def __search(self, imdb, isMovieSearch):
try:
sHtmlContent = self.scraper.get(self.base_link).content
pattern = '<meta name="csrf-token" content="([^"]+)">'
string = str(sHtmlContent)
token = re.compile(pattern, flags=re.I | re.M).findall(string)
if len(token) == 0:
return #No Entry found?
# first iteration of session object to be parsed for search
sHtmlContent = self.scraper.get(self.search % imdb,
headers={
'X-CSRF-TOKEN':
token[0],
'X-Requested-With':
'XMLHttpRequest'
}).text
content = json.loads(sHtmlContent)
if isMovieSearch:
returnObjects = content["movies"]
else:
returnObjects = content["series"]
return returnObjects
except:
try:
source_faultlog.logFault(__name__, source_faultlog.tagSearch,
imdb)
except:
return
return
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if not url:
return sources
j = self.__get_json(url)
j = [i for i in j['links'] if 'links' in j]
j = [(i['hoster'].lower(), i['id']) for i in j]
j = [(re.sub('hd$', '',
i[0]), i[1], 'HD' if i[0].endswith('hd') else 'SD')
for i in j]
j = [(i[0], i[1], i[2]) for i in j]
for hoster, url, quality in j:
valid, hoster = source_utils.is_host_valid(hoster, hostDict)
if not valid: continue
sources.append({
'source': hoster,
'quality': quality,
'language': 'de',
'url': ('watch/%s' % url),
'direct': False,
'debridonly': False
})
return sources
except:
source_faultlog.logFault(__name__, source_faultlog.tagScrape)
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if not url:
return sources
for idx, items in enumerate(url):
if "clip" in items:
sources.append({
'source': "clipboard.cc",
'quality': 'HD',
'language': 'de',
'url': items,
'direct': True,
'debridonly': False
})
valid, host = source_utils.is_host_valid(items, hostDict)
if not valid: continue
sources.append({
'source': host,
'quality': 'HD',
'language': 'de',
'url': items,
'direct': False,
'debridonly': False,
'checkquality': True
})
return sources
except:
source_faultlog.logFault(__name__, source_faultlog.tagScrape)
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if not url:
return sources
r = cache.get(client.request,
4,
urlparse.urljoin(self.base_link, self.conf_link),
XHR=True)
r = json.loads(r).get('streamer')
r = cache.get(client.request,
4,
r + '%s.mp4/master.m3u8' % url,
XHR=True)
r = re.findall('RESOLUTION\s*=\s*\d+x(\d+).*?\n(http.*?)(?:\n|$)',
r, re.IGNORECASE)
r = [(source_utils.label_to_quality(i[0]), i[1]) for i in r]
for quality, link in r:
sources.append({
'source': 'CDN',
'quality': quality,
'language': 'de',
'url': link,
'direct': True,
'debridonly': False
})
return sources
except:
source_faultlog.logFault(__name__, source_faultlog.tagScrape, url)
return sources
def __search(self, titles, year):
try:
query = self.search_link % (urllib.quote_plus(urllib.quote_plus(cleantitle.query(titles[0]))))
query = urlparse.urljoin(self.base_link, query)
t = [cleantitle.get(i) for i in set(titles) if i]
r = cache.get(client.request, 4, query)
links = dom_parser.parse_dom(r, 'a', attrs={'class': 'coverImage'})
links = [(i.attrs['href'], re.findall('(.*?)\(', i.attrs['title'])[0]) for i in links if year in i.content]
for i in links:
title = i[1]
title = cleantitle.get(title)
if title in t:
return i[0]
else:
continue
return ""
except:
try:
source_faultlog.logFault(__name__, source_faultlog.tagSearch, titles[0])
except:
return
return
def __search(self, titles):
try:
t = [cleantitle.get(i) for i in set(titles) if i]
for title in titles:
oRequest = cRequestHandler(self.base_link + "/", caching = False)
oRequest.addHeaderEntry('Host', 'cinemaxx.cc')
oRequest.addHeaderEntry('Referer', 'https://cinemaxx.cc/')
oRequest.addParameters('do', 'search')
oRequest.addParameters('subaction', 'search')
oRequest.addParameters('story', title)
oRequest.addParameters('full_search', '0')
oRequest.addParameters('search_start', '0')
oRequest.addParameters('result_from', '1')
oRequest.addParameters('submit', 'submit')
oRequest.setRequestType(1)
