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, search, limite, page):
bb = True
self.page = page
self.search = search
while bb == True:
url = 'https://en.wikipedia.org/w/index.php?limit='+limite+'&offset='+self.page+'&search='+((self.search).replace(' ', '+'))
print url
d = Download(url)
chapters = d.get_tags('ul', 'class', 'mw-search-results')
title = d.get_tags_file(str(chapters[0]),'div', 'class', 'mw-search-result-heading')
desc = d.get_tags_file(str(chapters[0]),'div', 'class', 'searchresult')
index = 0
link = []
for index in range(len(title)):
link.append(d.get_url_wikipedia(title[index], 'a', 'href'))
text_title = d.get_tags_text(str(title[index]))
text_desc = d.get_tags_text(str(desc[index]))
print link
print '\033[94m[',(index+1), '] ', text_title, '\033[0m\n', text_desc,'\n'
option=raw_input("ingrese el numero de una busqueda\npresione n para ir a la pagina siguiente\npresione p para ir a la pagina anterior\n")
if(option == 'n'):
self.page = str(int(float(self.page)) + int(float(limite)))
print '\n\n'
if(option == 'p' and int(float(self.page)) >= 0 ):
self.page = str(int(float(self.page)) - int(float(limite)))
print '\n\n'
if(option.isdigit()):
if(int(float(option)) > 0 and int(float(option)) <= (index+1)):
a = 'https://en.wikipedia.org'+str(link[int(float(option))-1][0])
v = Download(a)
div = v.get_tags('div', 'id', 'bodyContent')
text_page = v.get_tags_text(str(div[0]))
print '\n',a,'\n','\033[97m'+text_page+'\033[0m\n'
bb = False
chapters = []
chapters = []
title = []
desc = []
text_title = []
text_desc = []
url = ''
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'