Garmelon/PFERD
1
0
Fork 0
mirror of https://github.com/Garmelon/PFERD.git synced 2026-04-12 15:35:05 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add 'skip' option to crawlers

Browse source
This commit is contained in:
Joscha 2021-06-04 18:33:02 +02:00
parent fc31100a0f
commit df3ad3d890
6 changed files with 48 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

2
PFERD/crawl/__init__.py
View file

@ -3,7 +3,7 @@ from typing import Callable, Dict
from ..auth import Authenticator
from ..config import Config
from .crawler import Crawler, CrawlError # noqa: F401
from .crawler import Crawler, CrawlError, CrawlerSection # noqa: F401
from .ilias import KitIliasWebCrawler, KitIliasWebCrawlerSection
from .local_crawler import LocalCrawler, LocalCrawlerSection

9
PFERD/crawl/crawler.py
View file

@ -132,6 +132,15 @@ class DownloadToken(ReusableAsyncContextManager[Tuple[ProgressBar, FileSink]]):
class CrawlerSection(Section):
def type(self) -> str:
value = self.s.get("type")
if value is None:
self.missing_value("type")
return value
def skip(self) -> bool:
return self.s.getboolean("skip", fallback=False)
def output_dir(self, name: str) -> Path:
# TODO Use removeprefix() after switching to 3.9
if name.startswith("crawl:"):