result = oRequest.request()
links = dom_parser.parse_dom(result, 'div', attrs={'class': 'shortstory-in'})
links = [dom_parser.parse_dom(i, 'a')[0] for i in links]
links = [(i.attrs['href'], i.attrs['title']) for i in links]
links = [i[0] for i in links if any(a in cleantitle.get(i[1]) for a in t)]
if len(links) > 0:
return source_utils.strip_domain(links[0])
return
except:
try:
source_faultlog.logFault(__name__, source_faultlog.tagSearch, titles[0])
except:
return
return
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if not url:
return sources
html = cache.get(requests.get, 6, url)
url_regex = "hls.*?(http.*?m3u8)"
link = re.findall(url_regex, html.content)
link = link[0].replace("\\", "")
sources.append({
'source': 'CDN',
'quality': 'SD',
'language': 'de',
'url': link,
'direct': True,
'debridonly': False,
'info': ''
})
return sources
except:
source_faultlog.logFault(__name__, source_faultlog.tagScrape, link)
return sources
def resolve(self, url):
try:
url = urlparse.urljoin(self.base_link, url)
oRequest = cRequestHandler(url, caching=False)
oRequest.removeBreakLines(False)
oRequest.removeNewLines(False)
content = oRequest.request()
content = client.request(url)
url = dom_parser.parse_dom(content, 'iframe')[0].attrs['src']
recap = recaptcha_app.recaptchaApp()
key = recap.getSolutionWithDialog(
url, "6LeiZSYUAAAAAI3JZXrRnrsBzAdrZ40PmD57v_fs",
self.recapInfo)
print "Recaptcha2 Key: " + key
response = None
if key != "" and "skipped" not in key.lower():
content = client.request(url)
s = dom_parser.parse_dom(content, 'input',
attrs={'name': 's'})[0].attrs['value']
link = client.request(url + '?t=%s&s=%s' % (key, s),
output='geturl')
return link
elif not response or "skipped" in key.lower():
return
except Exception as e:
source_faultlog.logFault(__name__, source_faultlog.tagResolve)
return
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if not url:
return sources
oRequest = cRequestHandler(urlparse.urljoin(self.base_link, url))
content = oRequest.request()
links = dom_parser.parse_dom(content, 'a')
links = [
i for i in links
if 'href' in i.attrs and url in i.attrs['href']
]
links = [(i.attrs['href'], i.attrs['title'].replace('HD', ''),
'720p' if 'HD' in i.attrs['href'] else 'SD')
for i in links if 'title' in i.attrs]
for link, hoster, quality in links:
valid, hoster = source_utils.is_host_valid(hoster, hostDict)
if not valid: continue
sources.append({
'source': hoster,
'quality': quality,
'language': 'de',
'info': 'Recaptcha',
'url': link,
'direct': False,
'debridonly': False,
'captcha': True
})
return sources
except:
source_faultlog.logFault(__name__, source_faultlog.tagScrape)
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if not url:
return sources
data = {'ID': re.findall('\d+', url)[0], 'lang': 2}
data = cache.get(client.request, 4, urlparse.urljoin(self.base_link, self.request_link), post=data, XHR=True)
data = json.loads(data)
if data['status']:
data = [(i, data['links'][i]) for i in data['links'] if 'links' in data]
data = [(i[0], i[1][0], (i[1][1:])) for i in data]
for hoster, quali, links in data:
valid, hoster = source_utils.is_host_valid(hoster, hostDict)
if not valid: continue
quali = int(quali)
quali = '1080p' if quali > 2 else '720p' if quali > 1 else 'SD'
for link in links:
try:
sources.append({'source': hoster, 'quality': quali, 'language': 'de', 'url': self.out_link % link,
'direct': False, 'debridonly': False, 'captcha': True, 'info': 'Recaptcha'})
except:
pass
return sources
except:
source_faultlog.logFault(__name__, source_faultlog.tagScrape)
return sources
def __search(self, imdb, isMovieSearch):
try:
oRequest = cRequestHandler(self.base_link)
oRequest.removeBreakLines(False)
oRequest.removeNewLines(False)
sHtmlContent = oRequest.request()
pattern = '<meta name="csrf-token" content="([^"]+)">'
string = str(sHtmlContent)
token = re.compile(pattern, flags=re.I | re.M).findall(string)
if len(token) == 0:
return #No Entry found?
