mirror of https://github.com/Garmelon/PFERD.git
Compare commits
4 Commits
b1d42f8b70
...
fd2c4f1e9c
Author | SHA1 | Date |
---|---|---|
Julius Rüberg | fd2c4f1e9c | |
I-Al-Istannen | e9f8901520 | |
Julius Rüberg | 77c1f1516c | |
Julius Rüberg | 9e12e96d90 |
|
@ -92,6 +92,9 @@ common to all crawlers:
|
|||
load for the crawl target. (Default: `0.0`)
|
||||
- `windows_paths`: Whether PFERD should find alternative names for paths that
|
||||
are invalid on Windows. (Default: `yes` on Windows, `no` otherwise)
|
||||
- `aliases`: List of strings that are considered as an alias when invoking with
|
||||
the `--crawler` or `-C` flag. If there is more than one crawl section with
|
||||
the same aliases all are selected. Thereby, you can group different crawlers.
|
||||
|
||||
Some crawlers may also require credentials for authentication. To configure how
|
||||
the crawler obtains its credentials, the `auth` option is used. It is set to the
|
||||
|
@ -106,6 +109,7 @@ username = foo
|
|||
password = bar
|
||||
|
||||
[crawl:something]
|
||||
aliases = [sth, some]
|
||||
type = some-complex-crawler
|
||||
auth = auth:example
|
||||
on_conflict = no-delete
|
||||
|
|
|
@ -81,7 +81,7 @@ class KitIliasWebCrawlerSection(HttpCrawlerSection):
|
|||
return self.s.getboolean("forums", fallback=False)
|
||||
|
||||
|
||||
_DIRECTORY_PAGES: Set[IliasElementType] = set([
|
||||
_DIRECTORY_PAGES: Set[IliasElementType] = {
|
||||
IliasElementType.EXERCISE,
|
||||
IliasElementType.EXERCISE_FILES,
|
||||
IliasElementType.FOLDER,
|
||||
|
@ -90,16 +90,16 @@ _DIRECTORY_PAGES: Set[IliasElementType] = set([
|
|||
IliasElementType.MEDIACAST_VIDEO_FOLDER,
|
||||
IliasElementType.OPENCAST_VIDEO_FOLDER,
|
||||
IliasElementType.OPENCAST_VIDEO_FOLDER_MAYBE_PAGINATED,
|
||||
])
|
||||
}
|
||||
|
||||
_VIDEO_ELEMENTS: Set[IliasElementType] = set([
|
||||
_VIDEO_ELEMENTS: Set[IliasElementType] = {
|
||||
IliasElementType.MEDIACAST_VIDEO_FOLDER,
|
||||
IliasElementType.MEDIACAST_VIDEO,
|
||||
IliasElementType.OPENCAST_VIDEO,
|
||||
IliasElementType.OPENCAST_VIDEO_PLAYER,
|
||||
IliasElementType.OPENCAST_VIDEO_FOLDER,
|
||||
IliasElementType.OPENCAST_VIDEO_FOLDER_MAYBE_PAGINATED,
|
||||
])
|
||||
}
|
||||
|
||||
|
||||
def _iorepeat(attempts: int, name: str, failure_is_error: bool = False) -> Callable[[AWrapped], AWrapped]:
|
||||
|
@ -561,8 +561,8 @@ instance's greatest bottleneck.
|
|||
# If we do not want to crawl it (user filter) or we have every file
|
||||
# from the cached mapping already, we can ignore this and bail
|
||||
if not maybe_dl or self._all_opencast_videos_locally_present(element_path):
|
||||
# Mark all existing cideos as known so they do not get deleted
|
||||
# during dleanup. We "downloaded" them, just without actually making
|
||||
# Mark all existing videos as known so they do not get deleted
|
||||
# during cleanup. We "downloaded" them, just without actually making
|
||||
# a network request as we assumed they did not change.
|
||||
for video in self._previous_contained_opencast_videos(element_path):
|
||||
await self.download(video)
|
||||
|
|
|
@ -1,5 +1,5 @@
|
|||
from pathlib import Path
|
||||
from typing import Dict, List, Optional
|
||||
from typing import Dict, List, Optional, Set
|
||||
|
||||
from rich.markup import escape
|
||||
|
||||
|
@ -43,16 +43,24 @@ class Pferd:
|
|||
|
||||
crawl_sections = [name for name, _ in config.crawl_sections()]
|
||||
|
||||
crawlers_to_run = [] # With crawl: prefix
|
||||
crawlers_to_run = set() # With crawl: prefix
|
||||
unknown_names = [] # Without crawl: prefix
|
||||
|
||||
for name in cli_crawlers:
|
||||
section_name = f"crawl:{name}"
|
||||
if section_name in crawl_sections:
|
||||
log.explain(f"Crawler section named {section_name!r} exists")
|
||||
crawlers_to_run.append(section_name)
|
||||
else:
|
||||
log.explain(f"There's no crawler section named {section_name!r}")
|
||||
crawlers_to_run.add(section_name)
|
||||
# interprete name as alias of a crawler
|
||||
alias_names = self._find_crawlers_by_alias(name, config)
|
||||
if alias_names:
|
||||
crawlers_to_run.update(alias_names)
|
||||
log.explain_topic(f"Crawler alias {name!r} found corresponding crawler sections:")
|
||||
for alias_name in alias_names:
|
||||
log.explain(f"Crawler section named {alias_name!r} with alias {name!r} exists")
|
||||
|
||||
if not section_name in crawl_sections and not alias_names:
|
||||
log.explain(f"There's neither a crawler section named {section_name!r} nor does a crawler with alias {name!r} exist.")
|
||||
unknown_names.append(name)
|
||||
|
||||
if unknown_names:
|
||||
|
@ -65,6 +73,14 @@ class Pferd:
|
|||
|
||||
return crawlers_to_run
|
||||
|
||||
def _find_crawlers_by_alias(self, alias: str, config: Config) -> Set[str]:
|
||||
alias_names = set()
|
||||
for (section_name, section) in config.crawl_sections():
|
||||
section_aliases = section.get("aliases", [])
|
||||
if alias in section_aliases:
|
||||
alias_names.add(section_name)
|
||||
return alias_names
|
||||
|
||||
def _find_crawlers_to_run(
|
||||
self,
|
||||
config: Config,
|
||||
|
|
Loading…
Reference in New Issue