styleyear-mp3

import requests
from mutagen.easyid3 import EasyID3
import os
import re
from lxml import html
import csv
import glob
import time
from fuzzywuzzy import fuzz
import sys
from pathlib import Path

def return_tag_data(mp3file):
    audio = EasyID3(mp3file)
    return audio['artist'][0], audio['title'][0]

def write_tag_data(mp3file,style):
    audio = EasyID3(mp3file)
    audio['genre'] = style
    audio.save()

def write_tag_data(mp3file,year):
    audio = EasyID3(mp3file)
    audio['date'] = year
    audio.save()

def get_style(artist_c, title_c, artist, title):
    s = requests.Session()
    headers = {'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
                'Accept-Encoding': 'gzip, deflate, br',
                'Accept-Language': 'en-US,en;q=0.9',
                'Connection': 'keep-alive',
                'Host': 'www.discogs.com',
                'Referer': 'https://www.discogs.com/search/advanced',
                'Upgrade-Insecure-Requests': '1',
                'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36'}
    try:
        r = s.get('https://www.discogs.com/search/?type=master&title='+title_c.replace(' ','+')+'&artist='+artist_c.replace(' ','+')+\
                  '&label=&track=&catno=&barcode=&anv=&format=&credit=&genre=&style=&country=&year=&submitter=&contributor=&matrix=&advanced=1',headers=headers)
    except:
        time.sleep(2)
        try:
            r = s.get('https://www.discogs.com/search/?type=master&title='+title_c.replace(' ','+')+'&artist='+artist_c.replace(' ','+')+\
                      '&label=&track=&catno=&barcode=&anv=&format=&credit=&genre=&style=&country=&year=&submitter=&contributor=&matrix=&advanced=1',headers=headers)
        except:
            r = []
    if r != []:
        if 'find anything in the Discogs database matching your search criteria' not in r.text:
            sections = html.fromstring(r.text).xpath('//div[contains(@class,"card card_large float_fix")]')
            for section in sections:
                x = lambda x: html.fromstring(html.tostring(section)).xpath(x)
                y = lambda y: re.findall(y,str(html.tostring(section)),re.DOTALL)
                new_title = x('//a[@class="search_result_title"]//@title')[0].strip()
                new_artist = y('spanitemprop title="(.+?)"')[0].strip()
                if (fuzz.token_sort_ratio(title.lower().strip(),new_title.lower().strip()) > 50) and (fuzz.token_sort_ratio(artist.lower().strip(),new_artist.lower().strip()) > 50):
                    link = "https://www.discogs.com"+x('//a[@class="search_result_title"]//@href')[0].strip()
                    headers['Referer'] = 'https://www.discogs.com/search/?type=master&title='+title_c.replace(' ','+')+'&artist='+artist_c.replace(' ','+')+\
                                         '&label=&track=&catno=&barcode=&anv=&format=&credit=&genre=&style=&country=&year=&submitter=&contributor=&matrix=&advanced=1'
                    r1 = s.get(link,headers=headers)
                    if '404! Oh no!' not in r1.text:
                        style = ", ".join(html.fromstring(r1.text).xpath('//div[contains(text(),"Style:")]/following::div[@class="content"][1]//a//text()'))
                        return style

def clean(string):
    string = re.sub(r'\([^)]*\)', '', string).strip()
    if ',' in string:
        string = string.split(',')[0].strip()
    if '&' in string:
        string = string.split('&')[0].strip()
    return string

def get_year(artist_c, title_c, artist, title):
    s = requests.Session()
    headers = {'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
                'Accept-Encoding': 'gzip, deflate, br',
                'Accept-Language': 'en-US,en;q=0.9',
                'Connection': 'keep-alive',
                'Host': 'www.discogs.com',
                'Referer': 'https://www.discogs.com/search/advanced',
                'Upgrade-Insecure-Requests': '1',
                'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36'}
    try:
        r = s.get('https://www.discogs.com/search/?type=master&title='+title_c.replace(' ','+')+'&artist='+artist_c.replace(' ','+')+\
                  '&label=&track=&catno=&barcode=&anv=&format=&credit=&genre=&style=&country=&year=&submitter=&contributor=&matrix=&advanced=1',headers=headers)
    except:
        time.sleep(2)
        try:
            r = s.get('https://www.discogs.com/search/?type=master&title='+title_c.replace(' ','+')+'&artist='+artist_c.replace(' ','+')+\
                      '&label=&track=&catno=&barcode=&anv=&format=&credit=&genre=&style=&country=&year=&submitter=&contributor=&matrix=&advanced=1',headers=headers)
        except:
            r = []
    if r != []:
        if 'find anything in the Discogs database matching your search criteria' not in r.text:
            sections = html.fromstring(r.text).xpath('//div[contains(@class,"card card_large float_fix")]')
            for section in sections:
                x = lambda x: html.fromstring(html.tostring(section)).xpath(x)
                y = lambda y: re.findall(y,str(html.tostring(section)),re.DOTALL)
                new_title = x('//a[@class="search_result_title"]//@title')[0].strip()
                new_artist = y('spanitemprop title="(.+?)"')[0].strip()
                if (fuzz.token_sort_ratio(title.lower().strip(),new_title.lower().strip()) > 50) and (fuzz.token_sort_ratio(artist.lower().strip(),new_artist.lower().strip()) > 50):
                    link = "https://www.discogs.com"+x('//a[@class="search_result_title"]//@href')[0].strip()
                    headers['Referer'] = 'https://www.discogs.com/search/?type=master&title='+title_c.replace(' ','+')+'&artist='+artist_c.replace(' ','+')+\
                                         '&label=&track=&catno=&barcode=&anv=&format=&credit=&genre=&style=&country=&year=&submitter=&contributor=&matrix=&advanced=1'
                    r1 = s.get(link,headers=headers)
                    if '404! Oh no!' not in r1.text:
                        year = ", ".join(html.fromstring(r1.text).xpath('//div[contains(text(),"Year:")]/following::div[@class="content"][1]//a//text()'))
                        return year


def clean(string):
    string = re.sub(r'\([^)]*\)', '', string).strip()
    if ',' in string:
        string = string.split(',')[0].strip()
    if '&' in string:
        string = string.split('&')[0].strip()
    return string

for mp3file in Path(sys.argv[1]).glob('**/*.mp3'):
    print (mp3file)
    artist, title = return_tag_data(mp3file)
    artist_c = clean(artist)
    title_c = clean(title)
    style = get_style(artist_c, title_c, artist, title)
    year = get_year(artist_c, title_c, artist, title)
    if style != None:
        print ("Artist : {}\nTitle : {}\nStyle : {}\nYear : {}\n".format(artist, title, style, year))
        write_tag_data(mp3file, style)
        write_tag_data(mp3file, year)