# first iteration of session object to be parsed for search
oRequest = cRequestHandler(self.search % imdb)
oRequest.removeBreakLines(False)
oRequest.removeNewLines(False)
oRequest.addHeaderEntry('X-CSRF-TOKEN', token[0])
oRequest.addHeaderEntry('X-Requested-With', 'XMLHttpRequest')
sHtmlContent = oRequest.request()
content = json.loads(sHtmlContent)
if isMovieSearch:
returnObjects = content["movies"]
else:
returnObjects = content["series"]
return returnObjects
except:
try:
source_faultlog.logFault(__name__, source_faultlog.tagSearch,
imdb)
except:
return
return
def __search(self, titles):
try:
query = self.search_link % urllib.quote_plus(
cleantitle.query(titles[0]))
query = urlparse.urljoin(self.base_link, query)
t = [cleantitle.get(i) for i in set(titles) if i]
r = client.request(query)
body = dom_parser.parse_dom(r,
'div',
attrs={'class':
'content_body'})[1].content
r = dom_parser.parse_dom(body, 'a', req='href')
r = [(i.attrs['href'],
i.content.lower().replace('<b>', '').replace('</b>', ''))
for i in r if i]
r = [i for i in r if '<' not in i[1]]
r = [i[0] for i in r if cleantitle.get(i[1]) in t]
if len(r) > 0:
return source_utils.strip_domain(r[0])
return ""
except:
try:
source_faultlog.logFault(__name__, source_faultlog.tagSearch,
titles[0])
except:
return
return
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if not url:
return
url = urlparse.urljoin(self.base_link, url)
r = client.request(url)
r = r.replace('\n', ' ')
r = dom_parser.parse_dom(r, 'div', attrs={'class': 'fullstory'})
r = dom_parser.parse_dom(r, 'div', attrs={'class': 'row'})
r = dom_parser.parse_dom(r, 'div', attrs={'class': 'inner'})
r = dom_parser.parse_dom(r, 'a', req='href')
r = [i.attrs['href'].strip() for i in r]
for link in r:
valid, host = source_utils.is_host_valid(link, hostDict)
if not valid: continue
sources.append({
'source': host,
'quality': 'SD',
'language': 'de',
'url': link,
'direct': False,
'debridonly': False
})
return sources
except:
source_faultlog.logFault(__name__, source_faultlog.tagScrape)
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if not url:
return sources
query = urlparse.urljoin(self.base_link, url)
oRequest = cRequestHandler(query)
oRequest.removeBreakLines(False)
oRequest.removeNewLines(False)
content = oRequest.request()
quality = dom_parser.parse_dom(content,
'div',
attrs={'class': 'tabformat'})
for quali in quality:
if len(quality) > 1:
oRequest = cRequestHandler(
urlparse.urljoin(
self.base_link,
dom_parser.parse_dom(quali, 'a')[0].attrs['href']))
oRequest.removeBreakLines(False)
oRequest.removeNewLines(False)
content = oRequest.request()
self.__getRelease(sources, content, hostDict)
self.__getRelease(sources, content, hostDict)
if len(sources) == 0:
raise Exception()
return sources
except:
source_faultlog.logFault(__name__, source_faultlog.tagScrape, url)
return sources
def __search(self, titles, year):
try:
t = [cleantitle.get(i) for i in set(titles) if i]
y = [
'%s' % str(year),
'%s' % str(int(year) + 1),
'%s' % str(int(year) - 1), '0'
]
r = client.request(
urlparse.urljoin(self.base_link, self.search_link),
post=urllib.urlencode({'val': cleantitle.query(titles[0])}),
XHR=True)
r = dom_parser.parse_dom(r, 'li')
r = dom_parser.parse_dom(r, 'a', req='href')
r = [(i.attrs['href'], i.content,
re.findall('\((\d{4})', i.content)) for i in r]
r = [(i[0], i[1], i[2][0] if i[2] else '0') for i in r]
r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y]
if len(r) > 0:
r = r[0]
else:
return
return source_utils.strip_domain(r)
