def inserta_BD(self, response, fecha, inf):
if self.c.existe_inf(inf, self.id_domin) == False:
if veri(inf) == True:
self.c.inserta_item(response.meta['titulo'],
response.meta['cantante'],
response.meta['album'],
response.meta['referer'], inf, fecha,
self.id_domin)
def parse_attr2(self, response):
#print('ENTRA')
infringing = response.css('a.download-mp3-url ::attr(href)').get()
#print(infringing[-3::])
if infringing[-3::] == 'mp3':
if veri(infringing) == True:
imprime_datos(response.meta['Titulo'], response.meta['Fecha'],
response.meta['Cantante'],
response.meta['Album'], response.meta['referer'],
infringing)
def parse_attr(self, response):
if response.css('a.btn-dl'):
infringing = response.css('a.btn-dl ::attr(href)').get()
imprime_datos(response.meta['titulo'], response.meta['fecha'],
response.meta['cantante'], response.meta['album'],
response.meta['referer'], infringing)
#####INSERTA EN BD#####
if veri(infringing) == True:
if self.c.existe_inf(infringing, self.id_domin) == False:
self.c.inserta_item(response.meta['titulo'],
response.meta['cantante'],
response.meta['album'],
response.meta['referer'], infringing,
response.meta['fecha'], self.id_domin)
def parse_attr2(self, response):
referer = response.url
infringing = response.css(
'div.post-body.entry-content > center > table > tbody > tr > td > center > a ::attr(href)'
).get()
imprime_datos(response.meta['titulo'], response.meta['fecha'],
response.meta['cantante'], response.meta['album'],
referer, infringing)
#####INSERTA EN BD#####
if veri(infringing) == True:
if self.c.existe_inf(infringing, self.id_domin) == False:
self.c.inserta_item(response.meta['titulo'],
response.meta['cantante'],
response.meta['album'], referer,
infringing, response.meta['fecha'],
self.id_domin)
def parse_attr(self, response):
inf = response.css('button#download-btn ::attr(onclick)').get()
infringing = separa(inf, "'", 1)
for tb in response.css('td.column-title ::text'):
titulo = tb.get()
print('\n*****************DATOS*****************')
print('infringing: ' + infringing)
print('referer: ' + response.meta['referer'])
print('titulo: ' + titulo)
print('fecha: ' + response.meta['fecha'])
print('cantante: ' + response.meta['cantante'])
print('album: ' + response.meta['album'])
print('***************************************\n')
#####INSERTA EN BD#####
if veri(infringing) == True:
self.c.inserta_item(titulo, response.meta['cantante'], response.meta['album'],response.meta['referer'], infringing, response.meta['fecha'], self.id_domin)
def get_datos(self, titulo, fecha, cantante, album, referer, infringing):
#print('LEN: ' + str(len(titulo)))
#print('LEN: ' + str(len(infringing)))
#print('LEN: ' + str(len(referer)))
#print('LEN: ' + str(len(cantante)))
#print('LEN: ' + str(len(album)))
#print('titulo: ' + titulo[-1])
for i in range(len(infringing)):
print('\n*****************DATOS*****************')
print('infringing: ' + infringing[i])
print('referer: ' + referer[i])
print('titulo: ' + titulo[i])
print('fecha: ' + fecha)
print('cantante: ' + cantante[i])
print('album: ' + album[i])
print('***************************************\n')
#####INSERTA EN BD#####
if veri(infringing[i]) == True:
if self.c.existe_inf(infringing[i], self.id_domin) == False:
self.c.inserta_item(titulo[i], cantante[i], album[i], referer[i], infringing[i], fecha, self.id_domin)
def parse_attr(self, response):
infringing = response.css('h3 > a ::attr(href)').get()
print('\n*****************DATOS*****************')
print('infringing: ' + infringing)
print('referer: ' + response.meta['referer'])
print('titulo: ' + response.meta['titulo'])
print('fecha: ' + str(response.meta['fecha']))
print('cantante: ' + response.meta['cantante'])
print('album: ' + response.meta['album'])
print('***************************************\n')
#####INSERTA EN BD#####
if veri(infringing) == True:
