def parse_attr(self, response):
#####TOMA LA FECHA#####
fecha = response.css('time.published ::text').get().strip()
#####BÚSCA LA PALABRA DOWNLOAD#####
link = response.xpath('//*/div[28]/b/span/a/@href').extract_first()
if link is None:
link = response.css('div > b > span > a ::attr(href)').get()
if link is None:
link = response.xpath(
'//*/div[2]/div/div[13]/a/@href').extract_first()
prev_inf = link
#####IMPRIME INFORMACIÓN#####
imprime_datos(response.meta['titulo'], fecha,
response.meta['cantante'], response.meta['album'],
response.meta['referer'], prev_inf)
#####INSERTA EN BD#####
self.inserta_BD(response, fecha, prev_inf)
#####LLAMA AL REFERER#####
infringing = self.Abre_pag(prev_inf)
imprime_datos(response.meta['titulo'], fecha,
response.meta['cantante'], response.meta['album'],
response.meta['referer'], infringing)
#####INSERTA EN BD#####
self.inserta_BD(response, fecha, infringing)
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_attr(self, response):
fecha = response.css('div.post-body.entry-content > div > div.post-info-icon.tanggal > span ::text').get().strip()
prev_inf = response.xpath('//*[@class="post-body entry-content"]/div[2]/div[3]/a/@href').get()
infringing = open_adfly(prev_inf,'span[id*="skip_button"]')
imprime_datos(response.meta['titulo'], fecha, response.meta['cantante'], response.meta['album'], response.meta['referer'], infringing)
#####INSERTA EN BD#####
if self.c.existe_inf(infringing, self.id_domin) == False:
if infringing is not None:
#if veri(infringing) == True:
self.c.inserta_item(response.meta['titulo'], response.meta['cantante'], response.meta['album'], response.meta['referer'], infringing, fecha, self.id_domin)
#####INSERTA EN BD#####
if self.c.existe_inf(prev_inf, self.id_domin) == False:
#if veri(prev_inf) == True:
self.c.inserta_item(response.meta['titulo'], response.meta['cantante'], response.meta['album'], response.meta['referer'], prev_inf, 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):
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 extrae_categoria(driver):
global pag
next_page = 1
while next_page:
print(
"#################################### Página {} ####################################"
.format(pag))
for a in driver.find_elements_by_css_selector(
'div#blog-entries > article h2 > a'):
titulo = a.get_attribute('title').replace('(FLAC)',
'').replace('(Mp3)', '')
referer = a.get_attribute('href')
cantante, album = separa_titulo(titulo, '–')
time.sleep(2)
driver.execute_script("window.open(arguments[0]);", referer)
driver.switch_to.window(driver.window_handles[2])
ref_inf = extrae_infringing(driver)
if ref_inf:
for inf in ref_inf:
mega_link = get_mega(inf)
if mega_link != False:
if mega_link.find('mega') != -1:
if c.existe_inf(mega_link) == False:
imprime_datos(titulo, fecha, cantante, album,
referer, mega_link)
c.inserta_item(titulo, cantante, album,
referer, mega_link, fecha,
id_domin)
v.muestra_item_guardado(titulo)
close_taps(driver, 1)
try:
next_page = driver.find_element_by_css_selector(
'a.next.page-numbers')
next_page.click()
pag += 1
except:
print('Ocurrió un error al cambiar de página')
break
close_taps(driver, 0)
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
#####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()