From 5545d1190a0ab08932a8f176fc4a5d8d67c971d2 Mon Sep 17 00:00:00 2001
From: Lars Noack <lars.noack@outlook.de>
Date: Tue, 24 Jan 2023 09:40:01 +0100
Subject: [PATCH] started ma

---
 src/goof.py                                   |  3 +-
 src/music_kraken/database/objects/song.py     |  5 +-
 src/music_kraken/pages/__init__.py            |  8 +++
 .../pages/encyclopaedia_metallum.py           | 70 ++++++++++++++++++-
 src/music_kraken/utils/shared.py              |  2 +
 5 files changed, 84 insertions(+), 4 deletions(-)

diff --git a/src/goof.py b/src/goof.py
index 33d740e..83e8324 100644
--- a/src/goof.py
+++ b/src/goof.py
@@ -2,4 +2,5 @@ from music_kraken.pages import (
     EncyclopaediaMetallum
 )
 
-EncyclopaediaMetallum.search_by_query("Ghost Bath")
+print(EncyclopaediaMetallum.search_by_query("Ghost Bath"))
+EncyclopaediaMetallum.search_by_query("#a Ghost Bath #r Self Loather")
diff --git a/src/music_kraken/database/objects/song.py b/src/music_kraken/database/objects/song.py
index 6eb7ce1..6087497 100644
--- a/src/music_kraken/database/objects/song.py
+++ b/src/music_kraken/database/objects/song.py
@@ -343,10 +343,13 @@ class Artist(DatabaseObject, ID3Metadata):
             sources: List[Source] = None,
             main_songs: List[Song] = None,
             feature_songs: List[Song] = None,
-            main_albums: List[Album] = None
+            main_albums: List[Album] = None,
+            notes: str = None
     ):
         DatabaseObject.__init__(self, id_=id_)
 
+        self.notes = notes
+
         if main_albums is None:
             main_albums = []
         if feature_songs is None:
diff --git a/src/music_kraken/pages/__init__.py b/src/music_kraken/pages/__init__.py
index 406ec88..614efb1 100644
--- a/src/music_kraken/pages/__init__.py
+++ b/src/music_kraken/pages/__init__.py
@@ -1,3 +1,11 @@
 from .encyclopaedia_metallum import EncyclopaediaMetallum
 
 EncyclopaediaMetallum = EncyclopaediaMetallum
+
+MetadataPages = {
+    EncyclopaediaMetallum
+}
+
+AudioPages = {
+    
+}
diff --git a/src/music_kraken/pages/encyclopaedia_metallum.py b/src/music_kraken/pages/encyclopaedia_metallum.py
index f3aaac7..8983de3 100644
--- a/src/music_kraken/pages/encyclopaedia_metallum.py
+++ b/src/music_kraken/pages/encyclopaedia_metallum.py
@@ -1,10 +1,28 @@
 from typing import List
+import requests
+from bs4 import BeautifulSoup
+
+from ..utils.shared import (
+    ENCYCLOPAEDIA_METALLUM_LOGGER as LOGGER
+)
 
 from .abstract import Page
-from ..database import MusicObject
+from ..database import (
+    MusicObject,
+    Artist,
+    Source,
+    SourcePages
+)
 
 
 class EncyclopaediaMetallum(Page):
+    API_SESSION: requests.Session = requests.Session()
+    API_SESSION.headers = {
+        "Host": "www.metal-archives.com",
+        "Connection": "keep-alive"
+    }
+
+
     @classmethod
     def search_by_query(cls, query: str) -> List[MusicObject]:
         query_obj = cls.Query(query)
@@ -15,4 +33,52 @@ class EncyclopaediaMetallum(Page):
 
     @classmethod
     def simple_search(cls, query: Page.Query):
-        pass
+        """
+        Searches the default endpoint from metal archives, which intern searches only
+        for bands, but it is the default, thus I am rolling with it
+        """
+        endpoint = "https://www.metal-archives.com/search/ajax-band-search/?field=name&query={query}&sEcho=1&iColumns=3&sColumns=&iDisplayStart=0&iDisplayLength=200&mDataProp_0=0&mDataProp_1=1&mDataProp_2=2"
+
+        r = cls.API_SESSION.get(endpoint.format(query=query))
+        if r.status_code != 200:
+            LOGGER.warning(f"code {r.status_code} at {endpoint.format(query=query.query)}")
+            return []
+
+        print(r.json())
+        return cls.get_many_artists_from_json(r.json()['aaData'])
+
+    @classmethod
+    def get_artist_from_json(cls, html, genre, country) -> Artist:
+        """
+        TODO parse the country to a standart
+        """
+        # parse the html
+        # parse the html for the band name and link on metal-archives
+        soup = BeautifulSoup(html, 'html.parser')
+        anchor = soup.find('a')
+        artist_name = anchor.text
+        artist_url = anchor.get('href')
+        artist_id = int(artist_url.split("/")[-1])
+
+        notes = f"{artist_name} is a {genre} band from {country}"
+
+        anchor.decompose()
+        strong = soup.find('strong')
+        if strong is not None:
+            strong.decompose()
+            akronyms_ = soup.text[2:-2].split(', ')
+            notes += f"aka {akronyms_}"
+        notes += "."
+
+        return Artist(
+            id_=artist_id,
+            name=artist_name,
+            sources=[
+                Source(SourcePages.ENCYCLOPAEDIA_METALLUM, artist_url)
+            ],
+            notes = notes
+        )
+
+    @classmethod
+    def get_many_artists_from_json(cls, raw_artist_list: list) -> List[Artist]:
+        return [cls.get_artist_from_json(raw_artist) for raw_artist in raw_artist_list]
diff --git a/src/music_kraken/utils/shared.py b/src/music_kraken/utils/shared.py
index fdd7fa9..7c0b37c 100644
--- a/src/music_kraken/utils/shared.py
+++ b/src/music_kraken/utils/shared.py
@@ -41,6 +41,8 @@ LYRICS_LOGGER = logging.getLogger("lyrics")
 GENIUS_LOGGER = logging.getLogger("genius")
 TAGGING_LOGGER = logging.getLogger("tagging")
 
+ENCYCLOPAEDIA_METALLUM_LOGGER = logging.getLogger("ma")
+
 NOT_A_GENRE = ".", "..", "misc_scripts", "Music", "script", ".git", ".idea"
 MUSIC_DIR = os.path.join(os.path.expanduser("~"), "Music")