def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
if video_type == VIDEO_TYPES.TVSHOW and title:
test_url = '/category/tv-shows/' % (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(
'[/forum/7-1080p-720p-high-definition-movies/]', '',
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 = []
search_url = '/search/' + urllib.quote_plus(title)
html = self._http_get(search_url, require_debrid=False, cache_limit=1)
if video_type == VIDEO_TYPES.TVSHOW:
seen_urls = {}
for _attr, post in dom_parser2.parse_dom(
html, 'div', {'id': re.compile('post-\d+')}):
if CATEGORIES[video_type] not in post: continue
match = re.search(
'<span>\s*TAGS:\s*</span>\s*<a\s+href="([^"]+)[^>]+>([^<]+)',
post, re.I)
if match:
show_url, match_title = match.groups()
if show_url in seen_urls: continue
result = {
'url': scraper_utils.pathify_url(show_url),
'title': scraper_utils.cleanse_title(match_title),
'year': ''
}
seen_urls[show_url] = result
results.append(result)
elif video_type == VIDEO_TYPES.MOVIE:
norm_title = scraper_utils.normalize_title(title)
headings = re.findall('<h2>\s*<a\s+href="([^"]+)[^>]+>(.*?)</a>',
html)
posts = [
result.content for result in dom_parser2.parse_dom(
html, 'div', {'id': re.compile('post-\d+')})
]
for heading, post in zip(headings, posts):
if CATEGORIES[video_type] not in post or self.__too_old(post):
continue
post_url, post_title = heading
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 __get_ok(self, embed, flashvars):
hosters = []
link = flashvars[0].attrs['value']
match = re.search('metadataUrl=([^"]+)', link)
if match:
referer = scraper_utils.cleanse_title(urllib.unquote(embed[0].attrs['data']))
ok_url = scraper_utils.cleanse_title(urllib.unquote(match.group(1)))
html = self._http_get(ok_url, data='ok', headers={'Referer': referer}, cache_limit=.25)
js_data = scraper_utils.parse_json(html, ok_url)
stream_url = js_data.get('movie', {}).get('url')
if stream_url is not None:
host = urlparse.urlparse(stream_url).hostname
hoster = {'multi-part': False, 'host': host, 'class': self, 'quality': QUALITIES.HD720, 'views': None, 'rating': None, 'url': stream_url, 'direct': False, 'subs': 'Turkish Subtitles'}
hosters.append(hoster)
return hosters
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
search_url = scraper_utils.urljoin(self.base_url,
'/search/searchBoxSuggestion')
html = self._http_get(search_url,
params={
'top': 8,
'query': title
},
cache_limit=8)
js_data = scraper_utils.parse_json(html, search_url)
for item in js_data:
entityName = match_title_year = item.get('Value', '')
if entityName:
match_title, match_year2 = scraper_utils.extra_year(
match_title_year)
match_year = str(item.get('ReleaseYear', ''))
if not match_year: match_year = match_year2
match_url = '/ontology/EntityDetails?' + urllib.urlencode(
{
'entityName': entityName,
'ignoreMediaLinkError': 'false'
})
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=''):
scrape = title.lower().replace(' ','+').replace(':', '')
search_url = urlparse.urljoin(self.base_url, '/movie/search/')
search_url += urllib.quote_plus(title)
html = self._http_get(search_url, cache_limit=.25)
results = []
sections = {VIDEO_TYPES.MOVIE: 'movies', VIDEO_TYPES.TVSHOW: 'series'}
fragment = dom_parser.parse_dom(html, 'div', {'id': sections[video_type]})
if fragment:
for item in dom_parser.parse_dom(fragment[0], 'figcaption'):
match = re.search('title="([^"]+)[^>]+href="([^"]+)', item)
if match:
match_title_year, url = match.groups()
match = re.search('(.*?)\s+\(?(\d{4})\)?', match_title_year)
if match:
match_title, match_year = match.groups()
else:
match_title = match_title_year
url = urlparse.urljoin(match_title.group(1), 'watching.html')
match_year = ''
if match_title.startswith('Watch '): match_title = match_title.replace('Watch ', '')
if match_title.endswith(' Online'): match_title = match_title.replace(' Online', '')
if not year or not match_year or year == match_year:
result = {'title': scraper_utils.cleanse_title(match_title), 'year': scraper_utils.pathify_url(url), 'url': match_year}
results.append(result)
return results
def search(self, video_type, title, year, season=''):
if video_type == VIDEO_TYPES.MOVIE:
is_series = 1
else:
is_series = 2
search_url = urlparse.urljoin(
self.base_url,
'/advanced-search/?q[title]=%s&q[is_series]=%s&q[year_from]=%s&q[year_to]=%s'
