def download_movie(self, thread_id, url, movie):
"""
Method to get all songs from a movie website.
:param thread_id: As usual
:param url: URL of movie
:param movie: Name of movie
"""
movie_website = self.start_url + url
raw_html = open_request(movie_website, delayed=self.delay_request)
song_with_url = self.get_songs_with_url(raw_html)
# No new songs added
if db_operations.number_of_songs(self.start_url,
url) == len(song_with_url):
db_operations.update_last_crawl(self.start_url, url)
print_util.print_warning(
'{0} --> Movie {1} contains no new songs. Skipping.'.format(
thread_id, movie))
return
# Add all songs
for song_url, song in song_with_url:
self.task_queue.put({
'type': 2,
'url': song_url,
'song': song,
'movie': movie,
'movie_url': url,
'n_errors': 0
})
def get_song(self, thread_id, url, song, artist):
"""
Get song from a URL
:param thread_id: As usual
:param url: As usual
:param song: As usual
:param artist: Artist of song
"""
if db_operations.exists_song(self.start_url, url):
print_util.print_warning(
'{0} --> Song {1} already exists. Skipping.'.format(
thread_id, song))
complete_url = self.start_url + url
raw_html = open_request(complete_url, delayed=self.delay_request)
album, lyrics, lyricist, additional_artists = self.get_song_details(
raw_html
) # Note: additional_artists are artist(s) featured in the song
db_operations.save(song, url, album, url, self.start_url, lyrics,
additional_artists + [
artist,
], [
artist,
], lyricist)
def get_artist(self, thread_id, url, artist):
"""
Get songs for artist from URL in two parts:
1. Get songs from first page (:param url)
2. Add all other pages to task queue
:param thread_id:
:param url:
:param artist:
"""
complete_url = self.start_url + url
raw_html = open_request(complete_url, delayed=self.delay_request)
pages = self.get_pages_for_artist(raw_html)
# Add all songs from current page
for song_url, song in self.get_songs(raw_html):
self.task_queue.put({
'type': 3,
'url': song_url,
'song': song,
'artist': artist,
'n_errors': 0
})
# Add rest of pages in task queue
for page in pages[1:]:
self.task_queue.put({
'type': 2,
'url': page,
'artist': artist,
'n_errors': 0
})
def get_song(self, thread_id, url, song, album, album_url, artist):
"""
Method to get details of a song and save in database
:param thread_id: As usual
:param url: As usual
:param song: Song title
:param album: Album name
:param album_url: URL of album (same as artist) on the website
:param artist: As usual
"""
if db_operations.exists_song(self.start_url, url):
print_util.print_warning(
'{0} -> Song {1} already exists. Skipping'.format(
thread_id, song))
return
song_website = self.start_url + url
song_html = open_request(song_website, delayed=self.delay_request)
lyrics = self.get_song_details(song_html)
db_operations.save(song=song,
song_url=url,
movie=album,
movie_url=album_url,
start_url=self.start_url,
lyrics=lyrics,
singers=artist,
director=artist,
lyricist=artist)
def get_song(self, thread_id, url, song, album, album_url, artist):
"""
Method to get details of a song and save in database
:param thread_id: As usual
:param url: As usual
:param song: Song title
:param album: Album name
:param album_url: URL of album (same as artist) on the website
:param artist: As usual
"""
if db_operations.exists_song(self.start_url, url):
print_util.print_warning(
'{0} -> Song {1} already exists. Skipping'.format(
thread_id,
song
)
)
return
song_website = self.start_url + url
song_html = open_request(song_website, delayed=self.delay_request)
lyrics = self.get_song_details(song_html)
db_operations.save(
song=song,
song_url=url,
movie=album,
movie_url=album_url,
start_url=self.start_url,
lyrics=lyrics,
singers=artist,
director=artist,
lyricist=artist
)
def download_song(self, thread_id, url, song, movie, movie_url):
"""
Method to get song details from website.
