diff options
author | Wolfgang Müller | 2025-01-16 17:37:19 +0100 |
---|---|---|
committer | Wolfgang Müller | 2025-01-16 18:20:37 +0100 |
commit | c1163b70ad18a09667665d6aa173e503e6250a38 (patch) | |
tree | f07e00b983718cd99c6375a5e63c683f2c164143 | |
parent | 387550086a00b5a1b8221c1528e6f616430e7b3c (diff) | |
download | hircine-c1163b70ad18a09667665d6aa173e503e6250a38.tar.gz |
backend/plugins: Do not explicitly require source in anchira.to scraper
We've come across info.yaml files without this field. If it is missing,
instead rely on a simple heuristic.
-rw-r--r-- | src/hircine/plugins/scrapers/anchira.py | 10 |
1 files changed, 8 insertions, 2 deletions
diff --git a/src/hircine/plugins/scrapers/anchira.py b/src/hircine/plugins/scrapers/anchira.py index baee4bd..bb60ac9 100644 --- a/src/hircine/plugins/scrapers/anchira.py +++ b/src/hircine/plugins/scrapers/anchira.py @@ -19,7 +19,7 @@ from hircine.scraper.types import ( ) from hircine.scraper.utils import open_archive_file, parse_dict -URL_REGEX = re.compile(r"^https?://anchira\.to/g/") +SOURCE_REGEX = re.compile(r"^https?://anchira\.to/g/") class AnchiraYamlScraper(Scraper): @@ -45,8 +45,14 @@ class AnchiraYamlScraper(Scraper): self.data = self.load() source = self.data.get("Source") - if source and re.match(URL_REGEX, source): + if source and re.match(SOURCE_REGEX, source): self.is_available = True + elif not source: + # heuristic, but should be good enough + url = self.data.get("URL") + parody = self.data.get("Parody") + + self.is_available = url is not None and parody is not None def load(self): try: |