)
search_url = search_url % (urllib.quote_plus(title), is_series, year,
year)
results = []
html = self._http_get(search_url, cache_limit=.25)
if not re.search('Nothing was found', html):
for match in re.finditer(
'class="name">\s*<a\s+title="([^"]+)\s+\((\d{4})\)"\s+href="([^"]+)',
html):
title, year, url = match.groups('')
if re.search('/season-\d+/episode-\d+', url):
continue # exclude episodes
result = {
'url': scraper_utils.pathify_url(url),
'title': scraper_utils.cleanse_title(title),
'year': year
}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
html = self._http_get(self.base_url,
params={'s': title},
cache_limit=8)
for _attrs, item in dom_parser2.parse_dom(html, 'div',
{'class': 'cover'}):
match = dom_parser2.parse_dom(item, 'a', req=['href', 'title'])
if not match: continue
match_url, match_title_year = match[0].attrs['href'], match[
0].attrs['title']
if re.search('S\d+E\d+', match_title_year, re.I): continue
match_title, match_year = scraper_utils.extra_year(
match_title_year)
if not match_year:
match = re.search('-(\d{4})-', match_url)
if match:
match_year = match.group(1)
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=''):
search_url = urlparse.urljoin(self.base_url, '/search/%s.html')
search_url = search_url % (urllib.quote_plus(title))
html = self._http_get(search_url, cache_limit=8)
results = []
for thumb in dom_parser.parse_dom(html, 'div', {'class': 'thumb'}):
match_title = dom_parser.parse_dom(thumb,
'a', {'class': 'clip-link'},
ret='title')
url = dom_parser.parse_dom(thumb,
'a', {'class': 'clip-link'},
ret='href')
if match_title and url:
match_title, url = match_title[0], url[0]
is_season = re.search('Season\s+(\d+)$', match_title, re.I)
if (not is_season and video_type == VIDEO_TYPES.MOVIE) or (
is_season and video_type == VIDEO_TYPES.SEASON):
match_year = ''
if video_type == VIDEO_TYPES.MOVIE:
match_year = dom_parser.parse_dom(
thumb, 'div', {'class': '[^"]*status-year[^"]*'})
if match_year:
match_year = match_year[0]
else:
if season and int(is_season.group(1)) != int(season):
continue
if not year or not match_year or year == match_year:
result = {
'url': scraper_utils.pathify_url(url),
'title': scraper_utils.cleanse_title(match_title),
'year': match_year
}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
search_url = scraper_utils.urljoin(self.base_url, '/index.php')
data = {'subaction': 'search', 'story': title, 'do': 'search'}
headers = {'Referer': search_url}
html = self._http_get(search_url,
params={'do': 'search'},
data=data,
headers=headers,
cache_limit=1)
fragment = dom_parser2.parse_dom(html, 'div', {'id': 'dle-content'})
if not fragment: return results
for _attrs, item in dom_parser2.parse_dom(fragment[0].content, 'div',
{'class': 'short-film'}):
match = re.search('<h5><a\s+href="([^"]+)[^>]+title="([^"]+)',
item)
if not match: continue
url, match_title = match.groups('')
result = {
'url': scraper_utils.pathify_url(url),
'title': scraper_utils.cleanse_title(match_title),
'year': ''
}
results.append(result)
return results
def search(self, video_type, title, year, season=''):
search_url = self.base_url
if video_type in [VIDEO_TYPES.TVSHOW, VIDEO_TYPES.EPISODE]:
search_url += '/?tv'
search_url += '/index.php?advanced_search='
search_url += urllib.quote_plus(title)
search_url += '&year=' + urllib.quote_plus(str(year))
search_url += '&advanced_search=Search'
html = self._http_get(search_url, cache_limit=.25)
results = []
for element in dom_parser.parse_dom(html, 'div',
{'class': 'list_box_title'}):
match = re.search('href="([^"]+)"\s+title="(?:Watch )?([^"]+)',
element)
if match:
url, match_title_year = match.groups()
match = re.search('(.*?)(?:\s+\(?\s*(\d{4})\s*\)?)',
match_title_year)
if match:
match_title, match_year = match.groups()
else:
match_title = match_title_year
match_year = ''
if not year or not match_year or year == match_year:
result = {
'url': scraper_utils.pathify_url(url),
'title': scraper_utils.cleanse_title(match_title),
'year': match_year
}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
search_url = scraper_utils.urljoin(self.base_url, '/search/')
search_url = scraper_utils.urljoin(search_url,
urllib.quote_plus(title))
html = self._http_get(search_url, require_debrid=True, cache_limit=8)
for _attrs, fragment in dom_parser2.parse_dom(html, 'div',
{'class': 'list'}):
