本文整理汇总了Python中resources.lib.modules.cfscrape.create_scraper函数的典型用法代码示例。如果您正苦于以下问题:Python create_scraper函数的具体用法?Python create_scraper怎么用?Python create_scraper使用的例子?那么恭喜您, 这里精选的函数代码示例或许可以为您提供帮助。
在下文中一共展示了create_scraper函数的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于我们的系统推荐出更棒的Python代码示例。
示例1: sources
def sources(self, url, hostDict, hostprDict):
try:
sources = []
scraper = cfscrape.create_scraper()
r = scraper.get(url).content
try:
qual = re.compile('class="quality">(.+?)<').findall(r)
print qual
for i in qual:
if 'HD' in i:
quality = '1080p'
else:
quality = 'SD'
match = re.compile('<iframe src="(.+?)"').findall(r)
for url in match:
valid, host = source_utils.is_host_valid(url, hostDict)
sources.append({'source': host, 'quality': quality, 'language': 'en',
'url': url, 'direct': False, 'debridonly': False})
except Exception:
return sources
except Exception:
failure = traceback.format_exc()
log_utils.log('PLAYMOVIES - Exception: \n' + str(failure))
return sources
return sources
开发者ID:vphuc81,项目名称:MyRepository,代码行数:25,代码来源:Fantastic+(18).py
示例2: __search
def __search(self, titles, year):
try:
query = self.search_link % (urllib.quote_plus(cleantitle.getsearch(titles[0])))
query = urlparse.urljoin(self.base_link, query)
t = cleantitle.get(titles[0])
scraper = cfscrape.create_scraper()
data = scraper.get(query).content
#data = client.request(query, referer=self.base_link)
data = client.parseDOM(data, 'div', attrs={'class': 'result-item'})
r = dom_parser.parse_dom(data, 'div', attrs={'class': 'title'})
r = zip(dom_parser.parse_dom(r, 'a'), dom_parser.parse_dom(data, 'span', attrs={'class': 'year'}))
url = []
for i in range(len(r)):
title = cleantitle.get(r[i][0][1])
title = re.sub('(\d+p|4k|3d|hd|season\d+)','',title)
y = r[i][1][1]
link = r[i][0][0]['href']
if 'season' in title: continue
if t == title and y == year:
if 'season' in link:
url.append(source_utils.strip_domain(link))
print url[0]
return url[0]
else: url.append(source_utils.strip_domain(link))
return url
except:
return
开发者ID:CYBERxNUKE,项目名称:xbmc-addon,代码行数:31,代码来源:mzmovies.py
示例3: __init__
def __init__(self):
self.priority = 1
self.language = ['en']
self.domains = ['xmovies8.tv', 'xmovies8.ru', 'xmovies8.es', 'xmovies8.nz']
self.base_link = 'https://xmovies8.pl'
self.search_link = '/movies/search?s=%s'
self.scraper = cfscrape.create_scraper()
开发者ID:vphuc81,项目名称:MyRepository,代码行数:7,代码来源:xmovies8pl.py
示例4: __get_episode_url
def __get_episode_url(self, data, hostDict):
scraper = cfscrape.create_scraper()
try:
value = "/seasons/" + cleantitle.geturl(data['tvshowtitle']) + '-season-' + data['season']
url = self.base_link + value
print("INFO - " + url)
html = scraper.get(self.base_link)
html = scraper.get(url)
page_list = BeautifulSoup(html.text, 'html.parser')
page_list = page_list.find_all('div', {'class':'episodiotitle'})
ep_page = ''
for i in page_list:
if re.sub(r'\W+', '', data['title'].lower()) in re.sub(r'\W+', '', i.text.lower()):
ep_page = i.prettify()
if ep_page == '': return ''
ep_page = BeautifulSoup(ep_page, 'html.parser').find_all('a')[0]['href']
html = scraper.get(ep_page)
embed = re.findall('<iframe.+?src=\"(.+?)\"', html.text)[0]
url = embed
sources = []
if 'mehliz' in url:
html = scraper.get(url, headers={'referer': self.base_link + '/'})
files = re.findall('file: \"(.+?)\".+?label: \"(.+?)\"', html.text)
for i in files:
try:
sources.append({
'source': 'gvideo',
'quality': i[2],
'language': 'en',
'url': i[0] + "|Referer=https://www.mehlizmovies.com",
'direct': True,
'debridonly': False
})
except Exception:
pass
else:
valid, hoster = source_utils.is_host_valid(url, hostDict)
if not valid: return ''
urls, host, direct = source_utils.check_directstreams(url, hoster)
sources.append({
'source': host,
'quality': urls[0]['quality'],
'language': 'en',
'url': url + "|Referer=https://www.mehlizmovies.com",
'direct': False,
'debridonly': False
})
return sources
except Exception:
print("Unexpected error in Mehlix _get_episode_url Script:")
exc_type, exc_obj, exc_tb = sys.exc_info()
print(exc_type, exc_tb.tb_lineno)
return ""
开发者ID:vphuc81,项目名称:MyRepository,代码行数:60,代码来源:megaHD.py
示例5: __init__
def __init__(self):
self.priority = 1
self.language = ['en']
self.domains = ['hdmega.unblckd.cc']
self.base_link = 'http://hdmega.unblckd.ink/'
self.search_link = '/search-movies/%s.html'
self.scraper = cfscrape.create_scraper()
