added parallel download

.gitignore

+USDB.xlsx
+
+### MicrosoftOffice template
+*.tmp
+
+# Word temporary
+~$*.doc*
+
+# Word Auto Backup File
+Backup of *.doc*
+
+# Excel temporary
+~$*.xls*
+
+# Excel Backup File
+*.xlk
+
+# PowerPoint temporary
+~$*.ppt*
+
+# Visio autosave temporary files
+*.~vsd*
+
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+

coverdownloader.py

+import requests
+from pathlib import Path
+
+class CoverDownloader:
+    def __init__(self, outdir: str):
+        self.outdir = outdir
+
+    def download(self, url: str, artist: str, song: str, spotify_uri: str):
+        Path(self.outdir).mkdir(parents=True, exist_ok=True)
+        with open(Path(self.outdir) / f"{artist} - {song} - {spotify_uri}.jpg", "wb") as f:
+            f.write(requests.get(url).content)
\ No newline at end of file

db.py

+import pandas as pd
+import pandas.core.series
+
+
+def load(file: str):
+    with open(file, 'rb') as f:
+        return pd.read_excel(f)
+
+def get_usdb_url(song: pandas.Series):
+    return song["TXT Link"]
+
+def get_cover_image_url(song: pandas.Series):
+    return song["Cover Link"]
+
+def get_yt_video_url(song: pandas.Series):
+    return song["Video Link"]
+
+def get_artist_name(song: pandas.Series):
+    return song["Artist Name"]
+
+def get_song_name(song: pandas.Series):
+    return song["Track Name"]
+
+def get_track_id(song: pandas.Series):
+    return song["Spotify URI"]
+
+class USDB:
+    def __init__(self, file: str):
+        self.data = load(file)

main.py

-import requests
-from bs4 import BeautifulSoup
+import concurrent
 
+import pandas
 
-class USDBDownloader:
-    def __init__(self, sessid):
-        self.sessid = sessid
+from txtdownloader import TXTDownloader
+from ytdownloader import YTDownloader
+from coverdownloader import CoverDownloader
+from db import *
 
-    def download(self, url: str):
-        url = url.replace("detail", "gettxt")
-        print(url)
+db = USDB("USDB.xlsx")
+txt = TXTDownloader("nv0rb8ma82p37qrvduvch6j3f6", "./out/txt/")
+yt = YTDownloader("./out/audio/", "./out/video")
+cv = CoverDownloader("./out/covers/")
 
-        with requests.Session() as s:
-            page = s.post(url, data={'wd': 1}, cookies={'PHPSESSID': self.sessid})
+def download_song(song: pandas.Series):
+    usdb_url = get_usdb_url(song)
+    cover_url = get_cover_image_url(song)
+    yt_url = get_yt_video_url(song)
+    song_name = get_song_name(song).replace("/", "")
+    artist = get_artist_name(song).replace("/", "")
+    spotify_uri = get_track_id(song).replace("/", "")
 
-            soup = BeautifulSoup(page.content, 'html.parser')
-            txt = soup.find(name="textarea").text
-        return txt
+    if type(usdb_url) == str and usdb_url != " ":
+        txt.download(usdb_url, artist, song_name, spotify_uri)
 
+    if type(cover_url) == str and cover_url != " ":
+        cv.download(cover_url, artist, song_name, spotify_uri)
+
+    if type(yt_url) == str and yt_url != " ":
+        yt.download(yt_url, artist, song_name, spotify_uri)
+
+
+executor = concurrent.futures.ThreadPoolExecutor(10)
+futures = [executor.submit(download_song, song) for _, song in db.data.sample(10).iterrows()]
+concurrent.futures.wait(futures)
 
-if __name__ == '__main__':
-    usdbdl = USDBDownloader("")
-    usdbdl.download("http://usdb.animux.de/?link=detail&id=16196")

requirements.txt

@@ -5,3 +5,4 @@ idna==3.3
 requests==2.28.1
 soupsieve==2.3.2.post1
 urllib3==1.26.10
+pandas~=1.4.3
\ No newline at end of file

txtdownloader.py

+import urllib.parse
+from pathlib import Path
+
+import requests
+from bs4 import BeautifulSoup
+
+
+class TXTDownloader:
+    def __init__(self, sessid, outdir):
+        self.sessid = sessid
+        self.outdir = outdir
+
+    def download(self, url: str, artist: str, song: str, spotify_uri: str):
+        url = url.replace("detail", "gettxt")
+
+        with requests.Session() as s:
+            page = s.post(url, data={'wd': 1}, cookies={'PHPSESSID': self.sessid})
+            soup = BeautifulSoup(page.content, 'html.parser')
+            txt = soup.find(name="textarea").text
+
+            Path(self.outdir).mkdir(parents=True, exist_ok=True)
+            with open(Path(self.outdir) / f"{artist} - {song} - {spotify_uri}.txt", "w", encoding="utf-8") as f:
+                f.write(txt)
+

ytdownloader.py

+import shutil
+from pathlib import Path
+
+import yt_dlp.postprocessor
+from yt_dlp import YoutubeDL
+
+class YTDownloader:
+    def __init__(self, audiodir, videodir):
+        self.audiodir = audiodir
+        self.videodir = videodir
+
+    def download(self, url: str, artist: str, song: str, spotify_uri: str):
+        ydl_opts = {
+            'format': 'mp4/best',
+            'outtmpl': f'{str((Path(self.audiodir) / f"{artist} - {song} - {spotify_uri}").resolve())}.%(ext)s',
+            # ℹ️ See help(yt_dlp.postprocessor) for a list of available Postprocessors and their arguments
+            'keepvideo': True,
+            'postprocessors': [{  # Extract audio using ffmpeg
+                'key': 'FFmpegExtractAudio',
+                'preferredcodec': 'mp3',
+            }]
+        }
+        with YoutubeDL(ydl_opts) as ydl:
+            ydl.download(url)
+
+        Path(self.videodir).mkdir(parents=True, exist_ok=True)
+        shutil.move(Path(self.audiodir) / f"{artist} - {song} - {spotify_uri}.mp4", Path(self.videodir) / f"{artist} - {song} - {spotify_uri}.mp4")