if not dom_parser2.parse_dom(fragment, 'div',
{'class': 'lists_titles'}):
continue
for attrs, match_title_year in dom_parser2.parse_dom(
fragment, 'a', {'class': 'title'}, req='href'):
match_url = attrs['href']
match_title_year = re.sub('</?[^>]*>', '', match_title_year)
is_show = re.search('\(d{4|-\)', match_title_year)
if (is_show and video_type == VIDEO_TYPES.MOVIE) or (
not is_show and video_type == VIDEO_TYPES.TVSHOW):
continue
match_title, match_year = scraper_utils.extra_year(
match_title_year)
if not year or not match_year or year == match_year:
result = {
'url': scraper_utils.pathify_url(match_url),
'title': scraper_utils.cleanse_title(match_title),
'year': match_year
}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
seen_urls = set()
search_url = scraper_utils.urljoin(self.base_url, '/search/')
html = self._http_get(search_url, cache_limit=48)
norm_title = scraper_utils.normalize_title(title)
for _attrs, item in dom_parser2.parse_dom(html, 'div',
{'class': 'category-post'}):
match_url = dom_parser2.parse_dom(item, 'a', req='href')
match_title = dom_parser2.parse_dom(item, 'h3')
if match_url and match_title:
match_url = scraper_utils.pathify_url(
match_url[0].attrs['href'])
match_title = match_title[0].content
if match_url in seen_urls: continue
seen_urls.add(match_url)
if norm_title in scraper_utils.normalize_title(match_title):
result = {
'url': match_url,
'title': scraper_utils.cleanse_title(match_title),
'year': ''
}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
html = self._http_get(self.base_url,
params={'s': title},
cache_limit=1)
for item in dom_parser.parse_dom(html, 'div', {'class': 'item'}):
match = re.search('href="([^"]+).*?alt="([^"]+)', item, re.DOTALL)
if match:
url, match_title_year = match.groups()
match_title, match_year = scraper_utils.extra_year(
match_title_year)
if not match_year:
year_fragment = dom_parser.parse_dom(
item, 'span', {'class': 'year'})
if year_fragment:
match_year = year_fragment[0]
else:
match_year = ''
if not year or not match_year or year == match_year:
result = {
'url': scraper_utils.pathify_url(url),
'title': scraper_utils.cleanse_title(match_title),
'year': match_year
}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
search_title = re.sub('[^A-Za-z0-9. ]', '', title)
url = '/search/%s/' % (urllib.quote(search_title))
url = scraper_utils.urljoin(self.base_url, url)
html = self._http_get(url, cache_limit=48)
norm_title = scraper_utils.normalize_title(title)
for _attrs, item in dom_parser2.parse_dom(html, 'article',
{'class': 'movie-details'}):
match_url = dom_parser2.parse_dom(item, 'a', req='href')
match_title = dom_parser2.parse_dom(item, 'h2',
{'class': 'movie-title'})
match_year = dom_parser2.parse_dom(item, 'div',
{'class': 'movie-year'})
if match_url and match_title:
match_url = match_url[0].attrs['href']
match_title = match_title[0].content
match_year = match_year[0].content if match_year else ''
if norm_title in scraper_utils.normalize_title(
match_title) and (not match_year or not year
or year == match_year):
result = {
'url': scraper_utils.pathify_url(match_url),
'title': scraper_utils.cleanse_title(match_title),
'year': match_year
}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
search_url = scraper_utils.urljoin(self.base_url, '/movies.php')
cookies = {'onlylanguage': 'en', 'lang': 'en'}
params = {'list': 'search', 'search': title}
html = self._http_get(search_url, params=params, cookies=cookies, cache_limit=8)
for _attrs, content in dom_parser2.parse_dom(html, 'TR', {'id': re.compile('coverPreview\d+')}):
match = dom_parser2.parse_dom(content, 'a', req='href')
if not match: continue
match_url, match_title = match[0].attrs['href'], match[0].content
is_show = re.search('\(tvshow\)', match_title, re.I)
if (video_type == VIDEO_TYPES.MOVIE and is_show) or (video_type == VIDEO_TYPES.TVSHOW and not is_show):
continue
match_title = match_title.replace('(TVshow)', '')
match_title = match_title.strip()
match_year = ''
for _attrs, div in dom_parser2.parse_dom(content, 'div'):
match = re.match('\s*(\d{4})\s*', div)
if match:
match_year = match.group(1)
if not year or not match_year or year == match_year:
result = {'url': scraper_utils.pathify_url(match_url), 'title': scraper_utils.cleanse_title(match_title), 'year': match_year}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