:param thread_id: As usual
:param url: URL of song
:param song: Name of song
:param movie: Name of movie
:param movie_url: URL of movie
"""
# Song already exists
if db_operations.exists_song(self.start_url, url):
print_util.print_warning(
'{0} -> Song {1} already exists. Skipping.'.format(
thread_id, song))
return
# Get HTML
song_url_ = self.start_url + url
song_html = open_request(song_url_, delayed=self.delay_request)
lyrics, singers, music_by, lyricist = self.get_song_details(song_html)
# Save in database
db_operations.save(song=song,
song_url=url,
movie=movie,
movie_url=movie_url,
start_url=self.start_url,
lyrics=lyrics,
singers=singers,
director=music_by,
lyricist=lyricist)
def get_song(self, thread_id, url, song, artist):
"""
Get song from a URL
:param thread_id: As usual
:param url: As usual
:param song: As usual
:param artist: Artist of song
"""
if db_operations.exists_song(self.start_url, url):
print_util.print_warning(
'{0} --> Song {1} already exists. Skipping.'.format(
thread_id,
song
)
)
complete_url = self.start_url + url
raw_html = open_request(complete_url, delayed=self.delay_request)
album, lyrics, lyricist, additional_artists = self.get_song_details(
raw_html
) # Note: additional_artists are artist(s) featured in the song
db_operations.save(
song,
url,
album,
url,
self.start_url,
lyrics,
additional_artists + [artist, ],
[artist, ],
lyricist
)
def get_artist_albums(self, thread_id, url, artist):
"""
Method to get all songs for an artist
:param thread_id: As usual
:param url: As usual
:param artist: Artist name
"""
website = self.start_url + '/' + url
raw_html = open_request(website, delayed=self.delay_request)
albums_with_songs = self.get_albums_with_songs(raw_html)
for album, song_with_url in albums_with_songs:
for song_url, song in song_with_url:
self.task_queue.put(
{
'type': 2,
'song': song,
'url': song_url,
'album': album,
'album_url': url,
'artist': artist,
'n_errors': 0
}
)
def get_songs_from_page(self, thread_id, url, artist):
"""
Get songs from other pages of artist
:param thread_id: As usual
:param url: As usual
:param artist: As usual
"""
complete_url = self.start_url + url
raw_html = open_request(complete_url, delayed=self.delay_request)
for song_url, song in self.get_songs(raw_html):
self.task_queue.put({
'type': 3,
'url': song_url,
'song': song,
'artist': artist,
'n_errors': 0
})
def get_artists(self, thread_id, url):
"""
Method to get artists from a URL
:param thread_id: As usual
:param url: As usual
"""
complete_url = self.start_url + url
raw_html = open_request(complete_url, delayed=self.delay_request)
artists_with_url = self.get_artist_with_url(raw_html)
for artist_url, artist in artists_with_url:
self.task_queue.put({
'type': 1,
'url': artist_url,
'artist': artist,
'n_errors': 0
})
def get_movies(self, thread_id, url):
# Get website HTML
"""
Get movie list from website
:param thread_id: As usual
:param url: URL of website from which movies are to be fetched
"""
website = self.start_url + url
raw_html = open_request(website, delayed=self.delay_request)
# Add movies to task queue
movies_with_url = self.get_movies_with_url(raw_html)
for url, movie in movies_with_url:
self.task_queue.put({
'type': 1,
'url': url,
'movie': movie,
'n_errors': 0
})
def get_songs_from_page(self, thread_id, url, artist):
"""
Get songs from other pages of artist
:param thread_id: As usual
:param url: As usual
:param artist: As usual
"""
complete_url = self.start_url + url
raw_html = open_request(complete_url, delayed=self.delay_request)
for song_url, song in self.get_songs(raw_html):
self.task_queue.put(
{
'type': 3,
'url': song_url,
'song': song,
'artist': artist,
'n_errors': 0
}
)
def get_artists(self, thread_id, url):
