def search_lyrics(self, query, max_pages=1):
data = self.search(query, max_pages)
lyrics = {}
for entry in data["songs"]:
url, num = data["songs"][entry]["url"].split("#")
r = requests.get(url)
html = r.text
soup = BeautifulSoup(html, 'html.parser')
bucket = self._parse_lyrics(soup)
for song in bucket:
if bucket[song]["song_number"] == num:
lyrics[song] = bucket[song]
for entry in data["artists"]:
url = data["artists"][entry]["url"]
r = requests.get(url)
html = r.text
soup = BeautifulSoup(html, 'html.parser')
bucket = self._parse_artist(soup)
for album in bucket:
songs = bucket[album]
url = songs[0]["url"].replace("#1", "")
r = requests.get(url)
html = r.text
soup = BeautifulSoup(html, 'html.parser')
merge_dict(lyrics, self._parse_lyrics(soup))
for entry in data["albums"]:
url = data["albums"][entry]["url"]
r = requests.get(url)
html = r.text
soup = BeautifulSoup(html, 'html.parser')
merge_dict(lyrics, self._parse_lyrics(soup))
return lyrics
def search_discography(self, query, max_pages=1):
data = self.search(query, max_pages)
disco = {}
for k in data:
for entry in data[k]:
url = data[k][entry]["url"]
r = requests.get(url)
html = r.text
soup = BeautifulSoup(html, 'html.parser')
if "/lyrics/" not in url:
merge_dict(disco, self._parse_artist(soup))
return disco
def search(self, query, max_pages=1):
r = requests.get(self.search_url, {"q": query})
html = r.text
soup = BeautifulSoup(html, 'html.parser')
data = self._parse_search(soup)
if max_pages == -1:
max_pages = data["num_pages"]
if max_pages > 1 and data["num_pages"] > 1:
for p in range(2, data["num_pages"] + 1):
r = requests.get(self.search_url, {"q": query, "p": p})
html = r.text
soup = BeautifulSoup(html, 'html.parser')
bucket = self._parse_search(soup)
bucket.pop("num_pages")
merge_dict(data, bucket)
if p > max_pages:
break
data.pop("num_pages")
return data