html = self._http_get(self.base_url,
params={'s': title},
cache_limit=8)
for _attrs, item in dom_parser2.parse_dom(html, 'h2'):
for attrs, match_title_year in dom_parser2.parse_dom(item,
'a',
req=['href']):
match_url = attrs['href']
match_title_year = re.sub('[^\x00-\x7F]', '', match_title_year)
match = re.search('(.*?)\s+(\d{4})$', match_title_year)
if match:
match_title, match_year = match.groups()
else:
match = re.search('-(\d{4})/?$', match_url)
if match:
match_year = match.groups(1)
else:
match_title, match_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 = []
html = self._http_get(self.base_url,
params={'s': title},
cache_limit=1)
if re.search('Sorry, but nothing matched', html, re.I): return results
norm_title = scraper_utils.normalize_title(title)
for _attrs, item in dom_parser2.parse_dom(html, 'li',
{'class': 'box-shadow'}):
for attrs, _content in dom_parser2.parse_dom(item,
'a',
req=['href',
'title']):
match_url, match_title_year = attrs['href'], attrs['title']
if re.search('S\d{2}E\d{2}', match_title_year): continue
if re.search('TV\s*SERIES', match_title_year, re.I): continue
match_title, match_year = scraper_utils.extra_year(
match_title_year)
if (
not year or not match_year or year == match_year
) and norm_title in scraper_utils.normalize_title(match_title):
result = {
'title': scraper_utils.cleanse_title(match_title),
'year': match_year,
'url': scraper_utils.pathify_url(match_url)
}
results.append(result)
return results
def __get_links(self, url, video):
hosters = []
seen_urls = set()
for search_type in SEARCH_TYPES:
search_url, params = self.__translate_search(url, search_type)
if not search_url: continue
html = self._http_get(search_url, params=params, cache_limit=.5)
js_result = scraper_utils.parse_json(html, search_url)
if js_result.get('status') != 'success':
logger.log('Pron API Error: |%s|%s|: %s' % (search_url, params, js_result.get('message', 'Unknown Error')), log_utils.LOGWARNING)
continue
for result in js_result['result']:
stream_url = result['hosterurls'][0]['url']
if len(result['hosterurls']) > 1: continue
if result['extension'] == 'rar': continue
if stream_url in seen_urls: continue
if scraper_utils.release_check(video, result['title']):
host = urlparse.urlsplit(stream_url).hostname
quality = scraper_utils.get_quality(video, host, self._get_title_quality(result['title']))
hoster = {'multi-part': False, 'class': self, 'views': None, 'url': stream_url, 'rating': None, 'host': host, 'quality': quality, 'direct': False}
hoster['extra'] = scraper_utils.cleanse_title(result['title'])
if video.video_type == VIDEO_TYPES.MOVIE:
meta = scraper_utils.parse_movie_link(hoster['extra'])
else:
meta = scraper_utils.parse_episode_link(hoster['extra'])
if 'format' in meta: hoster['format'] = meta['format']
hosters.append(hoster)
seen_urls.add(stream_url)
return hosters
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
search_url = scraper_utils.urljoin(self.base_url, '/search')
params = {'type': 'movies', 'q': title}
html = self._http_get(search_url, params=params, cache_limit=8)
for _attrs, item in dom_parser2.parse_dom(
html, 'div', {'id': re.compile('movie-\d+')}):
is_tvshow = dom_parser2.parse_dom(item, 'div',
{'class': 'movieTV'})
if (video_type == VIDEO_TYPES.MOVIE
and is_tvshow) or (video_type == VIDEO_TYPES.TVSHOW
and not is_tvshow):
continue
match_url = dom_parser2.parse_dom(item, 'a', req='href')
match_title = dom_parser2.parse_dom(item, 'h4')
if match_url and match_title:
match_title = match_title[0].content
match_url = match_url[0].attrs['href']
match_year = ''
if not year or not match_year or year == match_year:
result = {
'url': scraper_utils.pathify_url(match_url),
'title': scraper_utils.cleanse_title(match_title),
'year': match_year
}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
if not self.include_paid and video_type != VIDEO_TYPES.MOVIE: return []
search_url = scraper_utils.urljoin(self.base_url, '/search.php')
html = self._http_get(search_url, params={'q': title}, cache_limit=.25)
results = []
if video_type == VIDEO_TYPES.MOVIE:
pattern = '<i>\s*Movies\s*</i>(.*)'
else:
pattern = '<i>\s*TV Series\s*</i>(.*)'
match = re.search(pattern, html)
if not match: return results
container = match.group(1)
pattern = "href='([^']+)'>([^<]+)\s*</a>\s*(?:\((\d{4})\))?"