"""
Method to get artists with URL from a web address
:param thread_id: As usual
:param url: As usual
"""
website = self.start_url + url
raw_html = open_request(website, delayed=self.delay_request)
artists_with_url = self.get_artists_with_url(raw_html)
for artist_url, artist in artists_with_url:
self.task_queue.put(
{
'type': 1,
'url': artist_url,
'artist': artist,
'n_errors': 0
}
)
def get_movies(self, thread_id, url):
# Get website HTML
"""
Get movie list from website
:param thread_id: As usual
:param url: URL of website from which movies are to be fetched
"""
website = self.start_url + url
raw_html = open_request(website, delayed=self.delay_request)
# Add movies to task queue
movies_with_url = self.get_movies_with_url(raw_html)
for url, movie in movies_with_url:
self.task_queue.put(
{
'type': 1,
'url': url,
'movie': movie,
'n_errors': 0
}
)
def get_artist_albums(self, thread_id, url, artist):
"""
Method to get all songs for an artist
:param thread_id: As usual
:param url: As usual
:param artist: Artist name
"""
website = self.start_url + '/' + url
raw_html = open_request(website, delayed=self.delay_request)
albums_with_songs = self.get_albums_with_songs(raw_html)
for album, song_with_url in albums_with_songs:
for song_url, song in song_with_url:
self.task_queue.put({
'type': 2,
'song': song,
'url': song_url,
'album': album,
'album_url': url,
'artist': artist,
'n_errors': 0
})
def download_song(self, thread_id, url, song, movie, movie_url):
"""
Method to get song details from website.
:param thread_id: As usual
:param url: URL of song
:param song: Name of song
:param movie: Name of movie
:param movie_url: URL of movie
"""
# Song already exists
if db_operations.exists_song(self.start_url, url):
print_util.print_warning(
'{0} -> Song {1} already exists. Skipping.'.format(
thread_id,
song
)
)
return
# Get HTML
song_url_ = self.start_url + url
song_html = open_request(song_url_, delayed=self.delay_request)
lyrics, singers, music_by, lyricist = self.get_song_details(song_html)
# Save in database
db_operations.save(
song=song,
song_url=url,
movie=movie,
movie_url=movie_url,
start_url=self.start_url,
lyrics=lyrics,
singers=singers,
director=music_by,
lyricist=lyricist
)
def download_movie(self, thread_id, url, movie):
"""
Method to get all songs from a movie website.
:param thread_id: As usual
:param url: URL of movie
:param movie: Name of movie
"""
movie_website = self.start_url + url
raw_html = open_request(movie_website, delayed=self.delay_request)
song_with_url = self.get_songs_with_url(raw_html)
# No new songs added
if db_operations.number_of_songs(self.start_url, url) == len(
song_with_url):
db_operations.update_last_crawl(self.start_url, url)
print_util.print_warning(
'{0} --> Movie {1} contains no new songs. Skipping.'.format(
thread_id,
movie
)
)
return
# Add all songs
for song_url, song in song_with_url:
self.task_queue.put(
{
'type': 2,
'url': song_url,
'song': song,
'movie': movie,
'movie_url': url,
'n_errors': 0
}
)
def get_artist(self, thread_id, url, artist):
"""
Get songs for artist from URL in two parts:
1. Get songs from first page (:param url)
2. Add all other pages to task queue
:param thread_id:
:param url:
:param artist:
"""
complete_url = self.start_url + url
raw_html = open_request(complete_url, delayed=self.delay_request)
pages = self.get_pages_for_artist(raw_html)
# Add all songs from current page
for song_url, song in self.get_songs(raw_html):
self.task_queue.put(
{
'type': 3,
'url': song_url,
'song': song,
'artist': artist,
'n_errors': 0
}
)
# Add rest of pages in task queue
for page in pages[1:]:
self.task_queue.put(
{
'type': 2,
'url': page,
'artist': artist,
'n_errors': 0
}
)