except:
source_faultlog.logFault(__name__, source_faultlog.tagSearch)
return
def __search(self, imdb):
try:
r = client.request(
urlparse.urljoin(self.base_link, self.search_link % imdb))
r = dom_parser.parse_dom(r, 'a', req='href')
r = [i.attrs['href'] for i in r if i]
url = None
if len(r) > 1:
for i in r:
data = client.request(urlparse.urljoin(self.base_link, i))
data = re.compile('(imdbid\s*[=|:]\s*"%s"\s*,)' % imdb,
re.DOTALL).findall(data)
if len(data) >= 1:
url = i
elif len(r) > 0:
url = r[0]
if url:
return source_utils.strip_domain(url)
except:
try:
source_faultlog.logFault(__name__, source_faultlog.tagSearch,
imdb)
except:
return
return
def __search(self, imdb):
try:
l = ['1', '15']
r = client.request(
urlparse.urljoin(self.base_link, self.search_link % imdb))
r = dom_parser.parse_dom(r,
'table',
attrs={'id': 'RsltTableStatic'})
r = dom_parser.parse_dom(r, 'tr')
r = [(dom_parser.parse_dom(i, 'a', req='href'),
dom_parser.parse_dom(i,
'img',
attrs={'alt': 'language'},
req='src')) for i in r]
r = [(i[0][0].attrs['href'], i[0][0].content, i[1][0].attrs['src'])
for i in r if i[0] and i[1]]
r = [(i[0], i[1], re.findall('.+?(\d+)\.', i[2])) for i in r]
r = [(i[0], i[1], i[2][0] if len(i[2]) > 0 else '0') for i in r]
r = sorted(r, key=lambda i: int(i[2])) # german > german/subbed
r = [i[0] for i in r if i[2] in l]
if len(r) > 0:
return source_utils.strip_domain(r[0])
return ""
except:
try:
source_faultlog.logFault(__name__, source_faultlog.tagSearch,
imdb)
except:
return
return
def resolve(self, url):
try:
url = urlparse.urljoin(self.base_link, url)
recap = recaptcha_app.recaptchaApp()
key = recap.getSolutionWithDialog(
url, "6LeERkUUAAAAAJH4Yqk-gQH1N6psg0KCuEq_Lkxf",
self.recapInfo)
print "Recaptcha2 Key: " + key
response = None
if key != "" and "skipped" not in key.lower():
response = self.scraper.post(
url,
data={'g-recaptcha-response': key},
allow_redirects=True)
elif not response or "skipped" in key.lower():
return
if response is not None:
url = response.url
if self.base_link not in url:
if 'google' in url:
return directstream.google(url)[0]['url']
return url
except Exception as e:
source_faultlog.logFault(__name__, source_faultlog.tagResolve)
return
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if not url:
return sources
episode = None
season = None
if isinstance(url, list):
season, episode, url = url
url = urlparse.urljoin(self.base_link, url)
oRequest = cRequestHandler(url, caching=False)
content = oRequest.request()
quality = re.findall(r'\<span class=\"film-rip ignore-select\"><a href=\"https://cinemaxx.cc/xfsearch/rip/(.*?)/', content)[0]
if "HD" in quality:
quality = '1080p'
else:
quality = 'SD'
link = dom_parser.parse_dom(content, 'div', attrs={'id': 'full-video'})
if season:
try:
link = re.findall("vk.show\(\d+,(.*?)\)", link[0].content)[0]
link = re.findall("\[(.*?)\]", link)[int(season)-1]
link = re.findall("'(.*?)'", link)
link = link[int(episode)-1]
valid, hoster = source_utils.is_host_valid(link, hostDict)
if valid:
sources.append({'source': hoster, 'quality': quality, 'language': 'de', 'info': '',
'url': link, 'direct': False, 'debridonly': False, 'checkstreams': True})
else: pass
except:
#we have a tvshow, but no seasons to choose
#cinemaxx can host specific seasons, its stated in the url (i.e. http://cinemaxx.cc/serien/743-homeland-7-staffel.html)
link = dom_parser.parse_dom(link, 'iframe')
link = link[0].attrs['src']
valid, hoster = source_utils.is_host_valid(link, hostDict)
if valid:
