, List, Optional, Set, Union, cast
import aiohttp import aiohttp
import yarl import yarl
@ -13,7 +14,7 @@ from ...config import Config
from ...logging import ProgressBar, log from ...logging import ProgressBar, log
from ...output_dir import FileSink, Redownload from ...output_dir import FileSink, Redownload
from ...utils import fmt_path, soupify, url_set_query_param from ...utils import fmt_path, soupify, url_set_query_param
from ..crawler import CrawlError, CrawlToken, CrawlWarning, DownloadToken, anoncritical from ..crawler import AWrapped, CrawlError, CrawlToken, CrawlWarning, DownloadToken, anoncritical
from ..http_crawler import HttpCrawler, HttpCrawlerSection from ..http_crawler import HttpCrawler, HttpCrawlerSection
from .file_templates import Links from .file_templates import Links
from .kit_ilias_html import IliasElementType, IliasPage, IliasPageElement from .kit_ilias_html import IliasElementType, IliasPage, IliasPageElement
@ -82,8 +83,6 @@ _VIDEO_ELEMENTS: Set[IliasElementType] = set([
IliasElementType.VIDEO_FOLDER_MAYBE_PAGINATED, IliasElementType.VIDEO_FOLDER_MAYBE_PAGINATED,
]) ])
AWrapped = TypeVar("AWrapped", bound=Callable[..., Awaitable[Optional[Any]]])
def _iorepeat(attempts: int, name: str, failure_is_error: bool = False) -> Callable[[AWrapped], AWrapped]: def _iorepeat(attempts: int, name: str, failure_is_error: bool = False) -> Callable[[AWrapped], AWrapped]:
def decorator(f: AWrapped) -> AWrapped: def decorator(f: AWrapped) -> AWrapped:
@ -252,7 +251,7 @@ instance's greatest bottleneck.
url: str, url: str,
parent: IliasPageElement, parent: IliasPageElement,
path: PurePath, path: PurePath,
) -> Optional[Awaitable[None]]: ) -> Optional[Coroutine[Any, Any, None]]:
maybe_cl = await self.crawl(path) maybe_cl = await self.crawl(path)
if not maybe_cl: if not maybe_cl:
return None return None
@ -310,7 +309,7 @@ instance's greatest bottleneck.
self, self,
parent_path: PurePath, parent_path: PurePath,
element: IliasPageElement, element: IliasPageElement,
) -> Optional[Awaitable[None]]: ) -> Optional[Coroutine[Any, Any, None]]:
if element.url in self._visited_urls: if element.url in self._visited_urls:
raise CrawlWarning( raise CrawlWarning(
f"Found second path to element {element.name!r} at {element.url!r}. Aborting subpath" f"Found second path to element {element.name!r} at {element.url!r}. Aborting subpath"
@ -360,7 +359,7 @@ instance's greatest bottleneck.
self, self,
element: IliasPageElement, element: IliasPageElement,
element_path: PurePath, element_path: PurePath,
) -> Optional[Awaitable[None]]: ) -> Optional[Coroutine[Any, Any, None]]:
log.explain_topic(f"Decision: Crawl Link {fmt_path(element_path)}") log.explain_topic(f"Decision: Crawl Link {fmt_path(element_path)}")
log.explain(f"Links type is {self._links}") log.explain(f"Links type is {self._links}")
@ -407,7 +406,7 @@ instance's greatest bottleneck.
self, self,
element: IliasPageElement, element: IliasPageElement,
element_path: PurePath, element_path: PurePath,
) -> Optional[Awaitable[None]]: ) -> Optional[Coroutine[Any, Any, None]]:
log.explain_topic(f"Decision: Crawl Booking Link {fmt_path(element_path)}") log.explain_topic(f"Decision: Crawl Booking Link {fmt_path(element_path)}")
log.explain(f"Links type is {self._links}") log.explain(f"Links type is {self._links}")
@ -443,7 +442,7 @@ instance's greatest bottleneck.
if hdrs.LOCATION not in resp.headers: if hdrs.LOCATION not in resp.headers:
return soupify(await resp.read()).select_one("a").get("href").strip() return soupify(await resp.read()).select_one("a").get("href").strip()
self._authenticate() await self._authenticate()
async with self.session.get(export_url, allow_redirects=False) as resp: async with self.session.get(export_url, allow_redirects=False) as resp:
# No redirect means we were authenticated # No redirect means we were authenticated
@ -456,7 +455,7 @@ instance's greatest bottleneck.
self, self,
element: IliasPageElement, element: IliasPageElement,
element_path: PurePath, element_path: PurePath,
) -> Optional[Awaitable[None]]: ) -> Optional[Coroutine[Any, Any, None]]:
# Copy old mapping as it is likely still relevant # Copy old mapping as it is likely still relevant
if self.prev_report: if self.prev_report:
self.report.add_custom_value( self.report.add_custom_value(
@ -564,7 +563,7 @@ instance's greatest bottleneck.
self, self,
element: IliasPageElement, element: IliasPageElement,
element_path: PurePath, element_path: PurePath,
) -> Optional[Awaitable[None]]: ) -> Optional[Coroutine[Any, Any, None]]:
maybe_dl = await self.download(element_path, mtime=element.mtime) maybe_dl = await self.download(element_path, mtime=element.mtime)
if not maybe_dl: if not maybe_dl:
return None return None