From 559646bc1147c2a50cef510ec484d0bffbf85380 Mon Sep 17 00:00:00 2001
From: Adrien Abraham <aabraham@freebox.fr>
Date: Fri, 23 Sep 2022 18:50:16 +0200
Subject: [PATCH] scrape-djtracklists: WIP

---
 scrape-djtracklists.py | 66 +++++++++++++++++++++++++++++++++++-------
 1 file changed, 55 insertions(+), 11 deletions(-)

diff --git a/scrape-djtracklists.py b/scrape-djtracklists.py
index 18ab845..1aa809d 100755
--- a/scrape-djtracklists.py
+++ b/scrape-djtracklists.py
@@ -2,11 +2,23 @@
 """Download tracklists from djtracklists.com."""
 
 import argparse
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Optional
 
 import requests
 from bs4 import BeautifulSoup
 
 
+@dataclass
+class Track:
+    title: str
+    artists: list[str]
+    mix: Optional[str]
+    mix_artists: Optional[list[str]]
+    timestamp: str
+
+
 def main():
     parser = argparse.ArgumentParser()
     parser.add_argument("-s", "--series", help="download this series")
@@ -14,31 +26,63 @@ def main():
     args = parser.parse_args()
 
     if tracklist_url := args.tracklist:
-        download_tracklist(tracklist_url)
+        tracklist = download_tracklist(tracklist_url)
+        name = tracklist_url.rstrip("/").rsplit("/", maxsplit=1)[-1]
+        file_name = Path.cwd() / (name + ".txt")
+        save_tracklist(tracklist, file_name)
 
 
 def is_track_row(css_class: str) -> bool:
-    return css_class == "on" or css_class == "off"
+    return css_class in ("on", "off")
 
 
-def download_tracklist(url: str):
-    response = requests.get(url)
+def download_tracklist(url: str) -> list[Track]:
+    response = requests.get(url, timeout=10)
     response.raise_for_status()
     soup = BeautifulSoup(response.text, "html.parser")
+    tracklist = []
     for row in soup.find_all("div", class_=is_track_row):
-        print("*" * 80)
+        artists = []
+        mix_artists = []
         try:
-            print("track", row.find("a", class_="track").string)
-            print("release", row.find("a", class_="release").string)
+            title = row.find("a", class_="track").string
+            mix = row.find("a", class_="release").string
         except AttributeError:
-            print("track", row.find("b").string)
+            title = row.find("b").string
+            mix = None
+        timestamp = row.find("span", class_="index_time").string
         for artist in row.find_all("a", class_="artist"):
             prev_tag = artist.previous_sibling.string
             if getattr(prev_tag, "string", "").strip() == "remixed  by":
-                print("remixing artist", artist.string)
+                mix_artists.append(artist.string)
             else:
-                print("artist", artist.string)
-        print("\n" * 10)
+                artists.append(artist.string)
+        tracklist.append(
+            Track(
+                title=title,
+                mix=mix,
+                artists=artists,
+                mix_artists=mix_artists or None,
+                timestamp=timestamp,
+            )
+        )
+    return tracklist
+
+
+def save_tracklist(tracklist: list[Track], file_name: Path):
+    try:
+        with open(file_name, "wt", encoding="utf8") as file:
+            for track in tracklist:
+                artists = " & ".join(track.artists)
+                line = f"{track.timestamp} — {artists} — {track.title}"
+                if track.mix:
+                    line += f" ({track.mix})"
+                if track.mix_artists:
+                    mix_artists = " & ".join(track.mix_artists)
+                    line += f" remixed by {mix_artists}"
+                file.write(line + "\n")
+    except OSError as exc:
+        print(f"Can't save tracklist: {exc}")
 
 
 if __name__ == "__main__":