mirror
/
auto-archiver
kopia lustrzana https://github.com/bellingcat/auto-archiver
1
0
Forkuj 0
Kod Zgłoszenia Packages Projekty Wydania Wiki Aktywność

improves generic extractor edge-cases and yt-dlp updates

pull/307/head
msramalho 2025-06-02 12:03:51 +01:00
rodzic ee3e871dd8
commit ac24fd8f49
Nie znaleziono w bazie danych klucza dla tego podpisu
1 zmienionych plików z 9 dodań i 3 usunięć
Pokaż statystyki Ściągnij plik aktualizacji Ściągnij plik porównania Expand all files Collapse all files

12
src/auto_archiver/modules/generic_extractor/generic_extractor.py
Wyświetl plik

@ -156,7 +156,7 @@ class GenericExtractor(Extractor):
logger.error("generate_once.js not found after transpilation.") logger.error("generate_once.js not found after transpilation.")
return return
self.extractor_args.setdefault("youtube", {})["getpot_bgutil_script"] = script_path self.extractor_args.setdefault("youtubepot-bgutilscript", {})["script_path"] = script_path
logger.info(f"PO Token script configured at: {script_path}") logger.info(f"PO Token script configured at: {script_path}")
except Exception as e: except Exception as e:
@ -301,7 +301,7 @@ class GenericExtractor(Extractor):
result.set_url(url) result.set_url(url)
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["description"]) result.set_content(video_data.pop("description"))
# extract comments if enabled # extract comments if enabled
if self.comments: if self.comments:
result.set( result.set(
@ -370,7 +370,6 @@ class GenericExtractor(Extractor):
return False return False
else: else:
entries = [data] entries = [data]
result = Metadata() result = Metadata()
for entry in entries: for entry in entries:
@ -379,6 +378,10 @@ class GenericExtractor(Extractor):
if not os.path.exists(filename): if not os.path.exists(filename):
filename = filename.split(".")[0] + ".mkv" filename = filename.split(".")[0] + ".mkv"
if not os.path.exists(filename):
logger.warning(f"File {filename} does not exist (see yt-dlp logs), skipping this entry.")
continue
new_media = Media(filename) new_media = Media(filename)
for x in ["duration", "original_url", "fulltitle", "description", "upload_date"]: for x in ["duration", "original_url", "fulltitle", "description", "upload_date"]:
if x in entry: if x in entry:
@ -396,6 +399,9 @@ class GenericExtractor(Extractor):
result.add_media(new_media) result.add_media(new_media)
except Exception as e: except Exception as e:
logger.error(f"Error processing entry {entry}: {e}") logger.error(f"Error processing entry {entry}: {e}")
if not len(result.media):
logger.warning(f"No media found for entry {entry}, skipping.")
return False
return self.add_metadata(data, info_extractor, url, result) return self.add_metadata(data, info_extractor, url, result)