def get_files(self, url):
position_link = 0
if url.find('youtube.com')>position_link:
d = Download(url)
div = d.get_tags('div', 'class', 'playlist-videos-container yt-scrollbar-dark yt-scrollbar')
indice_div = 0
videos = d.get_tags_html(str(div[indice_div]), 'a', 'class', 'yt-uix-sessionlink')
# print videos[:]
if videos != 'error':
links = d.get_urls('youtube', videos, 'href')
video_url_preffix = 'https://www.youtube.com'
for valor in links:
valor = (video_url_preffix+valor).split('&')[0]
self.download_now(str(valor), 'mp4', '/Users/samuel/Documents/python')
print '\n'
print 'se descargo la lista el archivo'
else: print 'link de youtube no hace referencia a un archivo valido'
def get_file(self, url):
position_link = 0
if url.find('slideshare.net')>position_link:
d = Download(url)
imgs = d.get_tags('img', 'class', 'slide_image')
if imgs != 'error':
links = d.get_urls('slideshare', imgs, 'data-full')
pdf = FPDF('P', 'pt', 'Letter')
index_cache = 0
index_link = 0
print "\nDownload images [",len(links),"]:\n"
for pagina_pdf in links:
file_path=urlretrieve(pagina_pdf.split('?')[index_link])[index_cache]
print " ", pagina_pdf
img=Image.open(file_path)
pdf.add_page(format = img.size)
pdf.image(file_path, x=0, y=0)
pdf.output('slideshare.pdf', 'F')
print 'se genero en archivo slideshare.pdf'
else: print 'link de slideshare no hace referencia a un archivo valido'
else: print 'link de slideshare no es valido'
