Created
August 17, 2018 23:11
-
-
Save ColinGreybosh/d8ab335efdeb19dbb7a3e4a26cda8489 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from collections import OrderedDict | |
from urllib.parse import quote | |
from mp3_tagger import * | |
import requests | |
import bs4 | |
import os | |
__dirpath__ = f'{os.path.dirname(os.path.abspath(__file__))}/' | |
def get_google_results(query): | |
base_url = 'https://www.google.com/search?q=' | |
url = base_url + quote(query) | |
headers = {'user-agent': | |
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) ' | |
'AppleWebKit/537.36 (KHTML, like Gecko) ' | |
'Chrome/60.0.3112.113 Safari/537.36'} | |
res = requests.get(url, headers=headers) | |
res.raise_for_status() | |
return res | |
def save_html_to_file(res, file_name): | |
html_filename = f'data/{file_name}.html' | |
os.makedirs(os.path.dirname(html_filename), exist_ok=True) | |
with open(html_filename, "wb") as html_file: | |
for chunk in res.iter_content(100000): | |
html_file.write(chunk) | |
html_file.close() | |
def parse_results(res): | |
soup = bs4.BeautifulSoup(res.text, "lxml") | |
labels = soup.select('span.w8qArf > a') | |
info = soup.select('span.LrzXr.kno-fv') | |
list(OrderedDict.fromkeys(labels)) | |
list(OrderedDict.fromkeys(info)) | |
return list(zip([tag.getText() for tag in labels], | |
[tag.getText() for tag in info])) | |
def save_tags(tags, mp3_filename): | |
print(tags) | |
song = MP3File(f'{__dirpath__}{mp3_filename}') | |
for tag in tags: | |
if 'Genre' in tag[0]: | |
print(tag[1]) | |
song.set_version(VERSION_2) | |
song.genre = tag[1].replace(', ', ';') | |
song.set_version(VERSION_BOTH) | |
if 'Released' in tag[0]: | |
print(tag[1]) | |
song.year = tag[1] | |
song.save() | |
def main(): | |
directory = os.fsencode(__dirpath__) | |
for file in os.listdir(directory): | |
mp3_filename = os.fsdecode(file) | |
if mp3_filename.endswith(".mp3"): | |
song_name = mp3_filename[:-4] | |
print(song_name) | |
res = get_google_results(f'{song_name} song genre and released') | |
save_html_to_file(res, song_name) | |
music_tags = parse_results(res) | |
if len(music_tags) != 0: | |
save_tags(music_tags, mp3_filename) | |
print('') | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment