bellingcat/auto-archiver
1
0
Fork 0
mirror of https://github.com/bellingcat/auto-archiver.git synced 2026-06-12 21:28:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

avoid empty metadata comments

Browse Source
This commit is contained in:
msramalho
2025-07-06 14:05:17 +01:00
parent 9d3cd5774b
commit d3efd7121c
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/auto_archiver/modules/generic_extractor/generic_extractor.py
View File

@@ -307,7 +307,7 @@ class GenericExtractor(Extractor):
if "description" in video_data and not result.get("content"): if "description" in video_data and not result.get("content"):
result.set_content(video_data.get("description")) result.set_content(video_data.get("description"))
# extract comments if enabled # extract comments if enabled
if self.comments and video_data.get("comments", []) is not None: if self.comments and video_data.get("comments", None) is not None:
result.set( result.set(
"comments", "comments",
[ [
@@ -516,7 +516,7 @@ class GenericExtractor(Extractor):
) )
return False return False
if result: if result and not result.is_success():
extractor_name = "yt-dlp" extractor_name = "yt-dlp"
if info_extractor: if info_extractor:
extractor_name += f"_{info_extractor.ie_key()}" extractor_name += f"_{info_extractor.ie_key()}"
@@ -535,7 +535,6 @@ class GenericExtractor(Extractor):
if url.startswith("https://ya.ru"): if url.startswith("https://ya.ru"):
url = url.replace("https://ya.ru", "https://yandex.ru") url = url.replace("https://ya.ru", "https://yandex.ru")
item.set("replaced_url", url) item.set("replaced_url", url)
logger.debug(f"{skip_proxy=}, {self.proxy_on_failure_only=}, {self.proxy=}")
# proxy_on_failure_only logic # proxy_on_failure_only logic
if self.proxy and self.proxy_on_failure_only and not skip_proxy: if self.proxy and self.proxy_on_failure_only and not skip_proxy:

1
tests/extractors/test_tiktok_tikwm_extractor.py
View File

@@ -141,6 +141,7 @@ class TestTiktokTikwmExtractor(TestExtractorBase):
assert result.get_title() == "Title" assert result.get_title() == "Title"
assert result.get("author") == "Author" assert result.get("author") == "Author"
assert result.get("other") == "data" assert result.get("other") == "data"
assert result.get("comments") is None
assert result.get("api_data") == {"id": 123, "other": "data"} assert result.get("api_data") == {"id": 123, "other": "data"}
assert result.media[1].get("duration") == 60 assert result.media[1].get("duration") == 60
assert result.get("timestamp") == datetime.fromtimestamp(1736301699, tz=timezone.utc) assert result.get("timestamp") == datetime.fromtimestamp(1736301699, tz=timezone.utc)