descarga revistas La Bicicleta

bicicletas.py

import wget, fitz, glob
import requests, time
from bs4 import BeautifulSoup

url='http://www.memoriachilena.gob.cl/602/w3-article-100795.html#documentos'
bs = BeautifulSoup(requests.get(url).text, 'lxml')

links = [link['href'] for link in bs.find_all('a')
            if '.pdf' in link.get('href','')]
print(len(links))

t0=time.time()
for ix, url in enumerate(links):
    if ix%10==5:
        print('%d/%d [DT=%f]' %(ix, len(links), round(time.time()-t0,2)))
    wget.download(url)
    
for fn in glob.glob('*.pdf'): 
    txt = [page.get_text() for page in fitz.open(fn)]
    print(fn, len(txt))