def __init__(self, url):
super(newpct_page, self).__init__()
self.url = url
self.bs4 = bs4(url)
self.id = url.__hash__()
self.get_info()
self.bs4 = None
def get_links_pagination(self, url):
this_bs4 = bs4(url)
pre_links = []
for link in this_bs4.soup.find_all(
"ul", class_="buscar-list")[0].findAll('a', href=True):
pre_links.append(link['href'].encode('utf-8'))
return pre_links
def __init__(self, url):
self.url = url
self.bs4 = bs4(url)
id = re.findall('\d+', url)
self.id = id[0]
self.get_info()
self.bs4 = None
super(filmaffinity_page, self).__init__()
def get_links_vo(url):
return_link_list = []
this_bs4 = bs4(url)
for link in this_bs4.get_all_links():
if any(re.findall(tag_vo, link['href'])):
if any(re.findall(pagination_vo, link['href'])) and not any(
re.findall(pagination_vo, url)):
return_link_list += get_links_vo(link['href'])
else:
if not any(re.findall(pagination_vo, link['href'])):
return_link_list.append(link['href'])
return return_link_list
def __init__(self, url):
self.url = url
self.bs4 = bs4(url)
self.id = url.__hash__()
file_path = os.path.abspath(
os.path.join(os.path.join(os.path.dirname(__file__)),
os.pardir)) + '/state/newpct_series/%s.json' % self.id
self.json = self.readJSONfile(file_path)
self.get_info()
self.bs4 = None
def get_links_hd(url):
return_link_list = []
this_bs4 = bs4(url)
for link in this_bs4.get_all_links():
if any(re.findall(tag_hd, link['href'])):
if any(re.findall(pagination_hd, link['href'])) and not any(
re.findall(pagination_hd, url)):
return_link_list += get_links_hd(link['href'])
else:
if not any(re.findall(pagination_hd, link['href'])):
return_link_list.append(link['href'])
#return_link_list = ['http://www.newpct1.com/series-hd/anatomia-de-grey/2259']
return return_link_list