for match in re.finditer(pattern, container):
url, match_title, match_year = match.groups('')
if not year or not match_year or year == match_year:
result = {
'url': scraper_utils.pathify_url(url),
'title': scraper_utils.cleanse_title(match_title),
'year': match_year
}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
if title:
first_letter = title[:1].lower()
if first_letter.isdigit(): first_letter = '0-9'
search_url = '/search.php/%s/' % (first_letter)
search_url = urlparse.urljoin(self.base_url, search_url)
html = self._http_get(search_url, cache_limit=24)
fragment = dom_parser.parse_dom(html, 'div', {'class': 'home'})
if fragment:
norm_title = scraper_utils.normalize_title(title)
for match in re.finditer('''href=["']([^'"]+)[^>]+>([^<]+)''',
fragment[0]):
url, match_title_year = match.groups()
match_title, match_year = scraper_utils.extra_year(
match_title_year)
if norm_title in scraper_utils.normalize_title(
match_title) and (not year or not match_year
or year == match_year):
result = {
'url': scraper_utils.pathify_url(url),
'title': scraper_utils.cleanse_title(match_title),
'year': match_year
}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
search_url = '/Category-FilmsAndTV/Genre-Any/Letter-Any/ByPopularity/1/Search-%s.htm' % (
urllib.quote(title))
search_url = scraper_utils.urljoin(self.base_url, search_url)
html = self._http_get(search_url, cache_limit=8)
results = []
for _attrs, result in dom_parser2.parse_dom(html, 'div',
{'class': 'searchResult'}):
match_url = dom_parser2.parse_dom(result,
'a', {'itemprop': 'url'},
req='href')
match_title = dom_parser2.parse_dom(result, 'span',
{'itemprop': 'name'})
match_year = dom_parser2.parse_dom(result, 'span',
{'itemprop': 'copyrightYear'})
match_year = match_year[0].content if match_year else ''
if match_url and match_title and (not year or not match_year
or year == match_year):
match_url = match_url[0].attrs['href']
match_title = match_title[0].content
if FRAGMENTS[video_type] not in match_url.lower(): continue
result = {
'url': scraper_utils.pathify_url(match_url),
'title': scraper_utils.cleanse_title(match_title),
'year': match_year
}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
search_in = 'm' if video_type == VIDEO_TYPES.MOVIE else 't'
search_url = scraper_utils.urljoin(self.base_url, '/search')
html = self._http_get(search_url,
data={
'searchquery': title,
'searchin': search_in
},
cache_limit=8)
fragment = dom_parser2.parse_dom(html, 'div', {'class': 'search-page'})
if not fragment: return results
fragment = dom_parser2.parse_dom(fragment[0].content, 'table')
if not fragment: return results
for attrs, match_title_year in dom_parser2.parse_dom(
fragment[0].content, 'a', req='href'):
match_url = attrs['href']
match_title, match_year = scraper_utils.extra_year(
match_title_year)
if not year or not match_year or year == match_year:
result = {
'url': scraper_utils.pathify_url(match_url),
'title': scraper_utils.cleanse_title(match_title),
'year': match_year
}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
xml_url = scraper_utils.urljoin(self.base_url, '/series.xml')
xml = self._http_get(xml_url, cache_limit=24)
if not xml: return results
try:
norm_title = scraper_utils.normalize_title(title)
match_year = ''
for element in ET.fromstring(xml).findall('.//dizi'):
name = element.find('adi')
if name is not None and norm_title in scraper_utils.normalize_title(
name.text):
url = element.find('url')
if url is not None and (not year or not match_year
or year == match_year):
result = {
'url': scraper_utils.pathify_url(url.text),
'title': scraper_utils.cleanse_title(name.text),
'year': ''
}
results.append(result)
except (ParseError, ExpatError) as e:
logger.log('Dizilab Search Parse Error: %s' % (e),
log_utils.LOGWARNING)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
headers = {'Referer': self.base_url}
params = {'search': title}
html = self._http_get(self.base_url,
params=params,
headers=headers,
cache_limit=8)
