def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
if video_type == VIDEO_TYPES.TVSHOW and title:
test_url = '/tv-show/%s/' % (scraper_utils.to_slug(title))
test_url = scraper_utils.urljoin(self.base_url, test_url)
html = self._http_get(test_url, require_debrid=True, cache_limit=24)
posts = dom_parser2.parse_dom(html, 'div', {'id': re.compile('post-\d+')})
if posts:
result = {'url': scraper_utils.pathify_url(test_url), 'title': scraper_utils.cleanse_title(title), 'year': ''}
results.append(result)
elif video_type == VIDEO_TYPES.MOVIE:
search_title = re.sub('[^A-Za-z0-9 ]', '', title.lower())
html = self._http_get(self.base_url, params={'s': search_title}, require_debrid=True, cache_limit=1)
norm_title = scraper_utils.normalize_title(title)
for _attrs, post in dom_parser2.parse_dom(html, 'div', {'id': re.compile('post-\d+')}):
match = re.search('<h\d+[^>]*>\s*<a\s+href="([^"]+)[^>]*>(.*?)</a>', post)
if match:
post_url, post_title = match.groups()
if '/tv-show/' in post or self.__too_old(post): continue
post_title = re.sub('<[^>]*>', '', post_title)
meta = scraper_utils.parse_movie_link(post_title)
full_title = '%s [%s] (%sp)' % (meta['title'], meta['extra'], meta['height'])
match_year = meta['year']
match_norm_title = scraper_utils.normalize_title(meta['title'])
if (match_norm_title in norm_title or norm_title in match_norm_title) and (not year or not match_year or year == match_year):
result = {'url': scraper_utils.pathify_url(post_url), 'title': scraper_utils.cleanse_title(full_title), 'year': match_year}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
if video_type == VIDEO_TYPES.TVSHOW and title:
test_url = '/tv-show/%s/' % (scraper_utils.to_slug(title))
test_url = scraper_utils.urljoin(self.base_url, test_url)
html = self._http_get(test_url, require_debrid=True, cache_limit=24)
posts = dom_parser2.parse_dom(html, 'div', {'id': re.compile('post-\d+')})
if posts:
result = {'url': scraper_utils.pathify_url(test_url), 'title': scraper_utils.cleanse_title(title), 'year': ''}
results.append(result)
elif video_type == VIDEO_TYPES.MOVIE:
search_title = re.sub('[^A-Za-z0-9 ]', '', title.lower())
html = self._http_get(self.base_url, params={'s': search_title}, require_debrid=True, cache_limit=1)
norm_title = scraper_utils.normalize_title(title)
for _attrs, post in dom_parser2.parse_dom(html, 'div', {'id': re.compile('post-\d+')}):
match = re.search('<h\d+[^>]*>\s*<a\s+href="([^"]+)[^>]*>(.*?)</a>', post)
if match:
post_url, post_title = match.groups()
if '/tv-show/' in post or self.__too_old(post): continue
post_title = re.sub('<[^>]*>', '', post_title)
meta = scraper_utils.parse_movie_link(post_title)
full_title = '%s [%s] (%sp)' % (meta['title'], meta['extra'], meta['height'])
match_year = meta['year']
match_norm_title = scraper_utils.normalize_title(meta['title'])
if (match_norm_title in norm_title or norm_title in match_norm_title) and (not year or not match_year or year == match_year):
result = {'url': scraper_utils.pathify_url(post_url), 'title': scraper_utils.cleanse_title(full_title), 'year': match_year}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
slug = scraper_utils.to_slug(title)
test_url = scraper_utils.urljoin(self.base_url, slug)
test_url += '-%s' % (year)
html = self._http_get(test_url, cache_limit=8)
if html:
result = {'title': scraper_utils.cleanse_title(title), 'year': year, 'url': scraper_utils.pathify_url(test_url)}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
slug = scraper_utils.to_slug(title)
test_url = scraper_utils.urljoin(self.base_url, slug)
test_url += '-%s' % (year)
html = self._http_get(test_url, cache_limit=8)
if html:
result = {'title': scraper_utils.cleanse_title(title), 'year': year, 'url': scraper_utils.pathify_url(test_url)}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
search_url = scraper_utils.urljoin(self.base_url, '/search/%s.html')
search_url = search_url % (scraper_utils.to_slug(title))
html = self._http_get(search_url, cache_limit=8)
for _attrs, item in dom_parser2.parse_dom(html, 'div', {'class': 'slideposter'}):
match_url = dom_parser2.parse_dom(item, 'a', req='href')
match_title_year = dom_parser2.parse_dom(item, 'img', req='alt')
if match_url and match_title_year:
match_url = match_url[0].attrs['href']
match_title_year = match_title_year[0].attrs['alt']
match_title, match_year = scraper_utils.extra_year(match_title_year)
if not year or not match_year or year == match_year:
result = {'title': scraper_utils.cleanse_title(match_title), 'year': match_year, 'url': scraper_utils.pathify_url(match_url)}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
if video_type == VIDEO_TYPES.TVSHOW and title:
test_url = '/show/%s/' % (scraper_utils.to_slug(title))
test_url = scraper_utils.urljoin(self.base_url, test_url)
html = self._http_get(test_url, require_debrid=True, cache_limit=24)
posts = dom_parser2.parse_dom(html, 'div', {'id': re.compile('post-\d+')})
if posts and CATEGORIES[video_type] in posts[0].content:
match = re.search('<div[^>]*>\s*show\s+name:.*?<a\s+href="([^"]+)[^>]+>(?!Season\s+\d+)([^<]+)', posts[0].content, re.I)
if match:
show_url, match_title = match.groups()
result = {'url': scraper_utils.pathify_url(show_url), 'title': scraper_utils.cleanse_title(match_title), 'year': ''}
results.append(result)
elif video_type == VIDEO_TYPES.MOVIE:
search_url = scraper_utils.urljoin(self.base_url, '/search/%s/')
search_title = re.sub('[^A-Za-z0-9 ]', '', title.lower())
search_url = search_url % (urllib.quote_plus(search_title))
headers = {'User-Agent': LOCAL_UA}
html = self._http_get(search_url, headers=headers, require_debrid=True, cache_limit=1)
headings = re.findall('<h2>\s*<a\s+href="([^"]+).*?">(.*?)</a>', html)
posts = [r.content for r in dom_parser2.parse_dom(html, 'div', {'id': re.compile('post-\d+')})]
norm_title = scraper_utils.normalize_title(title)
for heading, post in zip(headings, posts):
if not re.search('[._ -]S\d+E\d+[._ -]', heading[1], re.I) and not self.__too_old(post):
post_url, post_title = heading
post_title = re.sub('<[^>]*>', '', post_title)
meta = scraper_utils.parse_movie_link(post_title)
full_title = '%s [%s] (%sp)' % (meta['title'], meta['extra'], meta['height'])
match_year = meta['year']
match_norm_title = scraper_utils.normalize_title(meta['title'])
if (match_norm_title in norm_title or norm_title in match_norm_title) and (not year or not match_year or year == match_year):
result = {'url': scraper_utils.pathify_url(post_url), 'title': scraper_utils.cleanse_title(full_title), 'year': match_year}
results.append(result)
return results