if self.c.existe_inf(infringing, self.id_domin) == False:
self.c.inserta_item(response.meta['titulo'],
response.meta['cantante'],
response.meta['album'],
response.meta['referer'], infringing,
response.meta['fecha'], self.id_domin)
def parse_attr(self, response):
url = str(response.url)
link_mega = open_adfly(url, 'skip_bu2tton')
if link_mega is not None:
link_mega = 'mega' + self.separaLink(link_mega)
#return link_mega
infringing = str(unquote(link_mega))
print('\n*****************DATOS*****************')
print('infringing: ' + infringing)
print('fecha: ' + response.meta['fecha'])
print('referer: ' + response.meta['referer'])
print('titulo: '+ response.meta['titulo'])
print('cantante: '+ response.meta['cantante'])
print('album: '+ response.meta['album'])
print('***************************************\n')
#####INSERTA EN BD#####
if veri(infringing) == True:
if c.existe_inf(infringing, self.id_domin) == False:
self.c.inserta_item(response.meta['titulo'], response.meta['cantante'], response.meta['album'],response.meta['referer'], infringing, response.meta['fecha'], self.id_domin)
def parse_attr(self, response):
Referer = response.url
Artista = response.xpath(
'/html/body/div/div[2]/div/div[2]/span[2]/text()').extract_first()
Album = response.xpath(
'/html/body/div/div[2]/div/div[2]/span[4]/text()').extract_first()
Fecha = response.xpath(
'/html/body/div/div[2]/div/div[2]/span[6]/text()').extract_first()
Infringing = response.css(
'div#download-btn-div :nth-child(4) ::attr(onclick)').get()
Infringing = separa(Infringing, '"', 1)
for tr in response.css('tbody > tr :nth-child(1)'):
Cancion = tr.css('::text').get()
#####IMPRIME INFORMACIÓN#####
imprime_datos(Cancion, Fecha, Artista, Album, Referer, Infringing)
#####INSERTA EN BD#####
if self.c.existe_inf(Infringing, self.id_domin) == False:
if veri(Infringing) == True:
self.c.inserta_item(Cancion, Artista, Album, Referer,
Infringing, Fecha, self.id_domin)
def parse_attr(self, response):
titulo = response.css('h1 > a ::text').get()
cantante, album = separa_titulo(titulo, '-')
fecha = response.css('time > a ::text').get()
fecha = strip_spaces(fecha)
fecha = separa(fecha, '-', 0)
infringing = response.css(
'div.post__content > p > a ::attr(href)').get()
try:
if infringing.find('images') > 0:
infringing = response.xpath(
'//*[@id="post"]/div[2]/p/a[2]/@href').get()
if infringing is not None or infringing.find('megaupload') > 0:
if veri(infringing) == True:
imprime_datos(titulo, fecha, cantante, album,
response.meta['referer'], infringing)
if self.c.existe_inf(infringing, self.id_domin) == False:
self.c.inserta_item(titulo, cantante, album,
response.meta['referer'],
infringing, fecha, self.id_domin)
except:
pass
def parse_attr(self, response):
#####VARIABLE#####
found = 0
item = response.meta['item']
c = response.meta['controler']
#####TOMA EL ID DE LA PÁGINA#####
post_id = response.xpath(
'//*[@id="page"]/div/article/div/@id').extract()[0]
#####RECOLECTA LOS DATOS DE LA PÁGINA#####
item['titulo'] = response.xpath('//*[@id="' + post_id +
'"]/div/header/h1/text()').extract()[0]
item['href'] = response.url
item['fecha'] = response.xpath('//*[@id="' + post_id +
'"]/div/header/div/text()').extract()[0]
#####SEPARA CANTANTE Y ALBUM#####
separacion = str(item['titulo']).split('–')
cantante, album = separacion[0], separacion[1]
#####BÚSCA LA PALABRA DOWNLOAD#####
for link in response.xpath(
'//a[text()="DOWNLOAD AUDIO"]/@href').extract():
found = 1
item['infringing'] = link
if found == 0:
for link in response.xpath(
'//a[text()="DOWNLOAD ZIP"]/@href').extract():
item['infringing'] = link
#####INSERTA EN BD#####
if veri(item['infringing']) == True:
if c.existe_inf(item['infringing'], self.id_domin) == False:
c.inserta_item(str(item['titulo']), cantante, album,
str(item['href']), str(item['infringing']),
str(item['fecha']), self.id_domin)
return item
#####ESPERA A QUE CARGUE LA PÁGINA#####
