feat: implemented the merging from where it has been fetched from
All checks were successful
ci/woodpecker/push/woodpecker Pipeline was successful

This commit is contained in:
Hazel 2024-04-19 13:37:12 +02:00
parent 06ffae06a6
commit 301ff82bcf
3 changed files with 10 additions and 11 deletions

View File

@ -32,6 +32,7 @@ class InnerData:
def __init__(self, object_type, **kwargs):
self._refers_to_instances = set()
self._fetched_from: dict = {}
# collection : collection that is a collection of self
self._is_collection_child: Dict[Collection, Collection] = {}
@ -52,6 +53,8 @@ class InnerData:
:return:
"""
self._fetched_from.update(__other._fetched_from)
for key, value in __other.__dict__.copy().items():
# just set the other value if self doesn't already have it
if key not in self.__dict__ or (key in self.__dict__ and self.__dict__[key] == self._default_values.get(key)):
@ -109,7 +112,6 @@ class OuterProxy:
del kwargs[name]
self._fetched_from: dict = {}
self._inner: InnerData = InnerData(type(self), **kwargs)
self._inner._refers_to_instances.add(self)
@ -220,13 +222,13 @@ class OuterProxy:
def mark_as_fetched(self, *url_hash_list: List[str]):
for url_hash in url_hash_list:
self._fetched_from[url_hash] = {
self._inner._fetched_from[url_hash] = {
"time": get_unix_time(),
"url": url_hash,
}
def already_fetched_from(self, url_hash: str) -> bool:
res = self._fetched_from.get(url_hash, None)
res = self._inner._fetched_from.get(url_hash, None)
if res is None:
return False

View File

@ -352,7 +352,6 @@ class Bandcamp(Page):
if len(other_data_list) > 0:
other_data = json.loads(other_data_list[0]["data-tralbum"])
if DEBUG:
dump_to_file("bandcamp_song_data.json", data_container.text, is_json=True, exit_after_dump=False)
dump_to_file("bandcamp_song_data_other.json", json.dumps(other_data), is_json=True, exit_after_dump=False)
dump_to_file("bandcamp_song_page.html", r.text, exit_after_dump=False)
@ -367,7 +366,7 @@ class Bandcamp(Page):
song = Song(
title=clean_song_title(data["name"], artist_name=artist_data["name"]),
source_list=[Source(self.SOURCE_TYPE, data.get("mainEntityOfPage", data["@id"]), audio_url=mp3_url)],
source_list=[source, Source(self.SOURCE_TYPE, data.get("mainEntityOfPage", data["@id"]), audio_url=mp3_url)],
album_list=[Album(
title=album_data["name"].strip(),
date=ID3Timestamp.strptime(data["datePublished"], "%d %b %Y %H:%M:%S %Z"),
@ -380,8 +379,6 @@ class Bandcamp(Page):
lyrics_list=self._fetch_lyrics(soup=soup)
)
song.source_collection.append(source)
return song
def download_song_to_target(self, source: Source, target: Target, desc: str = None) -> DownloadResult:

View File

@ -13,7 +13,7 @@ if not load_dotenv(Path(__file__).parent.parent.parent / ".env"):
__stage__ = os.getenv("STAGE", "prod")
DEBUG = (__stage__ == "dev") and True
DEBUG_LOGGING = DEBUG and True
DEBUG_LOGGING = DEBUG and False
DEBUG_TRACE = DEBUG and True
DEBUG_OBJECT_TRACE = DEBUG and False
DEBUG_YOUTUBE_INITIALIZING = DEBUG and False