nate/journey-fm-playlist
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add scraping from Spirit FM recently played list, combine with Journey FM and deduplicate songs

Browse Source
This commit is contained in:
nmemmert committed 2025-11-17 11:56:26 -05:00
1 parent 7e7754f533
commit 32d87cf0c2
1 file changed
+78 -67
Download Patch File Download Diff File Expand all files Collapse all files
main.py
+78 -67
View File
@@ -31,77 +31,88 @@ SERVER_IP = '172.16.16.106' # Your local server IP
PLAYLIST_NAME = 'Journey FM Recently Played' PLAYLIST_NAME = 'Journey FM Recently Played'
def scrape_recently_played(): def scrape_recently_played():
"""Scrape recently played songs from myjourneyfm.com using Selenium""" """Scrape recently played songs from multiple stations using Selenium"""
options = Options() urls = [
options.add_argument("--headless") 'https://www.myjourneyfm.com/recently-played/',
options.add_argument("--no-sandbox") 'https://spiritfm.com/spiritfm-recently-played/'
options.add_argument("--disable-dev-shm-usage") ]
options.add_argument("--disable-gpu")
options.add_argument("--remote-debugging-port=9222")
options.add_argument("--user-data-dir=/tmp/chromium")
options.add_argument("--no-first-run")
options.add_argument("--disable-extensions")
options.binary_location = "/usr/bin/chromium-browser"
service = Service()
driver = webdriver.Chrome(service=service, options=options)
url = 'https://www.myjourneyfm.com/recently-played/' all_songs = []
driver.get(url) seen = set() # To avoid duplicates
# Wait for initial load for url in urls:
time.sleep(5) options = Options()
options.add_argument("--headless")
# Click "View More" button if exists options.add_argument("--no-sandbox")
try: options.add_argument("--disable-dev-shm-usage")
more_button = driver.find_element(By.ID, "moreSongs") options.add_argument("--disable-gpu")
more_button.click() options.add_argument("--remote-debugging-port=9222")
time.sleep(5) # Wait for more songs to load options.add_argument("--user-data-dir=/tmp/chromium")
except: options.add_argument("--no-first-run")
pass # Button not found or already loaded options.add_argument("--disable-extensions")
options.binary_location = "/usr/bin/chromium-browser"
html = driver.page_source service = Service()
driver.quit() driver = webdriver.Chrome(service=service, options=options)
# Optional: save HTML to file for debugging (comment out if not needed) driver.get(url)
# with open('page.html', 'w', encoding='utf-8') as f:
# f.write(html) # Wait for initial load
time.sleep(5)
soup = BeautifulSoup(html, 'html.parser')
# Click "View More" button if exists
songs = [] try:
# Find elements (div, li) that contain time in their text more_button = driver.find_element(By.ID, "moreSongs")
song_elements = soup.find_all(lambda tag: tag.name in ['div', 'li', 'p'] and re.search(r'\d+:\d+ [AP]M', tag.get_text())) more_button.click()
for element in song_elements: time.sleep(5) # Wait for more songs to load
spans = element.find_all('span') except:
if len(spans) >= 3: pass # Button not found or already loaded
title = spans[0].get_text().strip()
artist = spans[1].get_text().strip() html = driver.page_source
# Ignore time driver.quit()
songs.append({'artist': artist, 'title': title})
else: soup = BeautifulSoup(html, 'html.parser')
# Fallback to text parsing
full_text = element.get_text().strip() songs = []
match = re.search(r'(\d+:\d+ [AP]M)', full_text) # Find elements (div, li) that contain time in their text
if match: song_elements = soup.find_all(lambda tag: tag.name in ['div', 'li', 'p'] and re.search(r'\d+:\d+ [AP]M', tag.get_text()))
play_time = match.group(1) for element in song_elements:
before = full_text.split(play_time)[0].strip() spans = element.find_all('span')
if ' by ' in before: if len(spans) >= 3:
title, artist = before.split(' by ', 1) title = spans[0].get_text().strip()
title = title.strip() artist = spans[1].get_text().strip()
artist = artist.strip() # Ignore time
else: songs.append({'artist': artist, 'title': title})
# Split on capital letters else:
parts = re.findall(r'[A-Z][^A-Z]*', before) # Fallback to text parsing
if len(parts) == 4: full_text = element.get_text().strip()
title = ' '.join(parts[:2]) match = re.search(r'(\d+:\d+ [AP]M)', full_text)
artist = ' '.join(parts[2:]) if match:
play_time = match.group(1)
before = full_text.split(play_time)[0].strip()
if ' by ' in before:
title, artist = before.split(' by ', 1)
title = title.strip()
artist = artist.strip()
else: else:
title = ' '.join(parts[:3]) # Split on capital letters
artist = ' '.join(parts[3:]) parts = re.findall(r'[A-Z][^A-Z]*', before)
if title and artist: if len(parts) == 4:
songs.append({'artist': artist, 'title': title}) title = ' '.join(parts[:2])
artist = ' '.join(parts[2:])
else:
title = ' '.join(parts[:3])
artist = ' '.join(parts[3:])
if title and artist:
songs.append({'artist': artist, 'title': title})
# Add to all_songs, avoiding duplicates
for song in songs:
key = (song['title'].lower(), song['artist'].lower())
if key not in seen:
all_songs.append(song)
seen.add(key)
return songs return all_songs
def normalize_string(s): def normalize_string(s):
"""Normalize string for comparison""" """Normalize string for comparison"""