WebDriverWait(driver, 10).until(EC.element_to_be_clickable((By.CSS_SELECTOR, "h2 > a")))
#####GUARDA LA PÁGINA PRINCIPAL#####
main_window = driver.current_window_handle
#####TOMA EL HREF DE LA PÁGINA SIGUIENTE#####
next_page = driver.find_element_by_css_selector('a.sa.sa-nextpage.tip').get_attribute('href')
#####RECORRE TODAS LAS PÁGINAS#####
while next_page is not None:
#####TOMA LOS DATOS#####
for a in driver.find_elements_by_css_selector("h2 > a"):
referer = a.get_attribute('href')
titulo = a.find_element_by_css_selector('span').text
cantante, album = separa_titulo(titulo, '-')
fecha = date.today().strftime("%B %d, %Y")
#####ABRE UNA NUEVA PESTAÑA#####
driver.execute_script("window.open(arguments[0]);", referer)
driver.switch_to.window(driver.window_handles[1])
infringing = driver.find_element_by_xpath('//*[@id="shell"]/section/div[1]/div[2]/article/section/center/a').get_attribute('href')
imprime_datos(titulo, fecha, cantante, album, referer, infringing)
if c.existe_inf(infringing, id_domin) == False:
if veri(infringing) == True:
c.inserta_item(titulo, cantante, album, referer, infringing, fecha, id_domin)
#####CIERRA LA PESTAÑA#####
driver.close()
#####CAMBIA A LA PÁGINA PRINCIPAL#####
driver.switch_to.window(main_window)
#####ABRE LA SIGUIENTE PÁGINA#####
driver.get(next_page)
#####TOMA EL HREF DE LA PÁGINA SIGUIENTE#####
next_page = driver.find_element_by_css_selector('a.sa.sa-nextpage.tip').get_attribute('href')
driver.quit()
def parse(self, response):
id = '0'
#####COMENTARIOS#####
print('\n########Pagina ' + str(self._num_pagina) + '########')
for art in response.xpath('//*[@id="content"]/div[1]/article'):
band = True
titulo = art.css(' h2 > a ::text').get()
fecha = art.css('p > span > a ::text').get()
album, cantante = separa_titulo(titulo, '-')
referer = art.css('div > div.post-entry-content > a ::attr(href)').get()
id = self.get_id(referer,'/', 3)
infringing = self.get_infr(id)
if referer is None:
referer = art.css('div > div > p > strong > a ::attr(href)').get()
if referer is None:
#print('PATH: ' + str(art.xpath('//div/div/p[2]/a').extract()))
#print('A: ' + str(art.css('div.post-entry-content').get()))
for p in art.css('div.post-entry-content > strong > span > span > a') or art.css('div.post-entry-content > p > a'):
band = False
#print ('A: ' + str(art.css('div.post-entry-content').get()))
referer = p.css('::attr(href)').get()
id = self.get_id(referer,'/', 3)
infringing = self.get_infr(id)
#print('REF: ' + referer)
if self.comprueba_refer(referer, 'open') == True:
r = art.css('div.post-entry-content > p')
#print('A: ' + str(art.css('div.post-entry-content > p > strong').get()))
if r.css('strong') is not None:
r = r.css('strong > span')
referer = r.css('a ::attr(href)').get()
id = self.get_id(referer,'/', 3)
infringing = self.get_infr(id)
#####INSERTA EN BD#####
if veri(infringing) == True:
if self.c.existe_inf(infringing, self.id_domin) == False:
self.c.inserta_item(titulo, cantante, album, referer, infringing, fecha, self.id_domin)
else:
id = self.get_id(referer,'/', 3)
infringing = self.get_infr(id)
self.imprime_datos(titulo, fecha, cantante, album, referer, infringing)
else:
id = self.get_id(referer,'/', 3)
infringing = self.get_infr(id)
else:
if self.comprueba_refer(referer, '?') == True:
infringing = self.get_Mega(referer)
if band == True:
#####INSERTA EN BD#####
if veri(infringing) == True:
if self.c.existe_inf(infringing, self.id_domin) == False:
self.c.inserta_item(titulo, cantante, album, referer, infringing, fecha, self.id_domin)
self.imprime_datos(titulo, fecha, cantante, album, referer, infringing)
#referer = None
self._num_pagina+=1
try:
next_page = response.css('a.next.page-numbers ::attr(href)').get()
if next_page is not None:
yield response.follow(next_page, callback= self.parse)
except:
print('Hubo un problema al abrir la página siguiente')