sources.append({'source': hoster, 'quality': quality, 'language': 'de', 'info': '',
'url': link, 'direct': False, 'debridonly': False, 'checkstreams': True})
else: pass
else:
link = dom_parser.parse_dom(link, 'iframe')
link = link[0].attrs['src']
valid, hoster = source_utils.is_host_valid(link, hostDict)
if valid:
sources.append({'source': hoster, 'quality': quality, 'language': 'de', 'info': '',
'url': link, 'direct': False, 'debridonly': False, 'checkstreams': True})
else: pass
if len(sources) == 0:
raise Exception()
return sources
except:
source_faultlog.logFault(__name__, source_faultlog.tagScrape, url)
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if not url:
return sources
content = cache.get(client.request, 4,
urlparse.urljoin(self.base_link, url))
hoster = re.findall('blank"[^>]*href="([^"]+)">', content)
for link in hoster:
link = link.strip()
quali, info = source_utils.get_release_quality(link)
valid, hoster = source_utils.is_host_valid(link, hostDict)
if not valid: continue
sources.append({
'source': hoster,
'quality': quali,
'language': 'de',
'info': info,
'url': link,
'direct': False,
'debridonly': False,
'checkquality': True
})
return sources
except:
source_faultlog.logFault(__name__, source_faultlog.tagScrape, url)
return sources
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if not url:
return sources
data = urlparse.parse_qs(url)
data = dict([(i, data[i][0]) if data[i] else (i, '') for i in data])
url = data.get('url')
episode = int(data.get('episode', 1))
r = client.request(urlparse.urljoin(self.base_link, url))
r = {'': dom_parser.parse_dom(r, 'div', attrs={'id': 'gerdub'}), 'subbed': dom_parser.parse_dom(r, 'div', attrs={'id': 'gersub'})}
for info, data in r.iteritems():
data = dom_parser.parse_dom(data, 'tr')
data = [dom_parser.parse_dom(i, 'a', req='href') for i in data if dom_parser.parse_dom(i, 'a', attrs={'id': str(episode)})]
data = [(link.attrs['href'], dom_parser.parse_dom(link.content, 'img', req='src')) for i in data for link in i]
data = [(i[0], i[1][0].attrs['src']) for i in data if i[1]]
data = [(i[0], re.findall('/(\w+)\.\w+', i[1])) for i in data]
data = [(i[0], i[1][0]) for i in data if i[1]]
for link, hoster in data:
valid, hoster = source_utils.is_host_valid(hoster, hostDict)
if not valid: continue
sources.append({'source': hoster, 'quality': 'SD', 'language': 'de', 'url': link, 'info': info, 'direct': False, 'debridonly': False})
return sources
except:
source_faultlog.logFault(__name__,source_faultlog.tagScrape)
return sources
def __search(self, titles):
try:
t = [cleantitle.get(i) for i in set(titles) if i]
for title in titles:
params = {'a': '2', 'query': title}
content = cache.get(client.request,
4,
self.search_link,
post=params)
if content is not None and "noEntry" not in content:
content = content.replace('entryLink" <a=""', 'entryLink"')
entryLinks = dom_parser.parse_dom(
content, 'a', attrs={"class": "entryLink"})
if len(entryLinks) == 0: continue
links = [
link.attrs['href'] for link in entryLinks
if cleantitle.get(link.content) in t
]
if len(links) > 0:
return source_utils.strip_domain(links[0])
return
except:
try:
source_faultlog.logFault(__name__, source_faultlog.tagSearch,
titles[0])
except:
return
return
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if not url:
return sources
query = urlparse.urljoin(self.base_link, url)
r = cache.get(client.request, 4, query)
links = dom_parser.parse_dom(r, 'div', attrs={'id': 'tab-plot_german'})
links = dom_parser.parse_dom(links, 'tbody')
