def _get_thumbnail_url(self, url):
browser = Browser()
browser.open(url)
img_ = browser.cssselect('.movie_poster_area img')
if img_:
url = img_[0].get('src')
if not RE_INVALID_IMG.search(url):
return url
def _get_media_info(self, url):
browser = Browser()
browser.open(url)
info = {}
band_ = browser.cssselect('.band_name')
if band_:
info['artist'] = clean(band_[0].text, 1)
genre_ = browser.cssselect('.product_genre .data')
if genre_:
info['genre'] = [clean(g, 1) for g in genre_[0].text.split(',')]
return info
def _torrent_urls(self, url):
'''Iterate over torrent urls fetched from the raw html data.
'''
browser = Browser()
if browser.open(url):
for link in browser.links(url_regex=RE_URL_MAGNET):
yield link.absolute_url
def _get_collection(url):
browser = Browser()
browser.open(url)
res = []
for tr in browser.cssselect('table#r2 tr', []):
if tr.cssselect('th'):
continue
refs = tr.cssselect('input[type="checkbox"]')
if not refs:
continue
ref = refs[0].get('name')
if not ref:
logger.error('failed to get reference from %s', html.tostring(refs[0], pretty_print=True))
continue
res.append(ref)
return res
def _get_download_url(url):
browser = Browser()
netloc_parts = urlparse(url).netloc.split('.')
if 'mediafire' in netloc_parts:
browser.open(url)
if browser.cssselect('#form_captcha'):
raise FilestubeError('failed to get url from %s: captcha' % url)
tags = browser.cssselect('.error_msg_title')
if tags:
raise FilestubeError('failed to get download url from %s: %s' % (url, tags[0].text))
tags = browser.cssselect('.download_link')
if tags:
data_ = html.tostring(tags[0])
res = re.compile(r'"(http://.*?)"').findall(data_)
if res:
return res[0]
raise FilestubeError('failed to get download url from %s' % url)
def _mirror_urls(self, url):
'''Iterate over mirror urls.
'''
browser = Browser()
browser.open(url)
results = browser.cssselect('div.download dl')
if not results:
errors = browser.cssselect('div.error')
if not (errors and RE_ERROR.search(errors[0].text)):
logger.error('failed to get mirror urls from %s', url)
return
for result in results:
# Skip sponsored links
res = result.cssselect('dd')
if res and RE_SPONSORED_LINK.search(html.tostring(res[0])):
continue
links = result.cssselect('dt a')
if links:
mirror_url = links[0].get('href')
if not mirror_url.startswith('/'):
yield mirror_url
def _get_torrent_url(self, url):
browser = Browser()
if browser.open(url):
links = browser.cssselect('a[title="Magnet Link"]')
if links:
return links[0].get('href')
def _get_torrent_url(self, url):
browser = Browser()
if browser.open(url):
links = browser.cssselect('a.btn-magnet')
if links:
return links[0].get('href')