Scraping cancioneros part 2

lacuerda_new_scraper.py

import requests, pickle, sys
from bs4 import BeautifulSoup
from docx import Document       
from operator import methodcaller

url_bs = lambda url: BeautifulSoup(requests.get(url).text,'html5lib')  # magic!

def recopila_acordes(artista = 'Manu Chao'):       # "Manu Chao" -> manu_chao
    fartist = '_'.join(map(methodcaller("lower"),artista.split()))   
    url = f'https://acordes.lacuerda.net/{fartist}/'
    
    songs = url_bs(url).find_all('ul',attrs={'class':'b_main'})[0].find_all('a')   
    songs = [(s.text, url+s['href']+'.shtml') for s in songs]
    fetch = {' '.join(s[0].split()[:-1]): url_bs(s[1]) for s in songs}    
    fetched = {}
    for song_name, song_page in fetch.items():
        fv = song_page.find_all('div',attrs={'id':'t_body'})
        try:
            fetched[song_name] = fv[0].text 
        except:
            print("Unexpected error:", sys.exc_info()[0])
    
    print('Encontré %d canciones para %s' %(len(fetched), artista))
    return fetched

def make_ppt(data_canciones, artista):
    document = Document()
    document.add_heading(artista, 0)

    for songname, song_chords in data_canciones.items():
        document.add_heading(songname, level=1)
        document.add_paragraph(song_chords)   # style='Intense Quote'    
    fn = f'{artista}.docx';print('SAVING:', fn)
    document.save(fn)
    
def compilar_cancionero(artista):
    data_canciones = recopila_acordes(artista)
    make_ppt(data_canciones, artista)
    
if __name__ == '__main__':
  ARTISTAS = ['Charly Garcia','Fito Paez','Soda Stereo', 'Los Tres']
  for artist in ARTISTAS:
    compilar_cancionero(artist)