Add handler for Mediafile downloads

c3dbdl/c3dbdl.py

@@ -153,8 +153,6 @@ def fetchSongData(entries):
         for link_entry in download_links:
             link = link_entry.get("href")
             description = link_entry.get_text().strip()
-            if "c3universe.com" not in link:
-                continue
             messages.append(f"Found download link: {link} ({description})")
             dl_links.append(
                 {
@@ -252,6 +250,72 @@ def buildDatabase(pages, concurrency):
     return found_songs
 
 
+def downloadFile(download_url, download_path, download_filename):
+    attempts = 1
+    p = None
+    try:
+        with requests.get(download_url, stream=True) as r:
+            while attempts <= 3:
+                try:
+                    r.raise_for_status()
+                    break
+                except Exception:
+                    click.echo(
+                        f"Download attempt failed: HTTP {r.status_code}; retrying {attempts}/3"
+                    )
+                    sleep(attempts)
+                    attempts += 1
+            if r is None or r.status_code != 200:
+                if r:
+                    code = r.status_code
+                else:
+                    code = "-1"
+                raise HTTPError(download_url, code, "", None, None)
+
+            if not os.path.exists(download_path):
+                os.makedirs(download_path)
+
+            with open(download_filename, "wb") as f:
+                for chunk in r.iter_content(chunk_size=8192):
+                    f.write(chunk)
+            click.echo(f"Successfully downloaded to {download_filename}")
+    except Exception as e:
+        click.echo(f"Download attempt failed: {e}")
+        return None
+
+def parseC3Universe(dl_link):
+    try:
+        p = requests.get(dl_link)
+        if p.status_code != 200:
+            raise HTTPError(dl_link, p.status_code, "", None, None)
+
+        parsed_html = BeautifulSoup(p.text, "html.parser")
+        download_url = (
+            parsed_html.body.find("div", attrs={"class": "lock-head"})
+            .find("a")
+            .get("href")
+        )
+        return download_url
+    except Exception as e:
+        click.echo(f"Failed parsing or retrieving HTML link: {e}")
+        return None
+
+
+def parseMediafire(dl_link):
+    try:
+        p = requests.get(dl_link)
+        if p.status_code != 200:
+            raise HTTPError(dl_link, p.status_code, "", None, None)
+
+        parsed_html = BeautifulSoup(p.text, "html.parser")
+        download_url = parsed_html.find(
+            "a", attrs={"id": "downloadButton", "rel": "nofollow", "aria-label": "Download file"}
+        ).get("href")
+        return download_url
+    except Exception as e:
+        click.echo(f"Failed parsing or retrieving HTML link: {e}")
+        return None
+
 def downloadSong(destination, filename, entry, dlid, dldesc):
     click.echo(
         f"""> Downloading song "{entry['artist']} - {entry['title']}" by {entry['author']}..."""
@@ -278,21 +342,19 @@ def downloadSong(destination, filename, entry, dlid, dldesc):
             return
 
     for dl_link in dl_links:
-        try:
+        if 'dl.c3universe.com' in dl_link['link']:
-            p = requests.get(dl_link["link"])
+            download_url = parseC3Universe(dl_link["link"])
-            if p.status_code != 200:
+        elif 'www.mediafire.com' in dl_link["link"]:
-                raise HTTPError(dl_link["link"], p.status_code, "", None, None)
+            download_url = parseMediafire(dl_link["link"])
-
+        else:
-            parsed_html = BeautifulSoup(p.text, "html.parser")
+            click.echo("Download URL is not valid for CLI download; skipping...")
-            download_url = (
+            click.echo(f"URL: {dl_link['link']}")
-                parsed_html.body.find("div", attrs={"class": "lock-head"})
-                .find("a")
-                .get("href")
-            )
-        except Exception as e:
-            click.echo(f"Failed parsing or retrieving HTML link: {e}")
             continue
 
+        if download_url is None:
+            continue
+
+        print(entry)
         download_filename = filename.format(
             genre=entry["genre"],
             artist=entry["artist"],
@@ -312,38 +374,7 @@ def downloadSong(destination, filename, entry, dlid, dldesc):
             click.echo(f"File exists at {download_filename}")
             continue
 
-        attempts = 1
+        downloadFile(download_url, download_path, download_filename)
-        p = None
-        try:
-            with requests.get(download_url, stream=True) as r:
-                while attempts <= 3:
-                    try:
-                        r.raise_for_status()
-                        break
-                    except Exception:
-                        click.echo(
-                            f"Download attempt failed: HTTP {r.status_code}; retrying {attempts}/3"
-                        )
-                        sleep(attempts)
-                        attempts += 1
-                if r is None or r.status_code != 200:
-                    if r:
-                        code = r.status_code
-                    else:
-                        code = "-1"
-                    raise HTTPError(download_url, code, "", None, None)
-
-                if not os.path.exists(download_path):
-                    os.makedirs(download_path)
-
-                with open(download_filename, "wb") as f:
-                    for chunk in r.iter_content(chunk_size=8192):
-                        f.write(chunk)
-                click.echo(f"Successfully downloaded to {download_filename}")
-        except Exception as e:
-            click.echo(f"Download attempt failed: {e}")
-            continue
-
 
 @click.command(name="build", short_help="Build the local database.")
 @click.option(