开发者ID:varunrai,项目名称:repository.magicality,代码行数:7,代码来源:uhd.py
示例6: __init__
def __init__(self):
self.priority = 1
self.language = ['en']
self.domains = ['ondarewatch.com', 'dailytvfix.com']
self.base_link = 'http://www.dailytvfix.com'
self.scraper = cfscrape.create_scraper()
开发者ID:YourFriendCaspian,项目名称:dotfiles,代码行数:7,代码来源:darewatch.py
示例7: __init__
def __init__(self):
self.priority = 0
self.language = ['en']
self.domains = ['tv-release.pw', 'tv-release.immunicity.st']
self.base_link = 'http://tv-release.pw'
self.search_link = '?s=%s'
self.scraper = cfscrape.create_scraper()
开发者ID:varunrai,项目名称:repository.magicality,代码行数:7,代码来源:tvrelease.py
示例8: __init__
def __init__(self):
self.priority = 1
self.language = ['en']
self.domains = ['hdpopcorns.co','hdpopcorns.eu']
self.base_link = 'http://hdpopcorns.co'
self.search_link = '/?s=%s'
self.scraper = cfscrape.create_scraper()
开发者ID:vphuc81,项目名称:MyRepository,代码行数:7,代码来源:hdpopcorns.py
示例9: __init__
def __init__(self):
self.priority = 1
self.language = ['en']
self.domains = ['ultrahdindir.com']
self.base_link = 'http://ultrahdindir.com'
self.post_link = '/index.php?do=search'
self.scraper = cfscrape.create_scraper()
开发者ID:vphuc81,项目名称:MyRepository,代码行数:7,代码来源:ultrahd.py
示例10: __init__
def __init__(self):
self.priority = 0
self.language = ['en']
self.domains = ['watchserieshd.io']
self.base_link = 'https://www4.watchserieshd.io'
self.search_link = 'search.html?keyword=%s'
self.scraper = cfscrape.create_scraper()
开发者ID:vphuc81,项目名称:MyRepository,代码行数:7,代码来源:watchserieshd.py
示例11: __init__
def __init__(self):
self.priority = 1
self.language = ['en']
self.domains = ['movie4k.to']
self._base_link = None
self.search_link = '/movies.php?list=search&search=%s'
self.scraper = cfscrape.create_scraper()
开发者ID:vphuc81,项目名称:MyRepository,代码行数:7,代码来源:movie4kto.py
示例12: episode
def episode(self, url, imdb, tvdb, title, premiered, season, episode):
try:
if url == None: return
scraper = cfscrape.create_scraper()
url = urlparse.parse_qs(url)
url = dict([(i, url[i][0]) if url[i] else (i, '') for i in url])
url['premiered'], url['season'], url['episode'] = premiered, season, episode
try:
clean_title = cleantitle.geturl(url['tvshowtitle'])+'-season-%d' % int(season)
search_url = urlparse.urljoin(self.base_link, self.search_link % clean_title.replace('-', '+'))
r = scraper.get(search_url).content
r = client.parseDOM(r, 'div', {'id': 'movie-featured'})
r = [(client.parseDOM(i, 'a', ret='href'),
re.findall('<b><i>(.+?)</i>', i)) for i in r]
r = [(i[0][0], i[1][0]) for i in r if
cleantitle.get(i[1][0]) == cleantitle.get(clean_title)]
url = r[0][0]
except:
pass
data = scraper.get(url).content
data = client.parseDOM(data, 'div', attrs={'id': 'details'})
data = zip(client.parseDOM(data, 'a'), client.parseDOM(data, 'a', ret='href'))
url = [(i[0], i[1]) for i in data if i[0] == str(int(episode))]
return url[0][1]
except:
return
开发者ID:YourFriendCaspian,项目名称:dotfiles,代码行数:27,代码来源:123hulu.py
示例13: __init__
def __init__(self):
self.priority = 1
self.language = ['en']
self.domains = ['l23movies.com']
self.base_link = 'http://l23movies.com'
self.movies_search_path = ('search-movies/%s.html')
self.scraper = cfscrape.create_scraper()
开发者ID:YourFriendCaspian,项目名称:dotfiles,代码行数:7,代码来源:l23movies.py
示例14: __init__
def __init__(self):
self.priority = 1
self.language = ['en']
self.domains = ['scene-rls.com', 'scene-rls.net']
self.base_link = 'http://scene-rls.net'
self.search_link = '/?s=%s&submit=Find'
self.scraper = cfscrape.create_scraper()
开发者ID:vphuc81,项目名称:MyRepository,代码行数:7,代码来源:Fantastic+(24).py
示例15: sources
def sources(self, url, hostDict, hostprDict):
try:
sources = []
scraper = cfscrape.create_scraper()
r = scraper.get(url).content
try:
match = re.compile('<iframe .+?src="(.+?)"').findall(r)
for url in match:
if 'youtube' in url:
continue
valid, hoster = source_utils.is_host_valid(url, hostDict)
if not valid:
continue
sources.append({
'source': hoster,
'quality': 'SD',
'language': 'en',
'url': url,
'direct': False,
'debridonly': False
})
except Exception:
return sources
except Exception:
failure = traceback.format_exc()
log_utils.log('HackIMDB - Exception: \n' + str(failure))
return sources
return sources
开发者ID:vphuc81,项目名称:MyRepository,代码行数:28,代码来源:Fantastic+(13).py
注:本文中的resources.lib.modules.cfscrape.create_scraper函数示例由纯净天空整理自Github/MSDocs等源码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。 |
请发表评论