links = dom_parser.parse_dom(links, 'tr')
links = [(dom_parser.parse_dom(i, 'a')[0],
dom_parser.parse_dom(i, 'td', attrs={'class': 'votesCell'})[0])
for i in links if "gif" in i.content]
links = [(i[0][1], i[0].attrs['href'], source_utils.get_release_quality(i[1].content)[0]) for i in links]
for hoster, link, quality in links:
valid, hoster = source_utils.is_host_valid(hoster, hostDict)
if not valid:
continue
if '?' in link:
link = urlparse.urljoin(url, link)
sources.append({'source': hoster, 'quality': quality, 'language': 'de', 'url': link, 'direct': False,
'debridonly': False, 'checkquality': True})
if len(sources) == 0:
raise Exception()
return sources
except:
source_faultlog.logFault(__name__, source_faultlog.tagScrape, url)
return sources
def __search(self, titles, year, season='0'):
try:
query = self.search_link % (urllib.quote_plus(
cleantitle.query(titles[0])))
query = urlparse.urljoin(self.base_link, query)
titles = [cleantitle.get(i) for i in set(titles) if i]
cache.cache_clear()
searchResult = cache.get(self.scraper.get, 4, query).content
results = re.findall(
r'<div class=\"movie-title\">\n((?s).*?)\"(.*?)\">(.*?)</a>',
searchResult)
usedIndex = 0
#Find result with matching name and season
for x in range(0, len(results)):
title = cleantitle.get(results[x][2])
if any(i in title for i in titles):
return source_utils.strip_domain(results[x][1])
usedIndex += 1
return
except:
try:
source_faultlog.logFault(__name__, source_faultlog.tagSearch,
titles[0])
except:
return
return
def __search(self, titles, year):
try:
t = [cleantitle.get(i) for i in set(titles) if i]
y = [
'%s' % str(year),
'%s' % str(int(year) + 1),
'%s' % str(int(year) - 1), '0'
]
r = cache.get(self.__get_json, 12, "series")
r = [(i.get('id'), i.get('series')) for i in r]
r = [(i[0], i[1], re.findall('(.+?) \((\d{4})\)?', i[1]))
for i in r if cleantitle.get(i[1]) in t]
r = [(i[0], i[2][0][0] if len(i[2]) > 0 else i[1],
i[2][0][1] if len(i[2]) > 0 else '0') for i in r]
r = sorted(r, key=lambda i: int(i[2]),
reverse=True) # with year > no year
r = [i[0] for i in r if i[2] in y]
if len(r) > 0:
r = r[0]
else:
return
return 'series/%s/' % r
except:
source_faultlog.logFault(__name__, source_faultlog.tagSearch)
return
def sources(self, url, hostDict, hostprDict):
sources = []
try:
if not url:
return sources
r = cache.get(client.request, 4, urlparse.urljoin(self.base_link, url))
r = dom_parser.parse_dom(r, 'div', attrs={'class': 'hosterSiteVideo'})
r = dom_parser.parse_dom(r, 'li', attrs={'data-lang-key': re.compile('[1|2|3]')})
r = [(i.attrs['data-link-target'], dom_parser.parse_dom(i, 'h4'),
'subbed' if i.attrs['data-lang-key'] == '3' else '' if i.attrs['data-lang-key'] == '1' else 'subbed' if i.attrs['data-lang-key'] == '2' else '') for i
in r]
r = [(i[0], re.sub('\s(.*)', '', i[1][0].content), 'HD' if 'hd' in i[1][0][1].lower() else 'SD', i[2]) for i in r]
for link, host, quality, info in r:
print host
#if 'HD' in quality: host = re.findall('(.+?)\s*<br', host)[0]
valid, host = source_utils.is_host_valid(host, hostDict)
if not valid: continue
sources.append(
{'source': host, 'quality': quality, 'language': 'de', 'url': link, 'info': info, 'direct': False,
'debridonly': False})
return sources
except:
source_faultlog.logFault(__name__, source_faultlog.tagScrape, url)
return sources
def __search(self, titles, year, content):
try:
t = [cleantitle.get(i) for i in set(titles) if i]
c = client.request(urlparse.urljoin(self.base_link, self.year_link % int(year)), output='cookie')
