scrape-interesting-breton-music-website.py

scrape-interesting-breton-music-website.py

@@ -0,0 +1,74 @@
+#!/usr/bin/env python3
+# Ahem…
+import argparse
+from pathlib import Path
+from urllib.parse import urljoin, urlparse
+
+from bs4 import BeautifulSoup
+import requests
+
+
+def scrape_course(course_url: str, cookies: dict, output_dir: Path):
+    response = requests.get(course_url, cookies=cookies)
+    response.raise_for_status()
+    soup = BeautifulSoup(response.text, features="lxml")
+    for link in soup.find_all("a", class_="card-container-link"):
+        video_url = urljoin(course_url, link["href"])
+        scrape_video(video_url, cookies, output_dir)
+
+
+def scrape_video(video_url: str, cookies: dict, output_dir: Path):
+    print(f"Video {video_url}")
+    response = requests.get(video_url, cookies=cookies)
+    response.raise_for_status()
+    soup = BeautifulSoup(response.text, features="lxml")
+    for container in soup.find_all("div", class_="player-container"):
+        link = container.find("a")
+        if link is None:
+            continue
+        file_url = link["href"]
+        file_name = urlparse(file_url).path.split("/")[-1]
+        output_path = output_dir / file_name
+        download_file(file_url, cookies, output_path)
+    for link in soup.find_all("a"):
+        file_url = link["href"]
+        if not file_url.startswith("/scripts/files/"):
+            continue
+        file_url = urljoin(video_url, file_url)
+        file_name = urlparse(file_url).path.split("/")[-1]
+        output_path = output_dir / file_name
+        download_file(file_url, cookies, output_path)
+
+
+def download_file(url: str, cookies: dict, output_path: Path):
+    print(f'Downloading: "{url}"')
+    print(f'  → "{output_path}"')
+    with requests.get(url, cookies=cookies, stream=True) as response:
+        response.raise_for_status()
+        with open(output_path, 'wb') as file:
+            for chunk in response.iter_content(chunk_size=8192):
+                file.write(chunk)
+
+
+def main():
+    argparser = argparse.ArgumentParser()
+    argparser.add_argument("--course")
+    argparser.add_argument("--video")  # either video or course
+    argparser.add_argument("--phpsessid", help="PHPSESSID")
+    argparser.add_argument("-o", "--output")
+    args = argparser.parse_args()
+    cookies = {"PHPSESSID": args.phpsessid}
+    output_dir = Path(args.output) if args.output else Path.cwd()
+    if not output_dir.exists():
+        output_dir.mkdir(parents=True)
+
+    if course_url := args.course:
+        scrape_course(course_url, cookies, output_dir)
+    elif video_url := args.video:
+        scrape_video(video_url, cookies, output_dir)
+    else:
+        print("Nothing to do.")
+
+
+if __name__ == "__main__":
+    main()