for item in dom_parser.parse_dom(html, 'div', {'class': 'listCard'}):
match_title = dom_parser.parse_dom(item, 'p',
{'class': 'extraTitle'})
match_url = dom_parser.parse_dom(item, 'a', ret='href')
match_year = dom_parser.parse_dom(item, 'p', {'class': 'cardYear'})
if match_url and match_title:
match_url = match_url[0]
match_title = match_title[0]
match_year = match_year[0] if match_year else ''
if not year or not match_year or year == match_year:
result = {
'url': scraper_utils.pathify_url(match_url),
'title': scraper_utils.cleanse_title(match_title),
'year': match_year
}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
html = self._http_get(self.base_url,
params={'s': title},
cache_limit=8)
for _attrs, item in dom_parser2.parse_dom(html, 'div',
{'class': 'result-item'}):
match = dom_parser2.parse_dom(item, 'div', {'class': 'title'})
is_movie = dom_parser2.parse_dom(item, 'span', {'class': 'movies'})
if not is_movie or not match: return results
match = dom_parser2.parse_dom(match[0].content, 'a', req='href')
if not match: return results
match_url, match_title_year = match[0].attrs['href'], match[
0].content
match_title, match_year = scraper_utils.extra_year(
match_title_year)
if not match_year:
match_year = dom_parser2.parse_dom(item, 'span',
{'class': 'year'})
match_year = match_year[0].content if match_year else ''
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 = []
html = self._http_get(self.base_url,
params={'s': title},
cache_limit=4)
for _attrs, movie in dom_parser2.parse_dom(html, 'div',
{'class': 'movie'}):
match_url = dom_parser2.parse_dom(movie, 'a', req='href')
match_title_year = dom_parser2.parse_dom(movie, 'img', req='alt')
if match_url and match_title_year:
match_url = match_url[0].attrs['href']
if re.search('season-\d+-episode\d+', match_url): continue
match_title_year = match_title_year[0].attrs['alt']
match_title, match_year = scraper_utils.extra_year(
match_title_year)
if not match_year:
match_year = dom_parser2.parse_dom(movie, 'div',
{'class': 'year'})
try:
match_year = match_year[0].content
except:
match_year = ''
if not year or not match_year or year == match_year:
result = {
'url': scraper_utils.pathify_url(match_url),
'title': scraper_utils.cleanse_title(match_title),
'year': match_year
}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
search_url = urlparse.urljoin(self.base_url, '/search')
html = self._http_get(search_url, params={'q': title}, cache_limit=8)
results = []
for item in dom_parser.parse_dom(html, 'td', {'class': 'col-md-10'}):
match = re.search('href="([^"]+)">([^<]+)', item)
if match:
url, match_title = match.groups()
result = {'url': scraper_utils.pathify_url(url), 'title': scraper_utils.cleanse_title(match_title), 'year': ''}
results.append(result)
return results
def search(self, video_type, title, year, season=''):
html = self._http_get(self.base_url, cache_limit=8)
results = []
norm_title = scraper_utils.normalize_title(title)
pattern = 'class="[^"]*cat-item.*?href="([^"]+)[^>]+>([^<]+)'
for match in re.finditer(pattern, html):
url, match_title = match.groups()
if norm_title in scraper_utils.normalize_title(match_title):
result = {'url': scraper_utils.pathify_url(url), 'title': scraper_utils.cleanse_title(match_title), 'year': ''}
results.append(result)
return results
def search(self, video_type, title, year, season=''): # @UnusedVariable
results = []
norm_title = scraper_utils.normalize_title(title)
url = scraper_utils.urljoin(self.base_url, '/search/')
headers = {'Referer': self.base_url}
html = self._http_get(url, headers=headers, cache_limit=8)
for _attrs, item in dom_parser2.parse_dom(html, 'li'):
for attrs, _content in dom_parser2.parse_dom(item, 'a', req=['title', 'href']):
match_title, match_url = attrs['title'], attrs['href']
if norm_title in scraper_utils.normalize_title(match_title):
result = {'url': scraper_utils.pathify_url(match_url), 'title': scraper_utils.cleanse_title(match_title), 'year': ''}
results.append(result)
return results