p = urllib.urlencode({'search': cleantitle.query(titles[0])})
c = client.request(urlparse.urljoin(self.base_link, self.search_link), cookie=c, post=p, output='cookie')
r = client.request(urlparse.urljoin(self.base_link, self.type_link % content), cookie=c, post=p)
r = dom_parser.parse_dom(r, 'table', attrs={'width': '100%'})[0].content
r = dom_parser.parse_dom(r, 'tr')
r = [(dom_parser.parse_dom(i.content, 'a')) for i in r if 'otherLittles' in i.content]
r = sorted(r, key=lambda i: int(i[1].content), reverse=True) # with year > no year
links = [i[0].attrs['href'] for i in r if
(cleantitle.get(i[0].content).partition('<')[0] in t) and i[1].content == year]
if len(r) > 0:
return source_utils.strip_domain(links[0])
return ""
except:
source_faultlog.logFault(__name__, source_faultlog.tagSearch)
return
def __search(self, titles, year):
try:
query = self.search_link % urllib.quote_plus(cleantitle.query(titles[0]))
query = urlparse.urljoin(self.base_link, query)
t = [cleantitle.get(i) for i in set(titles) if i]
y = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0']
r = client.request(query, XHR=True)
if r and r.startswith('{'): r = '[%s]' % r
r = json.loads(r)
r = [(i['url'], i['name']) for i in r if 'name' in i and 'url' in i]
r = [(i[0], i[1], re.findall('(.+?) \(*(\d{4})?\)*$', i[1])) for i in r]
r = [(i[0], i[2][0][0] if len(i[2]) > 0 else i[1], i[2][0][1] if len(i[2]) > 0 else '0') for i in r]
r = sorted(r, key=lambda i: int(i[2]), reverse=True) # with year > no year
r = [i[0] for i in r if cleantitle.get(i[1]) in t and i[2] in y]
if len(r) > 0:
r = r[0]
else:
return
url = source_utils.strip_domain(r)
url = url.replace('serien/', '')
return url
except:
try:
source_faultlog.logFault(__name__, source_faultlog.tagSearch, titles[0])
except:
return
return
def __search(self, imdb):
try:
oRequest = cRequestHandler(
urlparse.urljoin(self.base_link, self.search_link % imdb))
oRequest.removeBreakLines(False)
oRequest.removeNewLines(False)
r = oRequest.request()
r = re.findall(r'linkto\".href=\"(.*?)\"\>', r)
url = None
if len(r) > 1:
for i in r:
oRequest = cRequestHandler(
urlparse.urljoin(self.base_link, i))
oRequest.removeBreakLines(False)
oRequest.removeNewLines(False)
data = oRequest.request()
data = re.compile('(imdbid\s*[=|:]\s*"%s"\s*,)' % imdb,
re.DOTALL).findall(data)
if len(data) >= 1:
url = i
elif len(r) > 0:
url = r[0]
if url:
return source_utils.strip_domain(url)
except:
try:
source_faultlog.logFault(__name__, source_faultlog.tagSearch,
imdb)
except:
return
return
def __search(self, titles, imdb, year):
try:
query = self.search_link % (urllib.quote_plus(cleantitle.query(titles[0])))
query = urlparse.urljoin(self.base_link, query)
t = [cleantitle.get(i) for i in set(titles) if i]
y = ['%s' % str(year), '%s' % str(int(year) + 1), '%s' % str(int(year) - 1), '0']
r = cache.get(client.request, 4, query, XHR=True)
r = json.loads(r)
r = [(i.get('title'), i.get('custom_fields', {})) for i in r.get('posts', [])]
r = [(i[0], i[1]) for i in r if i[0] and i[1]]
r = [(i[0], i[1].get('Streaming', ['']), i[1].get('Jahr', ['0']), i[1].get('IMDb-Link', [''])) for i in r if i]
r = [(i[0], i[1][0], i[2][0], re.findall('.+?(tt\d+).*?', i[3][0])) for i in r if i[0] and i[1] and i[2] and i[3]]
r = [i[1] for i in r if imdb in i[3] or (cleantitle.get(i[0]) in t and i[2] in y)]
if len(r) > 0 :
return source_utils.strip_domain(r[0])
return ""
except:
try:
source_faultlog.logFault(__name__, source_faultlog.tagSearch, titles[0])
except:
return
return
